[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN117351001B - Surface defect identification method for regenerated aluminum alloy template - Google Patents

Surface defect identification method for regenerated aluminum alloy template Download PDF

Info

Publication number
CN117351001B
CN117351001B CN202311537634.6A CN202311537634A CN117351001B CN 117351001 B CN117351001 B CN 117351001B CN 202311537634 A CN202311537634 A CN 202311537634A CN 117351001 B CN117351001 B CN 117351001B
Authority
CN
China
Prior art keywords
defect
image
preset
result
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311537634.6A
Other languages
Chinese (zh)
Other versions
CN117351001A (en
Inventor
刘君
卢小军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Delta Aluminium Industry Co ltd
Original Assignee
Delta Aluminium Industry Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Delta Aluminium Industry Co ltd filed Critical Delta Aluminium Industry Co ltd
Priority to CN202311537634.6A priority Critical patent/CN117351001B/en
Publication of CN117351001A publication Critical patent/CN117351001A/en
Application granted granted Critical
Publication of CN117351001B publication Critical patent/CN117351001B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • G06T7/0008Industrial image inspection checking presence/absence
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/54Extraction of image or video features relating to texture
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which relates to the technical field of aluminum alloy production and comprises the following steps: step 1: acquiring a real-time image of a template and preprocessing to obtain an image to be processed; step 2: extracting features of an image to be processed, generating defect feature information, inputting the defect feature information into a preset defect recognition model, and recognizing defects to obtain a first result; step 3: acquiring historical defect image information, establishing a historical defect image set, and simultaneously inputting a first result and the historical defect image set into a preset image comparison model for comparison analysis to obtain a second result; step 4: and screening in a preset model database based on the defect characteristic information to obtain a defect analysis model, and inputting a first result and a second result into the defect analysis model to perform defect analysis to obtain a final identification result. The invention can improve the recognition precision of the surface defects of the regenerated aluminum alloy template, thereby improving the quality control level of aluminum alloy production.

Description

Surface defect identification method for regenerated aluminum alloy template
Technical Field
The invention relates to the technical field of aluminum alloy production, in particular to a method for identifying surface defects of a regenerated aluminum alloy template.
Background
An aluminum alloy template is a mold or model for manufacturing various aluminum alloy articles. It is made of aluminium alloy material and has the features of high strength, high wear resistance, high corrosion resistance, etc. Aluminum alloy templates are widely used in various fields such as the automotive industry, aerospace, construction and architecture, the electronics and electrical industry, and the like.
At present, along with the improvement of energy conservation and environmental protection consciousness in industrial production, a regenerated aluminum alloy template technology is gradually applied to the field of aluminum alloy production, and the regenerated aluminum alloy template refers to an aluminum alloy template manufactured by recycling recovered waste aluminum materials. Although the use of the regenerated aluminum alloy template is helpful for promoting the circular economy and sustainable development, the resource consumption and the environmental impact are reduced. However, due to uncertainty and uneven quality of the waste aluminum materials, physical characteristics and product performance of the regenerated aluminum alloy template have a certain gap from those of the original template, so that quality control and detection of the regenerated aluminum alloy template are particularly important.
Therefore, the invention provides a method for identifying the surface defects of the regenerated aluminum alloy template.
Disclosure of Invention
The invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which is used for improving the identification precision of the surface defects of the regenerated aluminum alloy template, so as to improve the quality level of a regenerated aluminum alloy template finished product, thereby improving the quality control level of aluminum alloy production.
The invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
Step 1: acquiring a real-time image of a template through image acquisition equipment, and preprocessing the real-time image to obtain an image to be processed;
Step 2: extracting features of the image to be processed to generate defect feature information, and inputting the defect feature information into a preset defect recognition model to perform defect recognition to obtain a first result;
step 3: acquiring historical defect image information of a template, establishing a historical defect image set, and simultaneously inputting the first result and the historical defect image set into a preset image comparison model for comparison analysis to obtain a second result;
Step 4: and screening in a preset model database based on the defect characteristic information to obtain a defect analysis model, and inputting the first result and the second result into the defect analysis model to perform defect analysis to obtain a final identification result.
Preferably, in step 1, the method includes:
Image acquisition is carried out on the surface of the template from a preset angle through image acquisition equipment to obtain a real-time image, and a real-time image set is established according to the time sequence of the real-time image;
Preprocessing each real-time image in the real-time image set, and calibrating the real-time image meeting a preset first threshold value as an image to be processed.
Preferably, in step 2, it includes:
Acquiring images to be processed in the real-time image set, and screening out an adaptive feature extraction strategy from a preset strategy database;
selecting a proper feature extraction method from a preset strategy-method comparison table based on the feature extraction strategy;
and carrying out feature extraction on the image to be processed based on the feature extraction method to generate defect feature information.
Preferably, in step2, further includes:
Acquiring model information from a preset feature-model matching table based on the defect feature information, and selecting a corresponding preset defect identification model from a preset model database based on the model information;
And inputting the defect characteristic information into the preset defect identification model to identify the defects, so as to obtain a first result.
Preferably, in step 3, it includes:
Based on the defect characteristic information and the first result, screening historical defect image information with the matching degree larger than the first matching degree from a historical defect database;
performing defect classification on the historical defect image information, and establishing a historical defect image set based on classification results;
and meanwhile, comparing and analyzing the first result and the historical defect image set by using a preset image comparison model to obtain a second result.
Preferably, in step3, further includes:
performing content analysis on the defect characteristic information, and establishing a defect characteristic data packet based on analysis content;
Classifying and analyzing all defect characteristics in the defect characteristic data packet, and establishing a defect characteristic classification table;
Combining a preset category-factor matching table to obtain a first screening factor of each feature category in the defect feature classification table;
meanwhile, inputting the defect characteristic data packet into a preset characteristic analysis model for parameter calculation to obtain characteristic parameters corresponding to each defect characteristic;
Acquiring a second screening factor of each defect characteristic parameter by using a preset parameter-factor comparison table based on the characteristic parameter of each defect characteristic;
Screening historical defect image information with the matching degree larger than the first matching degree in a historical defect database by combining the first screening factor and the second screening factor;
classifying and analyzing the historical defect image information according to the characteristic information carried in the historical defect image information, and establishing a historical defect image set according to the classifying and analyzing result and the characteristic parameters of the corresponding defect characteristics;
Extracting the defect characteristics under the same classification and corresponding characteristic parameters in the defect characteristic classification table and the historical defect image set, and establishing a comparison data packet;
and inputting the comparison data packet corresponding to each characteristic category into a preset image comparison analysis model for comparison analysis by combining the first result to obtain a second result.
Preferably, in step 4, the method includes:
Performing cluster analysis on each defect feature in the defect feature information, simultaneously counting the number of defect features in the same category in a cluster analysis result, and performing descending arrangement according to the number of defect features contained in each category to obtain a feature descending list;
Extracting feature categories with ordinal numbers larger than the first ordinal number in the feature descending list, and obtaining first screening parameters according to a preset category-parameter comparison list;
Meanwhile, judging the priority of each defect feature in the defect feature information and a preset feature-priority comparison table to obtain the priority corresponding to each defect feature;
based on each defect feature and the corresponding priority, acquiring a second screening parameter corresponding to each defect feature by combining a preset priority-parameter comparison table;
inputting the first screening parameters and the second screening parameters into a preset model database for model matching to obtain a defect analysis model with matching degree larger than the second matching degree;
Acquiring first type information corresponding to the first result, and binding the first type information with the first result to obtain first binding information;
Inputting the first binding information and the second result into the defect analysis model, and carrying out parameter analysis on the characteristic parameters under the same characteristic category to obtain a final identification result.
Preferably, based on the feature extraction method, feature extraction is performed on the image to be processed to generate defect feature information, including:
Intercepting a plurality of square gray images with different preset sizes from the image to be processed and presetting a filtering function;
Filtering each gray image in m scales and n preset directions through a preset filter function to obtain m x n filter kernels corresponding to each square gray image;
Fusing all m x n filter kernels of the square gray images to obtain a first texture image;
Respectively acquiring a brightness average ave1 of the first texture image and a brightness average ave2 of a corresponding real-time image;
Adjusting the real-time image with the brightness average ave1 to obtain a first image to be analyzed, and simultaneously adjusting the first texture image with the brightness average ave2 to obtain a second image to be analyzed;
when a brightness value r1 i of an ith pixel point in the real-time image meets the condition that ave 1-delta 1 is less than or equal to r1 i and less than or equal to ave1+delta 1, replacing the ith pixel point with a brightness average value ave1, otherwise, keeping the ith pixel point unchanged, and further obtaining a first image to be analyzed, wherein delta 1 represents brightness variance correspondingly obtained when no defect exists on the surface of the regenerated aluminum alloy template;
Meanwhile, when the brightness value r2 j of the j-th pixel point in the first texture image meets the condition that ave 2-delta 2 is less than or equal to r2 j and less than or equal to ave2+delta 2, replacing the j-th pixel point with a brightness average value ave2, otherwise, keeping the j-th pixel point unchanged, and further obtaining a second image to be analyzed, wherein delta 2 represents brightness variances of the first texture image and the real-time image under all the same coordinates in which defects are determined preliminarily;
Acquiring first brightness variances sigma 1 2 of the first image to be analyzed and the real-time image, and simultaneously acquiring second brightness variances sigma 2 2 of the second image to be analyzed and the first texture image;
Obtaining the image quality W of the first texture image according to the brightness average ave1, the brightness average ave2, the first brightness variance sigma 1 2 and the second brightness variance sigma 2 2;
Wherein, oc 1, oc2, oc3 represent importance parameters; n1 represents the number of pixel brightness substitutions existing in the first image to be analyzed; n3 represents the total number of pixel points in the first image to be analyzed; n2 represents the number of pixel brightness substitutions in the second image to be analyzed; n4 represents the total number of pixel points in the second image to be analyzed;
If the image quality W is greater than or equal to a threshold quality, extracting features based on the first texture image;
otherwise, determining the adjustment definition from a difference-definition adjustment mapping table according to the difference value of the image quality W and the threshold quality, respectively acquiring an average gray value and an average fuzzy value of each square gray image, and analyzing based on the adjustment definition to obtain a weak texture region and a detail texture region;
Following the weak texture region First definition multiple adjustment and detail texture area adjustment according to/>Performing second definition multiple adjustment to obtain a second texture image, wherein G1 (avehd, avemh) represents an adjusting function based on an average gray value avehd and an average blur value avemh; β1, β2 represent adjustment weights; delta (mh) represents a variable based on ambiguity mh; delta (hd, bd) represents a variable based on the gradation value hd and the standard gradation value bd; g2 (avehd, avemh, maxmh, avemh 1) represents an adjustment function based on the average gray value avehd, the average blur value avemh, the maximum blur maxmh, and the average blur avemh1 satisfying the normal distribution probability; [] Representing a rounding symbol;
And extracting features based on the second texture image.
The implementation principle and the beneficial effects of the invention are as follows: firstly, preprocessing an obtained aluminum alloy template image, improving the image quality of a real-time image, and then extracting defect characteristics of the image to be processed through a preset filter function, so as to generate defect characteristic information and a metal surface image; and then, identifying the defects on the surface of the template in the defect identification model to obtain a first result, and performing comparison analysis with the matched historical defect image to generate a second result, wherein the current defects are judged by taking the historical data as a reference, so that the identification precision of the defects is greatly improved, and further, the final defect identification result is obtained by comprehensively analyzing and processing the first result and the second result, the defects are identified and analyzed from a multiple angle, the possibility of misjudgment is reduced, the detection precision of the defects is greatly improved, and the quality control level of the regenerated aluminum alloy template is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic flow chart of a method for identifying surface defects of a regenerated aluminum alloy template in an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for identifying surface defects of a recycled aluminum alloy template, including:
step 1: acquiring a real-time image of a template through image acquisition equipment, and preprocessing the real-time image to obtain an image to be processed;
step 2: extracting features of an image to be processed, generating defect feature information, inputting the defect feature information into a preset defect recognition model for defect recognition, and obtaining a first result;
step 3: acquiring historical defect image information of a template, establishing a historical defect image set, and simultaneously inputting a first result and the historical defect image set into a preset image comparison model for comparison analysis to obtain a second result;
Step 4: and screening in a preset model database based on the defect characteristic information to obtain a defect analysis model, and inputting a first result and a second result into the defect analysis model to perform defect analysis to obtain a final identification result.
In this embodiment, the image capturing apparatus: devices for acquiring image information of the recycled aluminum alloy template, such as cameras, video cameras, thermal imagers, etc.;
in this embodiment, the real-time image: capturing an image of the regenerated aluminum alloy template through image acquisition equipment;
In this example, the pretreatment: the original image is subjected to a series of processing steps to improve the quality of the image, reduce noise, enhance features in the image, etc., including but not limited to: image denoising, image enhancement, image sharpening and the like;
in this embodiment, the image to be processed: an image obtained after preprocessing the real-time image;
In this embodiment, feature extraction: the operation of extracting representative features from the image, wherein the image features can be the characterization of the local structure, texture, shape, color and other industrial numerical values of the image;
in this embodiment, defect feature information: the information of all the image features generated after the feature extraction is included;
In this embodiment, a defect recognition model is preset: the model for identifying the defects in the template image according to the input defect characteristic information is trained by big data in advance;
In this embodiment, the first result is: a recognition result generated by defect recognition of a preset defect recognition model;
in this embodiment, the history defect image information: i.e., a historical defect image of the template;
In this embodiment, a set of historical defect images: an image set composed of a plurality of history defect image information;
In this embodiment, an image contrast model is preset: the model for carrying out comparison analysis on the input first result and the historical defect image set is preset;
In this example, the second result: the analysis result is obtained after the first result and the historical defect image set are subjected to comparative analysis through a preset image comparison model;
In this embodiment, a model database is preset: a database containing a plurality of data processing models for processing and analyzing image data;
in this embodiment, the defect analysis model: the models are obtained through screening from a preset model database and used for carrying out defect analysis on the first result and the second result;
In this embodiment, the final recognition result: and carrying out defect analysis on the first result and the second result through a defect analysis model to obtain analysis results.
The working principle and the beneficial effects of the technical scheme are as follows: firstly, preprocessing an obtained aluminum alloy template image, improving the image quality of a real-time image, and then extracting defect characteristics of the image to be processed through a preset filter function, so as to generate defect characteristic information and a metal surface image; and then, identifying the defects on the surface of the template in the defect identification model to obtain a first result, and performing comparison analysis with the matched historical defect image to generate a second result, wherein the current defects are judged by taking the historical data as a reference, so that the identification precision of the defects is greatly improved, and further, the final defect identification result is obtained by comprehensively analyzing and processing the first result and the second result, the defects are identified and analyzed from a multiple angle, the possibility of misjudgment is reduced, the detection precision of the defects is greatly improved, and the quality control level of the regenerated aluminum alloy template is improved.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
image acquisition is carried out on the surface of the template from a preset angle through image acquisition equipment to obtain a real-time image, and a real-time image set is established according to the time sequence of the real-time image;
preprocessing each real-time image in the real-time image set, and calibrating the real-time image which accords with a preset first threshold value as an image to be processed.
In this embodiment, the preset angle: the imaging angle is preset, the image acquisition can be carried out on the surface of the template from a plurality of space angles, and the possibility of error judgment of defects is reduced;
In this embodiment, the time sequence: the sequence of the shooting time of the real-time images;
In this embodiment, the real-time image set: a plurality of groups of real-time images are arranged according to the sequence of shooting time;
in this embodiment, a first threshold is preset: the threshold value for determining whether the preprocessed image satisfies a preset condition, for example, the threshold value for parameters such as the image size, the signal-to-noise ratio, the contrast of the image, etc., is preset.
The working principle and the beneficial effects of the technical scheme are as follows: according to the invention, the images on the surface of the regenerated aluminum alloy template are acquired from a plurality of preset angles, so that the recognition accuracy of defect characteristics on the surface of the aluminum alloy template can be improved, the possibility of misjudgment from single-angle defect recognition is reduced, and meanwhile, the image quality is improved by preprocessing the real-time image set established according to the time sequence, and whether the error occurs in the current image or not can be determined by comparing the images before and after the time, so that the possibility of misjudgment is further reduced, and the recognition accuracy of the defects of the aluminum alloy template is improved.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
Acquiring images to be processed in a real-time image set, and screening out an adaptive feature extraction strategy from a preset strategy database;
selecting a proper feature extraction method from a preset strategy-method comparison table based on a feature extraction strategy;
And carrying out feature extraction on the image to be processed based on a feature extraction method to generate defect feature information.
In this embodiment, a policy database is preset: the database containing a plurality of strategies for extracting the image features is preset;
In this embodiment, feature extraction policy: a strategy which is obtained by matching from a preset strategy database and is used for extracting image characteristics in the image to be processed;
In this embodiment, a policy-method lookup table is preset: the table comprises a mapping relation between the feature extraction strategy and the feature extraction method and is used for distributing the corresponding feature extraction method to the corresponding image to be processed according to the input feature extraction strategy;
In this embodiment, the feature extraction method: and inputting the feature extraction strategy into a method for extracting the features of the image to be processed, which is obtained in a preset strategy-method comparison table.
The working principle and the beneficial effects of the technical scheme are as follows: according to the method, the strategy for extracting the characteristics of the image to be processed in the real-time image set is obtained by screening in the preset strategy database, the corresponding characteristic extraction strategy can be matched according to the type or the characteristics of the image, and then the corresponding image characteristic extraction method is obtained through the preset strategy-method comparison table, so that the compatibility of the image to be processed is improved, the more accurate characteristic extraction strategy and method can be adapted according to the type of the image, and the extraction efficiency and the recognition accuracy of the image characteristics are improved.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
acquiring model information from a preset feature-model matching table based on the defect feature information, and selecting a corresponding preset defect identification model from a preset model database based on the model information;
And inputting the defect characteristic information into a preset defect identification model to identify the defects, so as to obtain a first result.
In this embodiment, a feature-model matching table is preset: the matching table comprising mapping relation between defect characteristics and defect recognition models is preset and is used for acquiring corresponding defect recognition model information according to the input defect characteristic information;
In this embodiment, model information: and inputting the defect characteristic information into the defect identification model information obtained in the preset characteristic-model matching table, and screening the defect identification model information in a preset model database to obtain a corresponding defect identification model.
The working principle and the beneficial effects of the technical scheme are as follows: according to the method, firstly, defect characteristic information containing a large number of regenerated aluminum alloy template image characteristics is input into a preset characteristic-model matching table to obtain model information, and then a defect identification model matched with the defect characteristic information is obtained by screening the model information in a preset model database, so that the defect characteristic information is highly matched with the defect identification model, and the defect identification precision is increased.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
Based on the defect characteristic information and the first result, screening historical defect image information with the matching degree larger than the first matching degree from a historical defect database;
Performing defect classification on the historical defect image information, and establishing a historical defect image set based on a classification result;
and meanwhile, comparing and analyzing the first result and the historical defect image set by using a preset image comparison model to obtain a second result.
In this embodiment, the historical defect database: a database storing a plurality of images of defects of the aluminum alloy templates. The defect characteristics of the aluminum alloy template are compared with those of the current aluminum alloy template;
in this embodiment, the first degree of matching: the threshold value for screening the historical defect images matched with the defect characteristic information and the first result in the historical defect database is preset;
In this embodiment, defect classification: the method is characterized in that the method is divided according to the defect type of the historical defect image information, so that the defects of the aluminum alloy template can be better understood and managed.
The working principle and the beneficial effects of the technical scheme are as follows: according to the invention, the historical defect image information meeting the preset conditions is obtained by screening in the historical defect database according to the defect characteristic information and the first result of the regenerated aluminum alloy template, the historical defect information is further divided according to the defect types, the subsequent comparison with the first result is facilitated, then the comparison analysis is carried out on the type-divided historical defect image set and the first result through the preset image comparison model, the current recognition result is analyzed by taking the historical defect image as a reference, the possibility of misjudgment, misjudgment and missed judgment is reduced, and the defect recognition precision is improved.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
performing content analysis on the defect characteristic information, and establishing a defect characteristic data packet based on the analysis content;
classifying and analyzing all defect characteristics in the defect characteristic data packet, and establishing a defect characteristic classification table based on analysis results;
Combining a preset category-factor matching table to obtain a first screening factor of each feature category in the defect feature classification table;
Meanwhile, inputting the defect characteristic data packet into a preset characteristic analysis model for parameter calculation to obtain characteristic parameters corresponding to each defect characteristic;
Acquiring a second screening factor of each defect characteristic parameter by using a preset parameter-factor comparison table based on the characteristic parameter of each defect characteristic;
Screening historical defect image information with the matching degree larger than the first matching degree in a historical defect database by combining the first screening factor and the second screening factor;
Classifying and analyzing the historical defect image information according to the characteristic information carried in the historical defect image information, and establishing a historical defect image set according to the classifying and analyzing result and the characteristic parameters of the corresponding defect characteristics;
extracting the defect characteristics under the same classification in the defect characteristic classification table and the historical defect image set and corresponding characteristic parameters, and establishing a comparison data packet;
and inputting the comparison data packet corresponding to each characteristic category into a preset image comparison analysis model for comparison analysis by combining the first result, and obtaining a second result.
In this embodiment, content parsing: namely, analyzing the defect characteristic information to obtain the information content;
in this embodiment, the defect characterization packet: converting the analysis content obtained after the content analysis of the defect characteristic information into a data packet;
In this embodiment, classification analysis: classifying and analyzing all defect characteristics contained in the defect characteristic data packet according to preset standards so as to better understand the nature, cause and influence of the defects and facilitate subsequent improvement;
In this embodiment, the defect feature classification table: the method comprises the steps that a classification table is established according to analysis results generated after classifying and analyzing all defect characteristics in a defect characteristic data packet, wherein the classification table comprises defect characteristics of different categories;
In this embodiment, a category-factor matching table is preset: the table comprises mapping relations between defect types and first screening factors, and is used for acquiring corresponding first screening factors according to the types of the input defect characteristics, wherein the first screening factors are preset;
In this embodiment, the first screening factor: screening conditions for screening historical defect image information from a historical defect database;
In this embodiment, a feature analysis model is preset: the model for carrying out parameter calculation on the input defect characteristic data packet is preset;
In this embodiment, the parameters are calculated: measuring a parameter value corresponding to each defect characteristic in the defect characteristic data packet;
in this embodiment, the characteristic parameters: i.e., the parameter values, such as size, shape, location, distribution, number, severity, etc., corresponding to each defect feature;
in this embodiment, a parameter-factor lookup table is preset: the comparison table comprises a mapping relation between the characteristic parameters and the second screening factors and is used for acquiring the corresponding second screening factors according to the input defect characteristic parameters;
in this embodiment, the second screening factor: the screening conditions are used for screening the historical defect image information from the historical defect database and correspond to the first screening factors;
In this embodiment, the feature information: defect feature information contained in the history defect image information;
In this embodiment, the same categorization: i.e. the intersection of the defect feature classification table and the set of historical defect images, in other words the same defect feature class in the defect feature classification table and the set of historical defect images;
In this embodiment, the comparison data packet: and extracting the defect characteristics of the defect characteristic category and the defect characteristic of the same defect characteristic category contained in the defect characteristic classification table and the history defect image set to generate a data packet.
The working principle and the beneficial effects of the technical scheme are as follows: according to the method, firstly, a defect characteristic data packet for data processing is established according to analysis content of current defect characteristic information, then defect characteristics in the defect characteristic data packet are subjected to classification analysis to obtain a defect characteristic classification table, then a first screening factor is obtained according to a defect-category matching table, meanwhile, characteristic parameters of defects are calculated by using a preset characteristic analysis model, then a second screening factor is obtained according to a preset parameter-factor comparison table, then the first screening factor and the second screening factor are combined to screen historical reference image information meeting preset conditions in a historical defect database, further, the comparison analysis is carried out on the current defect characteristics, the historical defect characteristics and corresponding characteristic parameters under the same classification through a preset image comparison analysis model to generate a second result, the identification precision of the defect characteristics is greatly improved, the template defect identification precision is further improved, and accordingly the quality control level of the production of the regenerated aluminum alloy is guaranteed.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which comprises the following steps:
Performing cluster analysis on each defect feature in the defect feature information, simultaneously, counting the number of the defect features in the same category in the cluster analysis result, and performing descending arrangement according to the number of the defect features contained in each category to obtain a feature descending list;
extracting a characteristic category with the ordinal number larger than the first ordinal number in a characteristic descending list, and obtaining a first screening parameter according to a preset category-parameter comparison list;
Meanwhile, judging the priority of each defect feature in the defect feature information and a preset feature-priority comparison table to obtain the priority corresponding to each defect feature;
based on each defect feature and the corresponding priority, acquiring a second screening parameter corresponding to each defect feature by combining a preset priority-parameter comparison table;
Inputting the first screening parameters and the second screening parameters into a preset model database for model matching to obtain a defect analysis model with matching degree larger than the second matching degree;
Acquiring first type information corresponding to the first result, and binding the first type information with the first result to obtain first binding information;
Inputting the first binding information and the second result into a defect analysis model, and carrying out parameter analysis on the characteristic parameters under the same characteristic category to obtain a final identification result.
In this embodiment, cluster analysis: the operation of analyzing and processing the similar defect characteristics is helpful for finding patterns and associations among defects;
in this embodiment, the same category: i.e. the same cluster category;
in this embodiment, the number of defect features: the sum of the quantity of all defect characteristics under the same category in the clustering analysis result;
in this embodiment, the descending order is: the clustering results are arranged according to the descending order of the defect feature quantity contained in each category;
in this embodiment, the feature descending order table: a class sorting table generated after all classes are arranged in descending order according to the number of the included defect characteristics;
In this embodiment, the first ordinal number: the method comprises the steps of extracting a threshold value meeting a preset condition from a feature descending list, for example, if a first ordinal number is 3, then the defect categories with ordinal numbers of 1 and 2 are extracted, and the rest defect categories are not extracted;
in this embodiment, a category-parameter lookup table is preset: the comparison table containing the mapping relation between the characteristic category and the first screening parameter is preset and is used for acquiring the corresponding first screening parameter according to the input defect characteristic category;
In this embodiment, the first screening parameter: the method comprises the steps of screening parameters of a defect analysis model meeting preset conditions from a preset model database;
in this embodiment, a feature-priority lookup table is preset: the comparison table containing the mapping relation between the defect characteristics and the priorities is preset and is used for acquiring the corresponding priorities according to the input defect characteristics;
In this embodiment, priority: inputting the defect characteristics into a corresponding priority level obtained in a preset characteristic-priority comparison table, wherein the higher the priority is, the higher the importance of the defect characteristics is, and the higher the influence duty ratio in all the defect characteristics is;
in this embodiment, a priority-parameter lookup table is preset: the comparison table comprises a mapping relation between the priority and the second screening parameter and is used for acquiring the corresponding second screening parameter according to the input priority;
In this embodiment, the second screening parameter: the method comprises the steps of screening parameters of a defect analysis model meeting preset conditions from a preset model database, wherein the parameters correspond to first screening parameters;
In this embodiment, the model matches: screening in a preset model database according to the input first screening parameters and second screening parameters to obtain a matching process of a matched defect analysis model;
In this embodiment, the second degree of matching: a threshold value used for screening defect analysis models meeting preset conditions in a preset model database, for example, if the second matching degree is 90%, then the defect analysis models with the matching degree greater than 90% can be selected;
in this embodiment, the first category information: namely the defect category corresponding to the defect identification result;
in this embodiment, the first binding information: binding the first result with the corresponding first category information to generate information;
In this example, the parameter analysis: and carrying out parameter comparison and analysis on the characteristic parameters under the same characteristic category in the first binding information and the second result, and obtaining a final identification result of the defect of the regenerated aluminum alloy template.
The working principle and the beneficial effects of the technical scheme are as follows: the method can find the similarity and the difference between the defects by carrying out cluster analysis on the defect characteristics, is beneficial to identifying common defect modes and problem sources, and can continuously improve the identification precision and the identification speed of the defects; meanwhile, by combining the first screening parameter corresponding to the characteristic category with the ordinal number larger than the first ordinal number in the characteristic descending list and the second screening parameter corresponding to the priority, a defect analysis model is accurately matched in a preset model database, so that the suitability between the model and data is improved, and the data processing efficiency is improved; and then, carrying out parameter analysis on the first binding information and the second result to obtain a final defect identification result, greatly reducing the occurrence of misjudgment and other conditions, and improving the accuracy of defect identification on the regenerated aluminum alloy template, thereby improving the quality control level of aluminum alloy production.
The embodiment of the invention provides a method for identifying surface defects of a regenerated aluminum alloy template, which is based on a feature extraction method, performs feature extraction on an image to be processed to generate defect feature information, and comprises the following steps:
intercepting a plurality of square gray images with different preset sizes from an image to be processed and presetting a filtering function;
Filtering each gray image in m scales and n preset directions through a preset filter function to obtain m x n filter kernels corresponding to each square gray image;
performing fusion processing on m x n filter kernels of all square gray images to obtain a first texture image;
respectively acquiring a brightness average ave1 of the first texture image and a brightness average ave2 of the corresponding real-time image;
the real-time image is adjusted by the brightness average ave1 to obtain a first image to be analyzed, and meanwhile, the first texture image is adjusted by the brightness average ave2 to obtain a second image to be analyzed;
when a brightness value r1 i of an ith pixel point in the real-time image meets the condition that ave 1-delta 1 is less than or equal to r1 i and less than or equal to ave1+delta 1, replacing the ith pixel point with a brightness average value ave1, otherwise, keeping the ith pixel point unchanged, and further obtaining a first image to be analyzed, wherein delta 1 represents brightness variance correspondingly obtained when no defect exists on the surface of the regenerated aluminum alloy template;
Meanwhile, when the brightness value r2 j of the j-th pixel point in the first texture image meets the condition that ave 2-delta 2 is less than or equal to r2 j and less than or equal to ave2+delta 2, replacing the j-th pixel point with a brightness average value ave2, otherwise, keeping the j-th pixel point unchanged, and further obtaining a second image to be analyzed, wherein delta 2 represents brightness variances of the first texture image and the real-time image under all the same coordinates in which defects are determined preliminarily;
Acquiring first brightness variance sigma 1 2 of a first image to be analyzed and a real-time image, and simultaneously acquiring second brightness variance sigma 2 2 of a second image to be analyzed and a first texture image;
obtaining the image quality W of the first texture image according to the brightness average ave1, the brightness average ave2, the first brightness variance sigma 1 2 and the second brightness variance sigma 2 2;
Wherein, oc 1, oc2, oc3 represent importance parameters; n1 represents the number of pixel brightness substitutions existing in the first image to be analyzed; n3 represents the total number of pixel points in the first image to be analyzed; n2 represents the number of pixel brightness substitutions in the second image to be analyzed; n4 represents the total number of pixel points in the second image to be analyzed;
if the image quality W is greater than or equal to the threshold quality, extracting features based on the first texture image;
Otherwise, determining the adjustment definition from a difference-definition adjustment mapping table according to the difference value of the image quality W and the threshold quality, respectively acquiring an average gray value and an average fuzzy value of each square gray image, and analyzing based on the adjustment definition to obtain a weak texture region and a detail texture region;
For weak texture region First definition multiple adjustment and detail texture area adjustment according to/>Performing second definition multiple adjustment to obtain a second texture image, wherein G1 (avehd, avemh) represents an adjusting function based on an average gray value avehd and an average blur value avemh; β1, β2 represent adjustment weights; delta (mh) represents a variable based on ambiguity mh; delta (hd, bd) represents a variable based on the gradation value hd and the standard gradation value bd; g2 (avehd, avemh, maxmh, avemh 1) represents an adjustment function based on the average gray value avehd, the average blur value avemh, the maximum blur maxmh, and the average blur avemh1 satisfying the normal distribution probability; [] Representing a rounding symbol;
Feature extraction is performed based on the second texture image.
In this embodiment, the preset size: the size of the preset square gray-scale image is, for example 4*4, 5*5, 6*6, etc.;
in this embodiment, a square gray image: an image which is obtained by cutting out from the image to be processed, has a square shape and contains gray level information;
In this embodiment, a filter function is preset: the function for filtering the gray image in each direction is preset, for example, a Gabor function for extracting the texture features of the image;
in this embodiment, the filter kernel: the matrix generated according to the preset filtering function and used for carrying out filtering operation on each square gray image is consistent with the size of the direction gray image, for example, if the size of the square gray image is 4*4, the size of the filtering kernel is 4*4, and the matrix is used for calculating elements at the same position in the square gray image;
in this embodiment, the first texture image: the image containing the texture characteristics of the regenerated aluminum alloy template is obtained after the m x n filter kernels of all square gray images are fused;
In this embodiment, the first image to be analyzed: an image obtained by adjusting the real-time image through the brightness average value of the first texture image;
in this embodiment, the second image to be analyzed: an image obtained by adjusting the first texture image through the brightness average value of the real-time image;
In this embodiment, the pixel points: the most basic unit in the image is the smallest visible element in the image, each pixel point has a specific position and contains image attribute information such as color, transparency, gray scale, depth and the like, for example, if the size of the image is 5*5, the image contains 5*5 =25 pixel points;
in this embodiment, the threshold quality: a threshold value for determining whether the image quality W satisfies a preset condition;
In this embodiment, the difference: i.e. the image quality is less than the threshold quality, the numerical difference between the two;
In this embodiment, the difference-to-sharpness adjustment map: the mapping table comprises a mapping relation between the difference value and the adjustment definition and is used for acquiring the corresponding adjustment definition according to the input difference value;
In this embodiment, the average gray value: the average value obtained after the gray value sum of all pixel points in each square gray image is averaged;
in this embodiment, the average blur value: i.e. the average of the blur values of all pixels in each square gray image;
In this embodiment, the blur value: taking the average value of the pixel values of the surrounding areas of each pixel point in the image as the fuzzy value of the pixel point;
in this embodiment, the weak texture region: areas of the image that are relatively lacking in significant texture features or where texture details are not significant, e.g., areas where the gray scale differences between individual pixels are small;
in this embodiment, detail texture region: the pixel comprises a region with obvious texture or rich texture details, for example, a region with larger gray level difference among pixel points;
in this embodiment, the sharpness multiple adjustment: an operation of continuing the enlargement or reduction operation on the image to adjust the sharpness of the image;
In this embodiment, the second texture image: and carrying out first definition multiple adjustment on the weak texture region and carrying out second definition multiple adjustment on the detail texture region to obtain a texture image.
The working principle and the beneficial effects of the technical scheme are as follows: according to the invention, the square gray images with different sizes are subjected to filtering processing by utilizing the preset filtering function, so that a first texture image containing texture characteristic information of the regenerated aluminum alloy template can be obtained, and further, the image quality of the first texture image is obtained by analyzing and processing brightness values corresponding to the first texture image and the real-time image respectively, so that the image quality of the texture image is greatly improved, and the difficulty in subsequent texture recognition is reduced. Meanwhile, the invention can further improve the image quality of the first texture image by carrying out definition adjustment on the weak texture region and the detail texture region, thereby obtaining a second texture image with higher definition, and further reducing the difficulty of subsequent texture feature extraction.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (6)

1. The method for identifying the surface defects of the regenerated aluminum alloy template is characterized by comprising the following steps of:
Step 1: acquiring a real-time image of a template through image acquisition equipment, and preprocessing the real-time image to obtain an image to be processed;
Step 2: extracting features of the image to be processed to generate defect feature information, and inputting the defect feature information into a preset defect recognition model to perform defect recognition to obtain a first result;
step 3: acquiring historical defect image information of a template, establishing a historical defect image set, and simultaneously inputting the first result and the historical defect image set into a preset image comparison model for comparison analysis to obtain a second result;
Step 4: screening in a preset model database based on the defect characteristic information to obtain a defect analysis model, and inputting the first result and the second result into the defect analysis model to perform defect analysis to obtain a final identification result;
Wherein, step 2 includes:
Acquiring images to be processed in the real-time image set, and screening out an adaptive feature extraction strategy from a preset strategy database;
selecting a proper feature extraction method from a preset strategy-method comparison table based on the feature extraction strategy;
Based on the feature extraction method, feature extraction is carried out on the image to be processed, and defect feature information is generated, and the method comprises the following steps:
Intercepting a plurality of square gray images with different preset sizes from the image to be processed and presetting a filtering function;
Filtering each gray image in m scales and n preset directions through a preset filter function to obtain m x n filter kernels corresponding to each square gray image;
Fusing all m x n filter kernels of the square gray images to obtain a first texture image;
respectively acquiring a brightness average ave1 of the first texture image and a brightness average ave2 of a corresponding real-time image;
Adjusting the real-time image with the brightness average ave1 to obtain a first image to be analyzed, and simultaneously adjusting the first texture image with the brightness average ave2 to obtain a second image to be analyzed;
When the brightness value of the ith pixel point in the real-time image Satisfy/>Replacing the ith pixel point with a brightness average ave1 under the condition, otherwise, keeping the ith pixel point unchanged, and further obtaining a first image to be analyzed, wherein/>Representing the brightness variance obtained when the surface of the regenerated aluminum alloy template has no defect;
meanwhile, when the brightness value of the jth pixel point in the first texture image Satisfy/>2, Replacing the jth pixel point with a brightness average ave2, otherwise, keeping the jth pixel point unchanged, and further obtaining a second image to be analyzed, wherein/>2, Preliminarily determining the brightness variance of the first texture image and the real-time image under all the same coordinates with defects;
acquiring a first brightness variance of the first image to be analyzed and the real-time image Simultaneously, a second brightness variance/>, of the second image to be analyzed and the first texture image is obtained
According to the brightness average ave1, the brightness average ave2 and the first brightness varianceSecond luminance variance/>Acquiring the image quality W of the first texture image;
;
Wherein, 、/>、/>Representing an importance parameter; n1 represents the number of pixel brightness substitutions existing in the first image to be analyzed; n3 represents the total number of pixel points in the first image to be analyzed; n2 represents the number of pixel brightness substitutions in the second image to be analyzed; n4 represents the total number of pixel points in the second image to be analyzed;
If the image quality W is greater than or equal to a threshold quality, extracting features based on the first texture image;
otherwise, determining the adjustment definition from a difference-definition adjustment mapping table according to the difference value of the image quality W and the threshold quality, respectively acquiring an average gray value and an average fuzzy value of each square gray image, and analyzing based on the adjustment definition to obtain a weak texture region and a detail texture region;
Following the weak texture region First definition multiple adjustment and detail texture area adjustment according to/>Performing second definition multiple adjustment to obtain a second texture image, wherein/>The representation is based on the average gray value/>And mean blur value/>Is a function of the adjustment of (2); /(I)、/>Representing an adjustment weight; /(I)A variable representing a blur degree mh; /(I)A variable representing a gray value hd and a standard gray value bd; /(I)The representation is based on the average gray value/>Average blur value/>An adjustment function of the maximum ambiguity maxmh and the average ambiguity avemh1 satisfying the normal distribution probability; [ ] Representing a rounding symbol;
And extracting features based on the second texture image.
2. The method for identifying surface defects of a recycled aluminum alloy template according to claim 1, wherein in step 1, the method comprises the following steps:
Image acquisition is carried out on the surface of the template from a preset angle through image acquisition equipment to obtain a real-time image, and a real-time image set is established according to the time sequence of the real-time image;
Preprocessing each real-time image in the real-time image set, and calibrating the real-time image meeting a preset first threshold value as an image to be processed.
3. The method for identifying surface defects of a recycled aluminum alloy template according to claim 1, wherein in step 2, the method further comprises:
Acquiring model information from a preset feature-model matching table based on the defect feature information, and selecting a corresponding preset defect identification model from a preset model database based on the model information;
And inputting the defect characteristic information into the preset defect identification model to identify the defects, so as to obtain a first result.
4. The method for identifying surface defects of a recycled aluminum alloy template according to claim 1, wherein in step3, the method comprises the following steps:
Based on the defect characteristic information and the first result, screening historical defect image information with the matching degree larger than the first matching degree from a historical defect database;
performing defect classification on the historical defect image information, and establishing a historical defect image set based on classification results;
and meanwhile, comparing and analyzing the first result and the historical defect image set by using a preset image comparison model to obtain a second result.
5. The method for identifying surface defects of a recycled aluminum alloy template according to claim 4, wherein in step 3, the method further comprises:
performing content analysis on the defect characteristic information, and establishing a defect characteristic data packet based on analysis content;
classifying and analyzing all defect characteristics in the defect characteristic data packet, and establishing a defect characteristic classification table based on analysis results;
Combining a preset category-factor matching table to obtain a first screening factor of each feature category in the defect feature classification table;
meanwhile, inputting the defect characteristic data packet into a preset characteristic analysis model for parameter calculation to obtain characteristic parameters corresponding to each defect characteristic;
Acquiring a second screening factor of each defect characteristic parameter by using a preset parameter-factor comparison table based on the characteristic parameter of each defect characteristic;
Screening historical defect image information with the matching degree larger than the first matching degree in a historical defect database by combining the first screening factor and the second screening factor;
classifying and analyzing the historical defect image information according to the characteristic information carried in the historical defect image information, and establishing a historical defect image set according to the classifying and analyzing result and the characteristic parameters of the corresponding defect characteristics;
Extracting the defect characteristics under the same classification and corresponding characteristic parameters in the defect characteristic classification table and the historical defect image set, and establishing a comparison data packet;
and inputting the comparison data packet corresponding to each characteristic category into a preset image comparison analysis model for comparison analysis by combining the first result to obtain a second result.
6. The method for identifying surface defects of a recycled aluminum alloy template according to claim 1, wherein in step 4, the method comprises the following steps:
Performing cluster analysis on each defect feature in the defect feature information, simultaneously counting the number of defect features in the same category in a cluster analysis result, and performing descending arrangement according to the number of defect features contained in each category to obtain a feature descending list;
Extracting feature categories with ordinal numbers larger than the first ordinal number in the feature descending list, and obtaining first screening parameters according to a preset category-parameter comparison list;
Meanwhile, judging the priority of each defect feature in the defect feature information and a preset feature-priority comparison table to obtain the priority corresponding to each defect feature;
based on each defect feature and the corresponding priority, acquiring a second screening parameter corresponding to each defect feature by combining a preset priority-parameter comparison table;
inputting the first screening parameters and the second screening parameters into a preset model database for model matching to obtain a defect analysis model with matching degree larger than the second matching degree;
Acquiring first type information corresponding to the first result, and binding the first type information with the first result to obtain first binding information;
Inputting the first binding information and the second result into the defect analysis model, and carrying out parameter analysis on the characteristic parameters under the same characteristic category to obtain a final identification result.
CN202311537634.6A 2023-11-16 2023-11-16 Surface defect identification method for regenerated aluminum alloy template Active CN117351001B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311537634.6A CN117351001B (en) 2023-11-16 2023-11-16 Surface defect identification method for regenerated aluminum alloy template

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311537634.6A CN117351001B (en) 2023-11-16 2023-11-16 Surface defect identification method for regenerated aluminum alloy template

Publications (2)

Publication Number Publication Date
CN117351001A CN117351001A (en) 2024-01-05
CN117351001B true CN117351001B (en) 2024-05-28

Family

ID=89365076

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311537634.6A Active CN117351001B (en) 2023-11-16 2023-11-16 Surface defect identification method for regenerated aluminum alloy template

Country Status (1)

Country Link
CN (1) CN117351001B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117805145B (en) * 2024-02-28 2024-05-14 西安汉华建筑实业有限公司 Aluminum template surface defect detection method and system
CN118071731B (en) * 2024-04-01 2024-08-16 泰州职业技术学院 Waste metal identification method

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102289808A (en) * 2011-07-22 2011-12-21 清华大学 Method and system for evaluating image fusion quality
CN109559310A (en) * 2018-11-30 2019-04-02 国网山东省电力公司电力科学研究院 Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection
CN113838043A (en) * 2021-09-30 2021-12-24 杭州百子尖科技股份有限公司 Machine vision-based quality analysis method in metal foil manufacturing
CN114677336A (en) * 2022-03-10 2022-06-28 四川省建筑科学研究院有限公司 Curtain wall panel damage identification method based on infrared image
CN114757941A (en) * 2022-05-19 2022-07-15 国网智能科技股份有限公司 Transformer substation equipment defect identification method and device, electronic equipment and storage medium
CN114972356A (en) * 2022-08-03 2022-08-30 海门市腾飞橡塑厂 Plastic product surface defect detection and identification method and system
CN115032194A (en) * 2022-06-13 2022-09-09 南通雨奇金属制品有限公司 Intelligent detection and regulation method for components of regenerated aluminum alloy
CN115345802A (en) * 2022-10-18 2022-11-15 苏州迈创信息技术有限公司 Remote monitoring method for operation state of electromechanical equipment
CN115526859A (en) * 2022-09-28 2022-12-27 深圳市海葵信息技术有限公司 Method for identifying production defects, distributed processing platform, equipment and storage medium
CN115760820A (en) * 2022-11-28 2023-03-07 湖北三江航天万峰科技发展有限公司 Plastic part defect image identification method and application
CN116393403A (en) * 2023-04-11 2023-07-07 肇庆市大正铝业有限公司 Method and system for identifying waste impurities of surface structure of aluminum alloy product
WO2023134792A2 (en) * 2022-12-15 2023-07-20 苏州迈创信息技术有限公司 Led lamp wick defect detection method
CN116563641A (en) * 2023-05-30 2023-08-08 江西软件职业技术大学 Surface defect identification method and system based on small target detection
CN116862913A (en) * 2023-09-04 2023-10-10 深圳市鑫典金光电科技有限公司 Machine vision-based defect detection method and system for composite nickel-copper heat dissipation bottom plate
CN116977727A (en) * 2023-07-27 2023-10-31 上海理工大学 Image processing-based gas combustion flame real-time monitoring method and system
CN117033990A (en) * 2023-06-26 2023-11-10 华能大理风力发电有限公司祥云分公司 Photovoltaic array fault feature extraction and modeling method
CN117390214A (en) * 2023-12-12 2024-01-12 北京云成金融信息服务有限公司 File retrieval method and system based on OCR technology

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI603074B (en) * 2015-07-03 2017-10-21 元智大學 Optical film defect detection method and system thereof
US10769784B2 (en) * 2018-12-21 2020-09-08 Metal Industries Research & Development Centre Image analyzing method and electrical device
CN111583157B (en) * 2020-05-13 2023-06-02 杭州睿琪软件有限公司 Image processing method, system and computer readable storage medium
CN113763296B (en) * 2021-04-28 2024-08-06 腾讯云计算(北京)有限责任公司 Image processing method, device and medium

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102289808A (en) * 2011-07-22 2011-12-21 清华大学 Method and system for evaluating image fusion quality
CN109559310A (en) * 2018-11-30 2019-04-02 国网山东省电力公司电力科学研究院 Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection
CN113838043A (en) * 2021-09-30 2021-12-24 杭州百子尖科技股份有限公司 Machine vision-based quality analysis method in metal foil manufacturing
CN114677336A (en) * 2022-03-10 2022-06-28 四川省建筑科学研究院有限公司 Curtain wall panel damage identification method based on infrared image
CN114757941A (en) * 2022-05-19 2022-07-15 国网智能科技股份有限公司 Transformer substation equipment defect identification method and device, electronic equipment and storage medium
CN115032194A (en) * 2022-06-13 2022-09-09 南通雨奇金属制品有限公司 Intelligent detection and regulation method for components of regenerated aluminum alloy
CN114972356A (en) * 2022-08-03 2022-08-30 海门市腾飞橡塑厂 Plastic product surface defect detection and identification method and system
CN115526859A (en) * 2022-09-28 2022-12-27 深圳市海葵信息技术有限公司 Method for identifying production defects, distributed processing platform, equipment and storage medium
CN115345802A (en) * 2022-10-18 2022-11-15 苏州迈创信息技术有限公司 Remote monitoring method for operation state of electromechanical equipment
CN115760820A (en) * 2022-11-28 2023-03-07 湖北三江航天万峰科技发展有限公司 Plastic part defect image identification method and application
WO2023134792A2 (en) * 2022-12-15 2023-07-20 苏州迈创信息技术有限公司 Led lamp wick defect detection method
CN116393403A (en) * 2023-04-11 2023-07-07 肇庆市大正铝业有限公司 Method and system for identifying waste impurities of surface structure of aluminum alloy product
CN116563641A (en) * 2023-05-30 2023-08-08 江西软件职业技术大学 Surface defect identification method and system based on small target detection
CN117033990A (en) * 2023-06-26 2023-11-10 华能大理风力发电有限公司祥云分公司 Photovoltaic array fault feature extraction and modeling method
CN116977727A (en) * 2023-07-27 2023-10-31 上海理工大学 Image processing-based gas combustion flame real-time monitoring method and system
CN116862913A (en) * 2023-09-04 2023-10-10 深圳市鑫典金光电科技有限公司 Machine vision-based defect detection method and system for composite nickel-copper heat dissipation bottom plate
CN117390214A (en) * 2023-12-12 2024-01-12 北京云成金融信息服务有限公司 File retrieval method and system based on OCR technology

Also Published As

Publication number Publication date
CN117351001A (en) 2024-01-05

Similar Documents

Publication Publication Date Title
CN117351001B (en) Surface defect identification method for regenerated aluminum alloy template
CN113724231B (en) Industrial defect detection method based on semantic segmentation and target detection fusion model
CN108898610B (en) Object contour extraction method based on mask-RCNN
CN108562589B (en) Method for detecting surface defects of magnetic circuit material
Senthilkumaran et al. Image segmentation by using thresholding techniques for medical images
CN106096610B (en) A kind of file and picture binary coding method based on support vector machines
CN115082683A (en) Injection molding defect detection method based on image processing
CN106846316A (en) A kind of GIS inside typical defect automatic distinguishing method for image
CN110210477B (en) Digital instrument reading identification method
CN105809121A (en) Multi-characteristic synergic traffic sign detection and identification method
CN110706235B (en) Far infrared pedestrian detection method based on two-stage cascade segmentation
CN111667475B (en) Machine vision-based Chinese date grading detection method
CN116152242B (en) Visual detection system of natural leather defect for basketball
CN111814852B (en) Image detection method, image detection device, electronic equipment and computer readable storage medium
CN117788467B (en) Defect image classification method for titanium metal plate
CN113537037A (en) Pavement disease identification method, system, electronic device and storage medium
CN111507391A (en) Intelligent identification method for nonferrous metal broken materials based on machine vision
CN115294377A (en) System and method for identifying road cracks
CN118279304A (en) Abnormal recognition method, device and medium for special-shaped metal piece based on image processing
CN115272778A (en) Recyclable garbage classification method and system based on RPA and computer vision
CN114565607A (en) Fabric defect image segmentation method based on neural network
CN110766662B (en) Forging surface crack detection method based on multi-scale and multi-layer feature learning
CN110570469B (en) Intelligent identification method for angle position of automobile picture
CN116363136B (en) On-line screening method and system for automatic production of motor vehicle parts
CN118429242A (en) Image analysis method and system based on deep learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant