CN116448768A - Embedded online machine vision detection method - Google Patents
Embedded online machine vision detection method Download PDFInfo
- Publication number
- CN116448768A CN116448768A CN202310455659.5A CN202310455659A CN116448768A CN 116448768 A CN116448768 A CN 116448768A CN 202310455659 A CN202310455659 A CN 202310455659A CN 116448768 A CN116448768 A CN 116448768A
- Authority
- CN
- China
- Prior art keywords
- machine vision
- image
- production line
- online machine
- elongation
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 238000004519 manufacturing process Methods 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000005286 illumination Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims description 14
- 229910000838 Al alloy Inorganic materials 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 229910000881 Cu alloy Inorganic materials 0.000 claims description 7
- 229910000861 Mg alloy Inorganic materials 0.000 claims description 7
- 229910000831 Steel Inorganic materials 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 239000010959 steel Substances 0.000 claims description 7
- 238000011179 visual inspection Methods 0.000 abstract description 6
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000013016 damping Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000035939 shock Effects 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004382 visual function Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of visual inspection, and discloses an embedded online machine visual inspection method, which comprises the following steps: s1: starting a light-emitting monochromatic diode and a CCD camera; s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; s3: the features are cascaded. The quality detection of products on a production line in automatic production can be performed at high speed in the use process, and a light source can be provided when the surface of the products is detected through the monochromatic light emitting diode, so that the CCD camera is more accurate in observation, low in cost and favorable for wide popularization and application; the specification of the plates can be detected, so that the plates with the specification which does not meet the standard can be screened out, and workers can be informed of taking out the plates which do not meet the standard from the upper part of the production line through the buzzer.
Description
Technical Field
The invention relates to the technical field of visual inspection, in particular to an embedded online machine visual inspection method.
Background
Machine vision technology is an interdisciplinary in many fields, such as artificial intelligence, neurobiology, psychophysics, computer science, image processing, pattern recognition, etc. The machine vision mainly uses a computer to simulate the visual function of a person, extracts information from an image of an objective object, processes and understands the information, and is finally used for actual detection, measurement and control, in order to make the production efficiency more efficient in the production process, an embedded high-speed online machine vision detection method and device are disclosed as CN111957584A, and the embedded high-speed online machine vision detection device aims to solve the problems that the shock resistance of the existing embedded high-speed online machine vision detection device is weaker, the accurate parts inside the embedded high-speed online machine vision detection device are easily damaged by shock, the use of the embedded high-speed online machine vision detection device is affected, imaging blurring is caused by shock, the detection precision of the device is affected, and the device is easily affected by external unstable light, so that the error detection condition occurs. The support bracket is arranged below the main body bracket, an anti-falling clamping table is arranged at the lower end of the main body bracket, the anti-falling clamping table is connected with the main body bracket in a welded mode, a bottom damping spring is arranged at the lower end inside the support bracket, the bottom damping spring is connected with the support bracket and the anti-falling clamping table in a welded mode, lateral damping springs are arranged on two sides inside the support bracket, and the lateral damping springs are connected with the support bracket and the main body bracket in a welded mode;
however, there is a disadvantage in that in the visual inspection process, the surface of the product is inspected by an industrial camera, and in the production process, the defects on the surface of the product can be precisely observed by using an external light source when the camera is used for inspection, so that an embedded online machine visual inspection method is provided
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides an embedded online machine vision detection method which has the advantages of being capable of detecting the specification of a plate and the like, and solves the problem that the machining precision is low due to large specification error of the plate in the production process of the plate.
(II) technical scheme
In order to achieve the purpose of detecting the specification and the size of the metal plate, the invention provides the following technical scheme: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted;
s3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
Preferably, in the step S2, under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, an image signal of the detected object on the production line is collected in real time through a high-speed linear array Charge Coupled Device (CCD) camera.
Preferably, in the selecting of the features in the S2, the three features are: elongation 15-20, rectangle degree 88-93, plate area 120CM-130CM.
Preferably, the step of collecting the image signals of the detected object on the product production line in real time at high speed in S2 further comprises the following steps: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, because the field environment, CCD image photoelectric conversion, transmission circuit and electronic element can generate noise for the image, the noise reduces the quality of the image, and thus the image processing and analysis are adversely affected, the image is preprocessed to be denoised. The image enhancement aims at the application occasion of a given image, and the image processing method is used for purposefully emphasizing the whole or partial characteristics of the image, enabling the original unclear image to become clear or emphasizing some interesting features, expanding the differences among different object features in the image, inhibiting the uninteresting features, improving the image quality, enriching the information quantity and enhancing the image interpretation and recognition effects.
Preferably, the material system suitable for the production line in S2 is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
Preferably, the elongation is 12, the rectangle degree is 89 degrees, and the plate area is 130CM.
Preferably, the elongation is 18, the rectangle degree is 90 degrees, and the area of the plate is 128CM.
Preferably, the elongation is 16, the rectangle degree is 90 degrees, and the area of the plate is 125CM.
Preferably, the elongation is 17.7, the rectangle degree is 90 degrees, and the plate area is 127CM.
Preferably, the elongation is 19, the rectangle degree is 90 degrees, and the area of the plate is 126CM.
The invention provides an embedded online machine vision detection method, which comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted;
s3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
(III) beneficial effects
Compared with the prior art, the invention provides an embedded online machine vision detection method, which has the following beneficial effects:
1. according to the embedded online machine vision detection method, quality detection can be carried out on products on a production line in automatic production at a high speed in the use process, a light source can be provided when the surfaces of the products are detected through the monochromatic light emitting diode, so that the CCD camera is more accurate in observation, the cost is low, and the method is favorable for wide popularization and application.
2. According to the embedded online machine vision detection method, the specification of the plate can be detected, so that the plate with the specification which does not meet the standard can be screened out, a buzzer can inform a worker to take out the plate which does not meet the standard from the upper part of the production line, the problem that the processing device cannot fall on the surface of the plate in the subsequent processing process of the plate due to the fact that the specification of the plate is not right in the processing process is avoided, the damage to the processing device and the surface of the production line is caused, the mechanism of the subsequent plate is affected, the efficiency is reduced, and the specified production task cannot be completed is avoided.
3. According to the embedded online machine vision detection method, manual detection is replaced by a dynamic detection system technology of image recognition, intelligent and automatic detection technology of aluminum alloy plate and strip defects can be realized, manual recognition of appearance defects of the aluminum alloy plate and strip can be comprehensively replaced, a large amount of labor cost is saved, labor productivity is liberated, more reasonable direction is required for labor flow, defect recognition is more accurate, production technology is improved, production efficiency of production enterprises is improved, manufacturing and industrial production automation level of the aluminum alloy plate production enterprises is improved, and obvious economic and social benefits are realized.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, image signals of an object to be detected on a production line are collected in real time through a CCD camera of a high-speed linear array charge coupled device image sensor, and in feature selection, three selected features are as follows: the method comprises the following steps of acquiring image signals of a detected object on a product production line at a high speed in real time, wherein the elongation is 18, the rectangle degree is 90 degrees, and the area of a plate is 128 CM: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, wherein the material system suitable for the production line is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
S3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: and comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value.
S5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
Embodiment two: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, image signals of an object to be detected on a production line are collected in real time through a CCD camera of a high-speed linear array charge coupled device image sensor, and in feature selection, three selected features are as follows: the method is characterized in that the elongation is 18, the rectangle degree is 90 degrees, the area of the plate is 128CM, and the method further comprises the following steps after the image signals of the detected object on the product production line are acquired at high speed in real time: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, wherein the material system suitable for the production line is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
S3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: if the unqualified product appears, an alarm is sent out through the alarm buzzer to remind the staff to process, and the alarm can be sent out when the unqualified product appears through the installation of the alarm buzzer to remind the staff to process in time.
Embodiment III: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, image signals of an object to be detected on a production line are collected in real time through a CCD camera of a high-speed linear array charge coupled device image sensor, and in feature selection, three selected features are as follows: the method comprises the following steps of acquiring image signals of a detected object on a product production line at a high speed in real time, wherein the elongation is 16, the rectangle degree is 90 degrees, and the area of a plate is 125 CM: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, wherein the material system suitable for the production line is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
S3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: and comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value.
S5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
Experimental example four: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, image signals of an object to be detected on a production line are collected in real time through a CCD camera of a high-speed linear array charge coupled device image sensor, and in feature selection, three selected features are as follows: the method comprises the following steps of acquiring image signals of a detected object on a product production line at a high speed in real time, wherein the elongation is 17.7, the rectangle degree is 90 degrees, and the area of a plate is 127 CM: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, wherein the material system suitable for the production line is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
S3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
Fifth embodiment: the method comprises the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted; under the irradiation of a special illumination light source composed of a monochromatic light emitting diode, image signals of an object to be detected on a production line are collected in real time through a CCD camera of a high-speed linear array charge coupled device image sensor, and in feature selection, three selected features are as follows: the method comprises the following steps of acquiring image signals of a detected object on a product production line at a high speed in real time, wherein the elongation is 17.7, the rectangle degree is 90 degrees, and the area of a plate is 127 CM: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement and background compensation, wherein the material system suitable for the production line is aluminum alloy, magnesium alloy, copper alloy and various steel plates or strips.
S3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
The beneficial effects of the invention are as follows: the quality detection of the products on the production line in the automatic production can be carried out at high speed in the use process, and the cost is low, thereby being beneficial to wide popularization and application; the sheet specification can be detected, so that the sheet with the specification which does not meet the standard can be screened, a buzzer can inform a worker to take the sheet which does not meet the standard out of the upper part of the production line, the problem that the sheet cannot be dropped on the surface of the processing device and the surface of the production line in the subsequent processing process of the sheet due to the fact that the sheet specification is not matched is avoided, the damage to the surface of the processing device and the surface of the production line is caused, the mechanism of the subsequent sheet is influenced, the efficiency is reduced, and the specified production task cannot be completed is avoided; the intelligent and automatic detection of the aluminum alloy plate and strip defect detection technology can be realized by replacing the manual detection by the dynamic detection system technology of image recognition, so that the manual recognition of the appearance defects of the aluminum alloy plate and strip can be comprehensively replaced, a large amount of labor cost is saved, labor productivity is liberated, the more reasonable direction of the labor flow direction is promoted, meanwhile, the defect recognition is more accurate, the production process is improved, the production efficiency of a production enterprise is improved, the manufacturing and industrial production automation level of the aluminum alloy plate production enterprise is improved, and obvious economic and social benefits are realized.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An embedded online machine vision detection method is characterized by comprising the following steps:
s1: starting a light-emitting monochromatic diode and a CCD camera;
s2: under the irradiation of a special illumination light source composed of monochromatic light emitting diodes, image signals of detected objects on a product production line are collected at high speed in real time, and the characteristics of sensitive image areas with easy quality problems are extracted;
s3: the feature cascade is used for obtaining CTLBP features, and an SVM classifier is used for inputting the obtained CTLBP feature vectors into the SVM for classification;
s4: comparing the extracted characteristics of the sensitive image area with standard characteristics of the sensitive image area, and judging whether the detected object is qualified or not according to whether the similarity of the extracted characteristics of the sensitive image area and the standard characteristics of the sensitive image area reaches a preset value;
s5: and if the unqualified product appears, an alarm is sent out through an alarm buzzer to remind the staff to process.
2. The embedded online machine vision detection method according to claim 1, wherein the image signal of the detected object on the production line is collected in real time by a high-speed linear array Charge Coupled Device (CCD) camera under the irradiation of a special illumination light source composed of monochromatic light emitting diodes in the step S2.
3. The method for on-line machine vision inspection of claim 1, wherein in the step of selecting features, S2 is selected from three features: elongation 15-20, rectangle degree 88-93, plate area 120CM-130CM.
4. The method for on-line machine vision inspection according to claim 1, wherein the step of collecting the image signals of the inspected object on the product line in real time at high speed in S2 further comprises the steps of: preprocessing the collected image of the detected object to improve the quality of the image; the preprocessing operation includes: denoising, image enhancement, and background compensation.
5. The embedded online machine vision inspection method according to claim 1, wherein the material system suitable for the production line in S2 is a plate or strip of aluminum alloy, magnesium alloy, copper alloy and various steels.
6. An embedded online machine vision inspection method as claimed in claim 3, wherein the elongation is 12, the rectangle degree is 89 degrees, and the sheet area is 130CM.
7. An embedded online machine vision inspection method as claimed in claim 3, wherein the elongation is 18, the rectangle degree is 90 degrees, and the sheet area is 128CM.
8. An embedded online machine vision inspection method as claimed in claim 3, wherein the elongation is 16, the rectangle degree is 90 degrees, and the sheet area is 125CM.
9. An embedded online machine vision inspection method as claimed in claim 3, wherein the elongation is 17.7, the rectangle degree is 90 degrees, and the sheet area is 127CM.
10. An embedded online machine vision inspection method as claimed in claim 3, wherein the elongation is 19, the rectangle degree is 90 degrees, and the sheet area is 126CM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310455659.5A CN116448768A (en) | 2023-04-25 | 2023-04-25 | Embedded online machine vision detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310455659.5A CN116448768A (en) | 2023-04-25 | 2023-04-25 | Embedded online machine vision detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116448768A true CN116448768A (en) | 2023-07-18 |
Family
ID=87131957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310455659.5A Pending CN116448768A (en) | 2023-04-25 | 2023-04-25 | Embedded online machine vision detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116448768A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118097305A (en) * | 2024-04-16 | 2024-05-28 | 深圳市呈泰半导体科技有限公司 | Method and system for detecting quality of semiconductor light-emitting element |
-
2023
- 2023-04-25 CN CN202310455659.5A patent/CN116448768A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118097305A (en) * | 2024-04-16 | 2024-05-28 | 深圳市呈泰半导体科技有限公司 | Method and system for detecting quality of semiconductor light-emitting element |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288584A (en) | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision | |
| CN112348840A (en) | QFP chip pin defect discrimination method based on pixel region growth | |
| CN109840900A (en) | A kind of line detection system for failure and detection method applied to intelligence manufacture workshop | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN101221134A (en) | Method and device for detecting tiny bearing surface defect by computer vision technology | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN106290392A (en) | A kind of little micro-bearing surface pitting defects online test method and system thereof | |
| CN112614105B (en) | Depth network-based 3D point cloud welding spot defect detection method | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN201141839Y (en) | Device for detecting tiny bearing surface defect by computer vision technology | |
| CN112014407A (en) | Method for detecting surface defects of integrated circuit wafer | |
| CN116448768A (en) | Embedded online machine vision detection method | |
| CN112288741A (en) | Product surface defect detection method and system based on semantic segmentation | |
| CN116978834B (en) | Intelligent monitoring and early warning system for wafer production | |
| CN108776966B (en) | Method and system for detecting magnet appearance defects | |
| Liu et al. | Automatic detection technology of surface defects on plastic products based on machine vision | |
| CN111761224B (en) | Metal additive manufacturing online mobile monitoring mechanism and online appearance detection equipment | |
| CN113780830A (en) | Steel wire part quality inspection system, method and equipment based on projection | |
| CN114813748A (en) | Steel surface defect detection method and system based on machine vision | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN111307817B (en) | Online detection method and system for PCB production process of intelligent production line | |
| Heger et al. | Using data mining techniques to investigate the correlation between surface cracks and flange lengths in deep drawn sheet metals | |
| CN110763705A (en) | Deep learning identification method and system based on X-ray image and X-ray machine | |
| CN113160154B (en) | Method and system for detecting paint spraying defects of five-star feet based on machine vision | |
| CN114742823A (en) | Intelligent detection method for scratches on surface of object |
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 |