CN115994906A - Material image positioning method and device based on contour position index - Google Patents
Material image positioning method and device based on contour position index Download PDFInfo
- Publication number
- CN115994906A CN115994906A CN202310280394.XA CN202310280394A CN115994906A CN 115994906 A CN115994906 A CN 115994906A CN 202310280394 A CN202310280394 A CN 202310280394A CN 115994906 A CN115994906 A CN 115994906A
- Authority
- CN
- China
- Prior art keywords
- detected
- sample
- profile
- index array
- contour
- 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.)
- Granted
Links
- 239000000463 material Substances 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000000523 sample Substances 0.000 claims abstract description 226
- 238000010586 diagram Methods 0.000 claims description 73
- 238000003860 storage Methods 0.000 claims description 18
- 238000003491 array Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 13
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 230000002085 persistent effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000013077 target material Substances 0.000 description 2
- 239000002355 dual-layer Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- Image Analysis (AREA)
Abstract
The application relates to a material image positioning method and device based on contour position indexes. The method comprises the following steps: identifying sample contour points of the sample material image, and calculating a sample contour index array of the sample contour points; identifying contour points to be detected of a material image to be detected in the image to be detected, and calculating a contour index array to be detected of the contour points to be detected; according to the first preset pixel step distance, comparing the sample profile index array with the profile index array to be detected, and searching candidate profile points which accord with a preset similarity threshold in the profile index array to be detected; searching target contour points which accord with a preset similarity threshold value in the candidate contour points according to the second preset pixel step distance; and determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points. The scheme that this application provided can solve among the conveying material, discernment material image inefficiency and the slow problem of speed.
Description
Technical Field
The present disclosure relates to the field of image recognition, and in particular, to a method and an apparatus for positioning a material image based on a contour position index.
Background
In the production process of the bearing industry, a large number of material counting and identifying applications exist, and particularly, the material positioning and material identification in the aspects of flow control in the production process, warehousing inspection and acceptance, inventory checking, quantitative packaging and the like cannot be realized for the material rolling bodies with various numbers, varieties and specifications.
In the process of moving materials on a production line, the conventional visual detection technology recognizes the geometric center and the approximate angle of an object by using methods such as spot positioning and the like, so that the problems of poor precision, easiness in misjudgment and the like exist, and the conventional template matching mode has low searching speed although the precision can meet the requirement, and cannot meet the situation that the production beat requirement is fast.
Therefore, the existing material image positioning method has the problems of low accuracy and low speed in the identification process.
Disclosure of Invention
In order to solve or partially solve the problems existing in the related art, the scheme provided by the application can solve the problems of low efficiency and low speed of identifying the material image in the process of conveying the material.
In one aspect, the present application provides a method for positioning a material image based on a contour position index, including:
identifying sample contour points of the sample material image, and calculating a sample contour index array of the sample contour points;
Identifying contour points to be detected of a material image to be detected in the image to be detected, and calculating a contour index array to be detected of the contour points to be detected;
according to the first preset pixel step distance, comparing the sample profile index array with the profile index array to be detected, and searching candidate profile points which accord with a preset similarity threshold in the profile index array to be detected;
according to a second preset pixel step distance, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected, and searching a target profile point which accords with a preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance;
and determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points.
Optionally, identifying sample contour points of the sample material image includes:
calculating the transverse gradient of the sample material image and the longitudinal gradient of the sample material image, and combining the transverse gradient of the sample material image and the longitudinal gradient image of the sample material image;
and carrying out binarization processing on the combined sample material images, and identifying the image contour of the sample material images after the binarization processing to obtain sample contour points of the sample material images.
Optionally, the sample profile index array includes two-dimensional coordinates of the sample profile point and an index number corresponding to the sample profile point, the index number corresponding to the sample profile point is used to represent a position of the sample profile point in the sample material image, and calculating the sample profile index array of the sample profile point includes:
setting a position index number according to a two-dimensional coordinate of a sample contour point in a sample material image and a preset index direction, wherein the position index number is a one-dimensional array;
and obtaining a sample contour index array based on the two-dimensional coordinates of the sample contour points and the position index numbers of the sample contour points.
Optionally, identifying the contour point to be detected of the image of the material to be detected in the image to be detected includes:
calculating the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected, and combining the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected;
and carrying out binarization processing on the combined material images to be detected, and identifying the image contour of the binarized material images to be detected to obtain contour points to be detected of the material images to be detected.
Optionally, the profile index array to be detected includes two-dimensional coordinates of the profile point to be detected and an index number corresponding to the profile point to be detected, the index number corresponding to the profile point to be detected is used for indicating a position of the profile point to be detected in the image to be detected, and the profile index array to be detected of the profile point to be detected is calculated, including:
Acquiring a position index number of an image to be detected according to the two-dimensional coordinates of the contour point to be detected and a preset index direction;
and generating a contour index array to be detected according to the position index number and the two-dimensional coordinates of the contour point to be detected.
Optionally, comparing the sample profile index array with the to-be-detected index array according to a first preset pixel step distance, and searching candidate profile points meeting a preset similarity threshold in the to-be-detected profile index array, including:
acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set;
shifting the sample profile index array according to the shifting angle and the first preset pixel step distance, and comparing the sample profile index array with the profile index array to be detected;
drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to the comparison result;
traversing a preset offset angle set to obtain a first thermodynamic diagram set of a profile index array to be detected, and selecting a first thermodynamic diagram with highest similarity from the first thermodynamic diagram set;
and selecting a point meeting a preset similarity threshold from the first thermodynamic diagram with highest similarity as a candidate contour point.
Optionally, drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to the comparison result, including:
Determining pixel attributes corresponding to the contour points according to the similarity between the contour points in the wheel index array to be detected and the contour points of the sample contour index array;
the pixel attribute corresponding to the contour point comprises a gray value of the contour point determined according to the similarity of the contour point;
and generating a first thermodynamic diagram according to the pixel attribute corresponding to the contour point of the contour index array to be detected.
Optionally, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected according to a second preset pixel step distance, and searching the target profile points meeting a preset similarity threshold in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance, and the method comprises the following steps:
acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set;
shifting the sample profile index array according to the shifting angle and the first preset pixel step distance in the preset pixel range of the candidate profile point to be detected, and comparing the sample profile index array with the profile index array to be detected;
drawing a second thermodynamic diagram of the sample profile index array and the to-be-seen profile index array according to the comparison result;
Traversing a preset offset angle set to obtain a second thermodynamic diagram set of the profile index array to be detected, and selecting a second thermodynamic diagram with highest similarity from the second thermodynamic diagram set;
and selecting a point meeting a preset similarity threshold from the second thermodynamic diagram with highest similarity as a target contour point.
A second aspect of the present application provides a material image positioning device based on contour position index, including:
the first identification unit is used for identifying sample contour points of the sample material image and calculating a sample contour index array of the sample contour points;
the second identification unit is used for identifying contour points to be detected of the material images to be detected in the images to be detected and calculating a contour index array to be detected of the contour points to be detected;
the first index unit is used for comparing the sample profile index array with the to-be-detected index array according to a first preset pixel step distance, and searching candidate profile points which accord with a preset similarity threshold value in the to-be-detected profile index array;
the second index unit is used for comparing the sample profile index array with the profile index array to be detected in the preset pixel range of the candidate profile points to be detected according to a second preset pixel step distance, and searching target profile points which accord with a preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance;
And the determining unit is used for determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour point.
A second aspect of the present application provides a material image positioning apparatus based on profile position index, optionally including:
the detection module is used for identifying the region of interest of the conveyor belt image and extracting an image to be detected;
the first extraction module is used for preprocessing the image to be detected, extracting the material outline of the preprocessed image to be detected according to the material morphological characteristics, and obtaining a first material image;
the second extraction module is used for determining the adhesion proportion of the first material image and the background pixel, and extracting the material outline of the first material image according to the adhesion proportion, a preset adhesion threshold value and a preset size nuclear filter to obtain a second material image;
and the third extraction module is used for correcting the second material image, screening the corrected second material image according to a preset characteristic peak value so as to acquire a target material contour, and determining the material quantity according to the target material contour.
A third aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon which, when executed by a processor, causes the processor to perform the method as above.
A fourth aspect of the present application provides a computer readable storage medium having executable code stored thereon, which when executed by a processor of an electronic device, causes the processor to perform a method as above.
The technical scheme that this application provided can include following beneficial effect:
in a first aspect, the present application calculates a sample profile index array of sample profile points by identifying sample profile points of a sample material image; identifying contour points to be detected of a material image to be detected in the image to be detected, and calculating a contour index array to be detected of the contour points to be detected; the sample material image is simplified into the index array, then the sample profile index array is subjected to multiple selection and conversion according to a certain step distance to obtain a group of multi-angle sample index arrays, and then the multi-angle index arrays are compared with the profile index array to be detected, so that the accuracy of searching the to-be-detected point is improved, and the object positioning identification high-speed, high-precision and high-real-time detection is realized.
In the second aspect, the method comprises the steps of searching for candidate contour points which accord with a preset similarity threshold value in a contour index array to be detected by two times according to a first preset pixel step distance and comparing the sample contour index array with the index array to be detected; according to a second preset pixel step distance, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected, and searching a target profile point which accords with a preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance; and determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points, gradually narrowing the search range through multiple searches, and thus overcoming the problem of low precision of the traditional detection image.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a flow chart of a method for positioning a material image based on a contour position index according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a material image positioning device based on profile position index according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the production process of the bearing industry, a large number of material counting and identifying applications exist, and particularly, the material positioning and material identification in the aspects of flow control in the production process, warehousing inspection and acceptance, inventory checking, quantitative packaging and the like cannot be realized for the material rolling bodies with various numbers, varieties and specifications.
In the process of moving materials on a production line, the conventional visual detection technology recognizes the geometric center and the approximate angle of an object by using methods such as spot positioning and the like, so that the problems of poor precision, easiness in misjudgment and the like exist, and the conventional template matching mode has low searching speed although the precision can meet the requirement, and cannot meet the situation that the production beat requirement is fast. The conventional visual detection technology is used for identifying the geometric center and the approximate angle of an object by means of spot positioning and the like, so that the problems of poor precision, easiness in misjudgment and the like exist, and the conventional template matching mode is low in searching speed although the precision can meet the requirement, and cannot meet the situation that the production beat requirement is fast.
Therefore, the existing material image positioning method has the problems of low accuracy and low speed in the identification process.
In view of the above problems, no effective solution has been proposed at present.
The method is combined with chain plate transmission equipment, mechanical movement is combined with camera and polishing, all materials in a certain range of a chain plate are identified, and then counting is carried out after the material images are processed.
The application scene of the method comprises the following steps: and after the system is electrified, equipment software is started and logged in, the software starts the machine vision module to wait for a PLC signal to trigger a detection signal, the PLC motion control module is started, the feeding machine starts to convey materials to the chain plate, the started industrial camera and light source shoot and image process the materials in real time, the materials are positioned according to the contour position index-based material image positioning method provided by the application, and then the result is stored in the database.
It should be noted that the material in the present application may be a roller, for example, but not limited to a cylindrical roller, and may be a roller of other shapes.
Fig. 1 is a flow chart of a method for positioning a material image based on a contour position index according to an embodiment of the present application. The method comprises the following steps:
Step S101, identifying a sample contour point of the sample material image, and calculating a sample contour index array of the sample contour point.
The sample material image in this embodiment is a picture taken by a plane camera, so that the sample picture acquired by the plane camera needs to be detected and preprocessed to acquire the sample material image.
In one embodiment, identifying sample contour points of a sample material image includes: calculating the transverse gradient of the sample material image and the longitudinal gradient of the sample material image, and combining the transverse gradient image of the sample material image and the longitudinal gradient image of the sample material image; and carrying out binarization processing on the combined sample material images, and identifying the image contour of the sample material images after the binarization processing to obtain sample contour points of the sample material images.
In particular, for an input image function
Calculating the lateral gradient of the sample material image>
The calculation formula of (2) is shown in formula 1:
image function for input
Calculating the longitudinal gradient of the sample material image>
The calculation formula of (2) is shown in formula 2:
the calculation formula of combining the transverse gradient of the sample material image and the longitudinal gradient of the sample image to obtain a combined image G is shown as formula 3, and the formula 3 combines the transverse gradient and the longitudinal gradient of each pixel of the image to calculate the gradient of the pixel of the image.
then binarizing the combined image G to obtain a binarized image
The formula of (2) is shown in formula 4, wherein h is a preset edge threshold.
the binarization processing of the image is to set the gray scale of the point on the image to 0 or 255, that is, the whole image shows obvious black-and-white effect. I.e. the gray level image of 256 brightness levels is selected by a proper threshold value to obtain a binary image which can still reflect the whole and local characteristics of the image. The aggregate nature of the image is only related to the position of the point where the pixel value is 0 or 255, and the multi-level value of the pixel is not involved any more, so that the processing becomes simple, and the processing and compression amount of the data are small. In order to obtain an ideal binary image, a closed, connected boundary is generally used to define a non-overlapping region. All pixels with gray levels greater than or equal to the threshold are determined to belong to a particular object, with gray values of 255 indicating that otherwise the pixel points are excluded from the object area, and with gray values of 0 indicating the background or exceptional object area. If a particular object has uniform gray values within it and it is in a uniform background with other levels of gray values, a thresholding method can be used to obtain a comparative segmentation effect. If the difference between the object and the background is not represented by a gray scale value (e.g., a texture difference), the difference feature may be converted to a gray scale difference and the image may be segmented using a thresholding technique. The binarization of the dynamic adjustment threshold realization image can dynamically observe the specific result of the segmented image.
In one embodiment, the sample profile index array includes two-dimensional coordinates of the sample profile point and an index number corresponding to the sample profile point, the index number corresponding to the sample profile point is used to represent a position of the sample profile point in the sample material image, and calculating the sample profile index array of the sample profile point includes: setting a position index number according to a two-dimensional coordinate of a sample contour point in a sample material image and a preset index direction, wherein the position index number is a one-dimensional array; and obtaining a sample contour index array based on the two-dimensional coordinates of the sample contour points and the position index numbers of the sample contour points.
In this embodiment, in order to facilitate searching for the contour point, the index number of the contour point may be assigned according to the anticlockwise direction or according to the arrangement sequence of the pixel points of the sample material image, so as to facilitate searching for the corresponding contour point according to the position index.
Specifically, the sample profile index array includes two-dimensional coordinates of a sample profile point and an index number corresponding to the sample profile point, the index number corresponding to the sample profile point is used for indicating a position of the sample profile point in a sample material image, and the sample profile index array for calculating the sample profile point includes: setting position index numbers according to the two-dimensional coordinates of the sample contour points in the sample material image and the preset index direction, wherein the index numbers are one-dimensional arrays; and obtaining a sample contour index array based on the two-dimensional coordinates of the sample contour points and the position index numbers of the sample contour points. Specifically, adding the contour point index in the one-dimensional index array can be represented by the formula 5, wherein 
Representing the two-dimensional coordinates of the contour points, W being the width of the index array, +.>
And P is a corresponding index array for the position index number corresponding to the contour point.
step S102, identifying contour points to be detected of the material images to be detected in the images to be detected, and calculating a contour index array to be detected of the contour points to be detected.
In one embodiment, identifying contour points to be detected of an image of a material to be detected in an image to be detected includes: calculating the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected, and combining the transverse gradient of the material image to be detected and the longitudinal gradient image of the material image to be detected; and carrying out binarization processing on the combined material images to be detected, and identifying the image contour of the binarized material images to be detected to obtain contour points to be detected of the material images to be detected.
In this embodiment, the calculation of the transverse gradient image and the longitudinal gradient image of the image to be detected is mainly performed to enhance the image of the image to be detected. The lateral gradient image and the longitudinal gradient image are magnified in different details, so that the contour features of the combined images are more obvious. And (3) binarization processing, so that the gray value of the edge of the material is lower, and the background and the material communicating region are further distinguished. The binarization processing of the image is to set the gray scale of the point on the image to 0 or 255, that is, the whole image shows obvious black-and-white effect. I.e. the gray level image of 256 brightness levels is selected by a proper threshold value to obtain a binary image which can still reflect the whole and local characteristics of the image. The aggregate nature of the image is only related to the position of the point where the pixel value is 0 or 255, and the multi-level value of the pixel is not involved any more, so that the processing becomes simple, and the processing and compression amount of the data are small. In order to obtain an ideal binary image, a closed, connected boundary is generally used to define a non-overlapping region. All pixels with gray levels greater than or equal to the threshold are determined to belong to a particular object, with gray values of 255 indicating that otherwise the pixel points are excluded from the object area, and with gray values of 0 indicating the background or exceptional object area. If a particular object has uniform gray values within it and it is in a uniform background with other levels of gray values, a thresholding method can be used to obtain a comparative segmentation effect. If the difference between the object and the background is not represented by a gray scale value (e.g., a texture difference), the difference feature may be converted to a gray scale difference and the image may be segmented using a thresholding technique. The binarization of the dynamic adjustment threshold realization image can dynamically observe the specific result of the segmented image.
Specifically, the image function of the image to be detected is input, the transverse gradient of the image to be detected (as shown in the above formula 1) and the longitudinal gradient of the image to be detected (as shown in the above formula 2) are calculated respectively, the transverse gradient of the image to be detected and the longitudinal gradient of the image to be detected are combined to be G (as shown in the above formula 3), and the image to be detected is binarized to obtain a processed image (as shown in the above formula 4), wherein h is a preset edge threshold value.
In one embodiment, the profile index array to be detected includes two-dimensional coordinates of a profile point to be detected and an index number corresponding to the profile point to be detected, the index number corresponding to the profile point to be detected is used to represent a position of the profile point to be detected in the image to be detected, and the profile index array to be detected of the profile point to be detected is calculated, including: acquiring a position index number of an image to be detected according to the two-dimensional coordinates of the contour point to be detected and a preset index direction; and generating a contour index array to be detected according to the position index number and the two-dimensional coordinates of the contour point to be detected.
In this embodiment, in order to facilitate searching for the contour point, the index number of the contour point may be assigned according to the anticlockwise direction or according to the arrangement sequence of the pixel points of the sample material image, so as to facilitate searching for the corresponding contour point according to the position index. In order to ensure the accuracy of the index, the position index direction of the contour index to be detected is consistent with the sample index array.
Step S103, comparing the sample profile index array with the index array to be detected according to the first preset pixel step distance, and searching candidate profile points which accord with a preset similarity threshold in the profile index array to be detected.
In this embodiment, in the detection process, the image to be detected uses a gradient operator to obtain the pixel coordinates of the edge line, the pixel coordinates are converted into a one-dimensional index array through the address index, the offset is performed according to a certain step distance, then the offset and the sample data are subjected to overlap statistics, and the statistical result is drawn into an overlap proportion thermodynamic diagram, which mainly includes the following steps.
In one embodiment, comparing the sample profile index array with the to-be-detected index array according to a first preset pixel stride, and searching candidate profile points meeting a preset similarity threshold in the to-be-detected profile index array includes: acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set; shifting the sample profile index array according to the shifting angle and the first preset pixel step distance, and comparing the sample profile index array with the profile index array to be detected; drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to the comparison result; traversing a preset offset angle set to obtain a first thermodynamic diagram set of a profile index array to be detected, and selecting a first thermodynamic diagram with highest similarity from the first thermodynamic diagram set; and taking the point meeting the preset similarity threshold value as a candidate contour point from the first thermodynamic diagram with the highest similarity.
In this embodiment, the preset offset angle set includes first selecting an X-axis angle, and then generating the preset offset angle set according to a certain interval angle. And comparing the offset sample profile index array with the index array to be detected after each preset offset angle is selected, generating the similarity of each pixel point in the sample profile index array and the index array to be detected, and generating a thermodynamic diagram according to the comparison result in the offset process according to the similarity. That is, a thermodynamic diagram is generated each time a predetermined offset angle is selected for comparison.
In one embodiment, according to the comparison result, a thermodynamic diagram of the sample profile index array and the profile index array to be detected is drawn, including: determining pixel attributes corresponding to the contour points according to the similarity between the contour points in the wheel index array to be detected and the contour points of the sample contour index array; the pixel attribute corresponding to the contour point comprises a gray value of the contour point determined according to the similarity of the contour point; and generating a thermodynamic diagram according to the pixel attribute corresponding to the contour point of the contour index array to be detected.
In this embodiment, the similarity of the profile index array to be detected is expressed by using the formula (6), where the profile index array to be detected M is offset by k steps b and then is subjected to a sum operation with the sample array and then divided by the sample length in the formula (6) 
And obtaining the similarity F, and k is a plurality of index numbers.
in this embodiment, in the process of selecting the same preset offset angle, a thermodynamic diagram is generated according to the comparison result for the pixel points in the profile index array to be detected, where a preset similarity threshold may be set, as shown in formula (7), for the pixel points exceeding the preset similarity threshold, a corresponding pixel attribute (in this embodiment, a gray value 255 is given), and for the similar points not meeting the preset similarity threshold, a blank process is given.
and drawing a similarity thermodynamic diagram S, wherein j is a preset similarity threshold value, and an image larger than the similarity threshold value is endowed with a gray value 255.
In this embodiment, the thermodynamic diagrams are screened, a similarity threshold is specified, and the screened effective pixel coordinates are taken as the target coarse positioning positions, which can be said that the thermodynamic diagram with the largest gray value area is selected as the thermodynamic diagram with the highest similarity, namely the thermodynamic diagram with the largest candidate similarity points.
In one embodiment, the thermodynamic diagram with the most similar points is further determined, and if the thermodynamic diagram with the most similar points does not meet the preset requirement, it is determined that there is no material image to be detected in the images to be detected.
Step S104, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected according to a second preset pixel step, and searching the target profile points which accord with a preset similarity threshold in the candidate profile points, wherein the length of the second preset pixel step is smaller than that of the first preset pixel step.
In this embodiment, the candidate contour points to be detected are detected using a smaller step pitch
Conversion to index->
Performing secondary contour overlapping statistics on the periphery to obtain accuracyCoordinate position and angle, and more accurate similarity.
In one embodiment, according to a second preset pixel step, comparing the sample profile index array with the profile index array to be detected within a preset pixel range of the candidate profile points to be detected, and searching for a target profile point which meets a preset similarity threshold in the candidate profile points, wherein the length of the second preset pixel step is smaller than that of the first preset pixel step, and the method comprises the following steps: acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set; shifting the sample profile index array according to the shifting angle and the first preset pixel step distance in the preset pixel range of the candidate profile point to be detected, and comparing the sample profile index array with the profile index array to be detected; drawing a second thermodynamic diagram of the sample profile index array and the to-be-seen profile index array according to the comparison result; traversing a preset offset angle set to obtain a second thermodynamic diagram set of the profile index array to be detected, and selecting a second thermodynamic diagram with highest similarity from the second thermodynamic diagram set; and selecting a point meeting a preset similarity threshold from the second thermodynamic diagram with highest similarity as a target contour point.
In this embodiment, the preset offset angle set includes first selecting an X-axis angle, and then generating the preset offset angle set according to a certain interval angle. And comparing the offset sample profile index array with candidate profile points to be detected in the index array to generate similarity of the candidate profile points to be detected in the sample profile index array and the index array to be detected after each preset offset angle is selected, and generating a thermodynamic diagram according to the comparison result in the offset process according to the similarity. That is, a thermodynamic diagram is generated each time a predetermined offset angle is selected for comparison.
It should be noted that, corresponding to the candidate to-be-detected contour points of the to-be-detected contour index array, the pixel points except the candidate to-be-detected contour points in the to-be-detected contour index array can be subjected to blank processing, a second group of index numbers are given to the candidate to-be-detected contour points, and the second group of index arrays with the newly given index numbers are compared with the sample contour index array, so that more accurate pixel points and more accurate offset pixel distances can be screened.
In one embodiment, according to the comparison result, a second thermodynamic diagram of the sample profile index array and the to-be-seen profile index array is drawn; selecting a second thermodynamic diagram with highest similarity, and selecting candidate contour points to be detected, which meet a preset similarity threshold, in the second thermodynamic diagram with the similarity as target contour points according to the preset similarity threshold, wherein the candidate contour points comprise: determining pixel attributes corresponding to the contour points according to the similarity between the second index array (namely the index array of the candidate contour points to be detected) and the contour points of the sample contour index array; the pixel attribute corresponding to the contour point comprises a gray value of the contour point determined according to the similarity of the contour point; and generating a second thermodynamic diagram according to the pixel attribute corresponding to the contour point of the contour index array to be detected.
In this embodiment, in the process of selecting the same preset offset angle, a thermodynamic diagram is generated according to the comparison result for the pixel points in the profile index array to be detected, where a preset similarity threshold may be set, as shown in the above formula (7), for the pixel points exceeding the preset similarity threshold, a corresponding pixel attribute (in this embodiment, a gray value of 255) is assigned, and for the similar points not meeting the preset similarity threshold, a blank process is assigned
In this embodiment, the thermodynamic diagrams are screened, a similarity threshold is specified, and the screened effective pixel coordinates are taken as the target contour points, which can be said that the thermodynamic diagram with the largest gray value area is selected as the thermodynamic diagram with the highest similarity, that is, the thermodynamic diagram with the largest target contour points.
Step S105, determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points.
In this embodiment, coordinates of the target contour point are compared with contour points of the target contour point in the sample contour index array, a position difference of the target contour point in the sample material image and the material image to be detected is calculated according to a comparison result, and position information of the material to be detected in the image to be detected is determined according to the position difference.
As shown in fig. 2, the present invention further provides a material image positioning device based on contour position index according to a second aspect of the present application, including:
a first identifying unit 201, configured to identify a sample contour point of a sample material image, and calculate a sample contour index array of the sample contour point;
the second identifying unit 202 is configured to identify a contour point to be detected of the material image to be detected in the image to be detected, and calculate a contour index array to be detected of the contour point to be detected;
the first index unit 203 is configured to compare the sample profile index array with the index array to be detected according to a first preset pixel step, and find candidate profile points in the profile index array to be detected, where the candidate profile points meet a preset similarity threshold;
a second index unit 204, configured to compare the sample profile index array and the profile index array to be detected within a preset pixel range of the candidate profile points to be detected according to a second preset pixel step, and find a target profile point that meets the preset similarity threshold in the candidate profile points, where a length of the second preset pixel step is smaller than a length of the first preset pixel step;
And the determining unit 205 is configured to determine position information of the material to be detected in the image to be detected according to the coordinates of the target contour point.
In one embodiment, identifying sample contour points of a sample material image includes: calculating the transverse gradient of the sample material image and the longitudinal gradient of the sample material image, and combining the transverse gradient of the sample material image and the longitudinal gradient image of the sample material image; and carrying out binarization processing on the combined sample material images, and identifying the image contour of the sample material images after the binarization processing to obtain sample contour points of the sample material images.
In one embodiment, the sample profile index array includes two-dimensional coordinates of the sample profile point and an index number corresponding to the sample profile point, the index number corresponding to the sample profile point is used to represent a position of the sample profile point in the sample material image, and calculating the sample profile index array of the sample profile point includes: setting a position index number according to a two-dimensional coordinate of a sample contour point in a sample material image and a preset index direction, wherein the position index number is a one-dimensional array; and obtaining a sample contour index array based on the two-dimensional coordinates of the sample contour points and the position index numbers of the sample contour points.
In one embodiment, identifying contour points to be detected of an image of a material to be detected in an image to be detected includes: calculating the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected, and combining the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected; and carrying out binarization processing on the combined material images to be detected, and identifying the image contour of the binarized material images to be detected to obtain contour points to be detected of the material images to be detected.
In one embodiment, the profile index array to be detected includes two-dimensional coordinates of a profile point to be detected and an index number corresponding to the profile point to be detected, the index number corresponding to the profile point to be detected is used to represent a position of the profile point to be detected in the image to be detected, and the profile index array to be detected of the profile point to be detected is calculated, including: acquiring a position index number of an image to be detected according to the two-dimensional coordinates of the contour point to be detected and a preset index direction; and generating a contour index array to be detected according to the position index number and the two-dimensional coordinates of the contour point to be detected.
In one embodiment, comparing the sample profile index array with the to-be-detected index array according to a first preset pixel stride, and searching candidate profile points meeting a preset similarity threshold in the to-be-detected profile index array includes: acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set; shifting the sample profile index array according to the shifting angle and the first preset pixel step distance, and comparing the sample profile index array with the profile index array to be detected; drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to the comparison result; traversing a preset offset angle set to obtain a first thermodynamic diagram set of a profile index array to be detected, and selecting a first thermodynamic diagram with highest similarity from the first thermodynamic diagram set; and selecting a point meeting a preset similarity threshold from the first thermodynamic diagram with highest similarity as a candidate contour point.
In one embodiment, drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to the comparison result includes: determining pixel attributes corresponding to the contour points according to the similarity between the contour points in the wheel index array to be detected and the contour points of the sample contour index array; the pixel attribute corresponding to the contour point comprises a gray value of the contour point determined according to the similarity of the contour point; and generating a first thermodynamic diagram according to the pixel attribute corresponding to the contour point of the contour index array to be detected.
In one embodiment, according to a second preset pixel step, comparing the sample profile index array with the profile index array to be detected within a preset pixel range of the candidate profile points to be detected, and searching for a target profile point which meets a preset similarity threshold in the candidate profile points, wherein the length of the second preset pixel step is smaller than that of the first preset pixel step, and the method comprises the following steps: acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set; shifting the sample profile index array according to the shifting angle and the first preset pixel step distance in the preset pixel range of the candidate profile point to be detected, and comparing the sample profile index array with the profile index array to be detected; drawing a second thermodynamic diagram of the sample profile index array and the to-be-seen profile index array according to the comparison result; traversing a preset offset angle set to obtain a second thermodynamic diagram set of the profile index array to be detected, and selecting a second thermodynamic diagram with highest similarity from the second thermodynamic diagram set; and selecting a point meeting a preset similarity threshold from the second thermodynamic diagram with highest similarity as a target contour point.
The technical scheme that this application provided can include following beneficial effect:
in a first aspect, the present application calculates a sample profile index array of sample profile points by identifying sample profile points of a sample material image; identifying contour points to be detected of a material image to be detected in the image to be detected, and calculating a contour index array to be detected of the contour points to be detected; the sample material image is simplified into the index array, then the sample profile index array is subjected to multiple selection and conversion according to a certain step distance to obtain a group of multi-angle sample index arrays, and then the multi-angle index arrays are compared with the profile index array to be detected, so that the accuracy of searching the to-be-detected point is improved, and the object positioning identification high-speed, high-precision and high-real-time detection is realized.
In the second aspect, the method comprises the steps of searching for candidate contour points which accord with a preset similarity threshold value in a contour index array to be detected by two times according to a first preset pixel step distance and comparing the sample contour index array with the index array to be detected; according to a second preset pixel step distance, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected, and searching a target profile point which accords with a preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance; and determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points, gradually narrowing the search range through multiple searches, and thus overcoming the problem of low precision of the traditional detection image.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Referring to fig. 3, an electronic device 300 includes a memory 310 and a processor 320.
The processor 320 may be a central processing unit (CentralProceSing Unit, CPU), but may also be other general purpose processors, digital Signal Processors (DSP), application specific integrated circuits (ApplicationSpecific Integrated Circuit, ASIC), field-programmable gate arrays (Field-ProgrammableGate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Memory 310 may include various types of storage units such as system memory, read Only Memory (ROM), and persistent storage. Where the ROM may store static data or instructions that are required by the processor 320 or other modules of the computer. The persistent storage may be a readable and writable storage. The persistent storage may be a non-volatile memory device that does not lose stored instructions and data even after the computer is powered down. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the persistent storage may be a removable storage device (e.g., diskette, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as dynamic random access memory. The system memory may store instructions and data that are required by some or all of the processors at runtime. Furthermore, memory 310 may include any combination of computer-readable storage media including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks, and/or optical disks may also be employed. In some implementations, memory 310 may include a readable and/or writable removable storage device such as a Compact Disc (CD), a digital versatile disc read only (e.g., DVD-ROM, dual layer DVD-ROM), a blu-ray read only disc, an ultra-dense disc, a flash memory card (e.g., SD card, minSD card, micro-SD card, etc.), a magnetic floppy disk, and the like. The computer readable storage medium does not contain a carrier wave or an instantaneous electronic signal transmitted by wireless or wired transmission.
The memory 310 has stored thereon executable code that, when processed by the processor 320, can cause the processor 320 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing part or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) having stored thereon executable code (or a computer program or computer instruction code) which, when executed by a processor of an electronic device (or a server, etc.), causes the processor to perform part or all of the steps of the above-described methods according to the present application.
The embodiments of the present application have been described above, the foregoing description is exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (11)
1. The material image positioning method based on the contour position index is characterized by comprising the following steps of:
identifying sample contour points of a sample material image, and calculating a sample contour index array of the sample contour points;
identifying contour points to be detected of a material image to be detected in the image to be detected, and calculating a contour index array to be detected of the contour points to be detected;
according to a first preset pixel step distance, comparing the sample profile index array with the index array to be detected, and searching candidate profile points which accord with a preset similarity threshold in the profile index array to be detected;
according to a second preset pixel step distance, comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected, and searching target profile points which accord with the preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance;
and determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour points.
2. The method of claim 1, wherein identifying sample contour points of the sample material image comprises:
Calculating the transverse gradient of the sample material image and the longitudinal gradient of the sample material image, and combining the transverse gradient of the sample material image and the longitudinal gradient image of the sample material image;
and carrying out binarization processing on the combined sample material images, and identifying the image contour of the sample material images after the binarization processing to obtain sample contour points of the sample material images.
3. The method of claim 1, wherein the sample profile index array includes two-dimensional coordinates of a sample profile point and an index number corresponding to the sample profile point, the index number corresponding to the sample profile point being used to represent a position of the sample profile point in the sample material image, the calculating the sample profile index array of the sample profile point comprising:
setting position index numbers according to two-dimensional coordinates of the sample contour points in the sample material image and a preset index direction, wherein the position index numbers are one-dimensional arrays;
and obtaining the sample contour index array based on the two-dimensional coordinates of the sample contour points and the position index numbers of the sample contour points.
4. The method of claim 1, wherein identifying contour points to be detected of the image of the material to be detected in the image to be detected comprises:
Calculating the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected, and combining the transverse gradient of the material image to be detected and the longitudinal gradient of the material image to be detected;
and carrying out binarization processing on the combined material images to be detected, and identifying the image contour of the binarized material images to be detected to obtain the contour points to be detected of the material images to be detected.
5. The method according to claim 1, wherein the profile index array to be detected includes two-dimensional coordinates of a profile point to be detected and an index number corresponding to the profile point to be detected, the index number corresponding to the profile point to be detected is used to represent a position of the profile point to be detected in the image to be detected, and the calculating the profile index array to be detected of the profile point to be detected includes:
acquiring a position index number of an image to be detected according to the two-dimensional coordinates of the contour point to be detected and a preset index direction;
and generating the profile index array to be detected according to the position index number and the two-dimensional coordinates of the profile point to be detected.
6. The method of claim 1, wherein comparing the sample profile index array and the index array to be detected according to a first predetermined pixel stride, and searching candidate profile points in the profile index array to be detected that meet a predetermined similarity threshold, comprises:
Acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set;
shifting the sample profile index array according to the shifting angle and the first preset pixel step distance, and comparing the sample profile index array with the profile index array to be detected;
drawing a first thermodynamic diagram of the sample profile index array and the profile index array to be detected according to a comparison result;
traversing the preset offset angle set to obtain a first thermodynamic diagram set of the profile index array to be detected, and selecting a first thermodynamic diagram with highest similarity from the first thermodynamic diagram set;
and selecting a point meeting a preset similarity threshold from the first thermodynamic diagram with the highest similarity as a candidate contour point.
7. The method of claim 6, wherein the mapping the first thermodynamic diagram of the sample profile index array and the profile index array to be detected based on the comparison result comprises:
determining pixel attributes corresponding to contour points according to the similarity between the contour points in the wheel index array to be detected and the contour points of the sample contour index array;
the pixel attributes corresponding to the contour points comprise gray values of the contour points determined according to the similarity of the contour points;
And generating the first thermodynamic diagram according to the pixel attribute corresponding to the contour point of the contour index array to be detected.
8. The method according to claim 1, wherein the comparing the sample profile index array with the profile index array to be detected within a preset pixel range of the candidate profile points to be detected according to a second preset pixel step, and searching for a target profile point meeting the preset similarity threshold in the candidate profile points, wherein the second preset pixel step has a length smaller than that of the first preset pixel step, includes:
acquiring a preset offset angle set, and selecting an offset angle from the preset offset angle set;
shifting the sample profile index array according to the shifting angle and the first preset pixel step distance in the preset pixel range of the candidate profile point to be detected, and comparing the sample profile index array with the profile index array to be detected;
drawing a second thermodynamic diagram of the sample profile index array and the to-be-seen profile index array according to the comparison result;
traversing the preset offset angle set to obtain a second thermodynamic diagram set of the profile index array to be detected, and selecting a second thermodynamic diagram with highest similarity from the second thermodynamic diagram set;
And selecting a point meeting a preset similarity threshold from the second thermodynamic diagram with the highest similarity as a target contour point.
9. A contour position index-based material image positioning device, comprising:
the first identification unit is used for identifying sample contour points of the sample material image and calculating a sample contour index array of the sample contour points;
the second identification unit is used for identifying outline points to be detected of the material images to be detected in the images to be detected and calculating an outline index array to be detected of the outline points to be detected;
the first index unit is used for comparing the sample profile index array with the index array to be detected according to a first preset pixel step distance, and searching candidate profile points which accord with a preset similarity threshold value in the profile index array to be detected;
the second index unit is used for comparing the sample profile index array with the profile index array to be detected in a preset pixel range of the candidate profile points to be detected according to a second preset pixel step distance, and searching target profile points which accord with the preset similarity threshold value in the candidate profile points, wherein the length of the second preset pixel step distance is smaller than that of the first preset pixel step distance;
And the determining unit is used for determining the position information of the material to be detected in the image to be detected according to the coordinates of the target contour point.
10. An electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor causes the processor to perform the method of any of claims 1 to 8.
11. A computer readable storage medium having stored thereon executable code which when executed by a processor of an electronic device causes the processor to perform the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280394.XA CN115994906B (en) | 2023-03-22 | 2023-03-22 | Material image positioning method and device based on contour position index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280394.XA CN115994906B (en) | 2023-03-22 | 2023-03-22 | Material image positioning method and device based on contour position index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115994906A true CN115994906A (en) | 2023-04-21 |
| CN115994906B CN115994906B (en) | 2023-06-20 |
Family
ID=85992368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310280394.XA Active CN115994906B (en) | 2023-03-22 | 2023-03-22 | Material image positioning method and device based on contour position index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994906B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993811A (en) * | 2019-03-19 | 2019-07-09 | 广东智媒云图科技股份有限公司 | A kind of creation of works method and device based on skin texture material |
| EP3683721A1 (en) * | 2019-01-18 | 2020-07-22 | Intelligrated Headquarters LLC | A material handling method, apparatus, and system for identification of a region-of-interest |
| CN112258578A (en) * | 2020-09-28 | 2021-01-22 | 深圳数马电子技术有限公司 | Coordinate origin measuring method and device |
| WO2022258398A1 (en) * | 2021-06-07 | 2022-12-15 | Asml Netherlands B.V. | Determining rounded contours for lithography related patterns |
| CN115619775A (en) * | 2022-12-02 | 2023-01-17 | 杭州深度视觉科技有限公司 | Material counting method and device based on image recognition |
-
2023
- 2023-03-22 CN CN202310280394.XA patent/CN115994906B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3683721A1 (en) * | 2019-01-18 | 2020-07-22 | Intelligrated Headquarters LLC | A material handling method, apparatus, and system for identification of a region-of-interest |
| CN109993811A (en) * | 2019-03-19 | 2019-07-09 | 广东智媒云图科技股份有限公司 | A kind of creation of works method and device based on skin texture material |
| CN112258578A (en) * | 2020-09-28 | 2021-01-22 | 深圳数马电子技术有限公司 | Coordinate origin measuring method and device |
| WO2022258398A1 (en) * | 2021-06-07 | 2022-12-15 | Asml Netherlands B.V. | Determining rounded contours for lithography related patterns |
| CN115619775A (en) * | 2022-12-02 | 2023-01-17 | 杭州深度视觉科技有限公司 | Material counting method and device based on image recognition |
Non-Patent Citations (2)
| Title |
|---|
| BILEL SDIRI等: "Efficient enhancement of stereo endoscopic images based on joint wavelet decomposition and binocular combination", 《IEEE TRANSACTION ON MEDICAL IMAGING》 * |
| 冯绍欣: "基于双目视觉的物料袋空间定位方法研究", 《万方数据》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115994906B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10671835B2 (en) | Object recognition | |
| US11227405B2 (en) | Determining positions and orientations of objects | |
| US8422759B2 (en) | Image processing method and image processing device | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| US20130033617A1 (en) | Generating an image presegmented into regions of interest and regions of no interest | |
| CN107240130B (en) | Remote sensing image registration method, device and system | |
| CN111444964A (en) | Multi-target rapid image matching method based on self-adaptive ROI (region of interest) division | |
| CN111968115B (en) | Method and system for detecting orthopedic consumables based on rasterization image processing method | |
| CN111814852A (en) | Image detection method, image detection device, electronic equipment and computer-readable storage medium | |
| CN117474929A (en) | Tray outline dimension detection method and system based on machine vision | |
| CN115619775B (en) | Material counting method and device based on image recognition | |
| CN110807354B (en) | Industrial assembly line product counting method | |
| CN107895166B (en) | Method for realizing target robust recognition based on feature descriptor by geometric hash method | |
| CN115994906B (en) | Material image positioning method and device based on contour position index | |
| CN105139508A (en) | Method and device for detecting paper money | |
| CN118135179B (en) | Cascade identification method and device for cutting plate, computer equipment and storage medium | |
| CN111507177B (en) | Identification method and device for metering turnover cabinet | |
| CN117333458A (en) | Method and system for detecting irregular workpieces with holes based on contour difference | |
| CN114049380B (en) | Target object positioning and tracking method, device, computer equipment and storage medium | |
| CN116563837A (en) | High-precision map guideboard graphic data resolving method, device, equipment and storage medium | |
| CN114146939A (en) | Multi-view visual part sorting method and system based on abnormal point detection | |
| KR20090002638A (en) | Method for measuring similarity using frenquency range | |
| CN111753723A (en) | Fingerprint identification method and device based on density calibration | |
| CN118229672B (en) | Mark image positioning method and system based on film color difference | |
| CN117053696A (en) | High-precision measuring method and system for width of large-width film |
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 |