CN112541894B - Product deformation detection method - Google Patents
Product deformation detection method Download PDFInfo
- Publication number
- CN112541894B CN112541894B CN202011463917.7A CN202011463917A CN112541894B CN 112541894 B CN112541894 B CN 112541894B CN 202011463917 A CN202011463917 A CN 202011463917A CN 112541894 B CN112541894 B CN 112541894B
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- product
- reference image
- edge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000009499 grossing Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a product deformation detection method, which comprises the following steps: s1: registering a reference image; s2: processing the reference image and setting detection parameters and a judgment threshold value; s3: processing an image to be detected; s4: and outputting a detection result according to the processing result and the judging threshold value. The S1: the reference image is registered as registering one reference image: (1) The reference image is a normal product image shot by a user and is used for setting a detection area and detection conditions; (2) The user selects a desired detection area in the reference image for detecting the deformation, the detection area should comprise at least two repeated shapes. According to the deformation detection method of the product, the calculation complexity is low, the detection result can avoid illumination change and image noise influence by gradient integration, sliding average and other methods, the position of the center line of the repeated shape of the product can be stably detected, and meanwhile, the upper limit unit of the set judgment condition of the method is one pixel, so that the detection precision is high, and tiny deformation can be identified by matching with a high-definition camera and a lens.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a product deformation detection method.
Background
The Image processing technology is a technology for processing Image information by a computer and mainly comprises Image digitization, image enhancement and restoration, image data coding, image segmentation, image recognition and the like, wherein geometric figures (Graphics) are composed of points, lines, planes, colors and the like, are generated by a drawing program and are a set of a series of drawing instructions, and are generally manufactured by various drawing software, and a dot matrix Image (Image) is composed of various pixel points and colors, is obtained by using equipment such as a video camera, a scanner, a digital camera and the like, and can also be generated by using the drawing software.
The existing deformation detection method adopts a template matching method, namely, the current product image and the normal product image are compared, the similarity of the current product image and the normal product image is calculated, if the similarity is lower than a certain threshold value, the product is considered to be deformed, otherwise, the product is considered to be normal, the method is generally time-consuming under the condition of large image area because a similarity matching algorithm is needed, in addition, the detection precision of the method is not high, if the product is only slightly deformed, the method possibly fails to detect, the current product image and the normal product image are differentiated, the pixel area of the differential image is calculated, if the area is higher than a certain threshold value, the current product is considered to be deformed, otherwise, the calculation is simple and efficient, but the method is often influenced by image noise, and false detection or omission is easy to occur.
Disclosure of Invention
The invention aims to provide a product deformation detection method, which is used for solving the problems that the existing deformation detection method in the background technology adopts a template matching method, namely, the similarity of a current product image and a normal product image is compared, the product is considered to be deformed if the similarity is lower than a certain threshold value, otherwise, the product is considered to be normal, the similarity matching algorithm is needed, the algorithm is generally time-consuming under the condition of large image area, in addition, the detection precision is not high, the method can be missed if the product only slightly deforms, the method also comprises the steps of differentiating the current product image and the normal product image, calculating the pixel area of a differential image, and considering the current product to deform if the area is higher than a certain threshold value, otherwise, the method is simple and efficient, but is often influenced by image noise, and the problem of false detection or missing detection easily occurs.
A method for detecting deformation of a product comprises the following steps:
s1: registering a reference image;
s2: processing the reference image and setting detection parameters and a judgment threshold value;
s3: processing an image to be detected;
s4: and outputting a detection result according to the processing result and the judging threshold value.
Preferably, the step S1: the reference image is registered as registering one reference image:
(1) The reference image is a normal product image shot by a user and is used for setting a detection area and detection conditions;
(2) The user selects a detection area for detecting deformation in the reference image, wherein the detection area comprises at least two repeated shapes;
(3) The reference image detection area image is set to P0.
Preferably, the step S2: processing a reference image, setting detection parameters and a judgment threshold value as set detection directions, wherein the detection directions are divided into a horizontal direction and a vertical direction, setting an edge threshold value percentage, marking as P, and setting an edge smoothing coefficient W, and specifically comprising the following steps:
(1) Copy detection area image P0
(2) Performing binarization processing on the P0 to obtain an image P1, and setting a binarization threshold value to be automatic;
(3) Processing P1 along a set detection direction by using a Sobel operator to obtain a gray level map P2;
(4) Integrating the P2 along the direction perpendicular to the set detection direction to obtain a one-dimensional array Q1;
(5) Smoothing the Q1 by using a sliding average algorithm to obtain Q2, wherein the size of a smoothing window is a smoothing coefficient W set by a user;
(6) Calculating the maximum value in Q2 and recording the maximum value as Max;
(7) And calculating an edge threshold t=max×p according to the set edge threshold percentage P.
Preferably, the step S3: the image to be detected is processed to set an edge threshold percentage and an edge smoothing coefficient, the positions of center lines of repeated shapes in the detection area are detected along the set detection direction, and the number of the center lines, the maximum distance between adjacent center lines and the minimum distance between adjacent center lines are calculated, wherein the unit is a pixel.
Preferably, the step S4: outputting a detection result according to the processing result and the judging threshold value, wherein the detection result is the upper limit and the lower limit of the number of the central lines and the central line distance according to the calculated number of the central lines of the normal products and the maximum and minimum distances, and if the number of the central lines or the central line distance of the products to be detected exceeds the set upper limit and the lower limit, the products can be considered to be deformed, and the specific steps are as follows:
(1) Traversing all elements Q2[ i ] in Q2, when |Q2[ i ] | > T and |Q2[ i ] | is not less than |Q2[ i-1] | and |Q2[ i ] | is not less than |Q2[ i+1] |, considering that a position i has an obvious edge, and sequentially recording all the i meeting the conditions into an array Q3
(2) Traversing all elements Q3[ i ] in Q3, when i is even, forming a pair of even subscripts and adjacent elements of odd subscripts, calculating an average value a= (Q3i+Q3i+1)/2 0, wherein a is the position of two edge central lines, recording all a into an array Q4, and storing the positions of all the edge central lines by Q4.
Preferably, the same detection area is extracted, the positions of the center lines of the repeated shapes in the detection area are detected along the same detection direction, and the number of the center lines and the maximum distance and the minimum distance between the adjacent center lines are calculated, wherein the units are pixels.
Preferably, the number of center lines or the center line distance of the product to be detected exceeds the set upper limit and the set lower limit, deformation is considered to occur, a NG signal is output, and otherwise an OK signal is output.
Compared with the prior art, the invention has the following beneficial effects: the method has low calculation complexity, can avoid illumination change and image noise influence of detection results by gradient integration, sliding average and other methods, can stably detect the position of the center line of the repeated shape of the product, and can identify micro deformation by matching with a high-definition camera and a lens because the upper limit unit of the set judgment condition of the method is one pixel.
Drawings
FIG. 1 is a flow chart of a method for detecting deformation of a product according to the present invention;
FIG. 2 is a flow chart of the repeated shape center line position detection of the product deformation detection method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Referring to fig. 1-2, the present invention provides a technical solution: a method for detecting deformation of a product comprises the following steps:
s1: registering a reference image;
s2: processing the reference image and setting detection parameters and a judgment threshold value;
s3: processing an image to be detected;
s4: and outputting a detection result according to the processing result and the judging threshold value.
Preferably, the step S1: the reference image is registered as registering one reference image:
(1) The reference image is a normal product image shot by a user and is used for setting a detection area and detection conditions;
(2) The user selects a detection area for detecting deformation in the reference image, wherein the detection area comprises at least two repeated shapes;
(3) The reference image detection area image is set to P0.
Preferably, the step S2: processing a reference image, setting detection parameters and a judgment threshold value as set detection directions, wherein the detection directions are divided into a horizontal direction and a vertical direction, setting an edge threshold value percentage, marking as P, and setting an edge smoothing coefficient W, and specifically comprising the following steps:
(1) Copy detection area image P0
(2) Performing binarization processing on the P0 to obtain an image P1, and setting a binarization threshold value to be automatic;
(3) Processing P1 along a set detection direction by using a Sobel operator to obtain a gray level map P2;
(4) Integrating the P2 along the direction perpendicular to the set detection direction to obtain a one-dimensional array Q1;
(5) Smoothing the Q1 by using a sliding average algorithm to obtain Q2, wherein the size of a smoothing window is a smoothing coefficient W set by a user;
(6) Calculating the maximum value in Q2 and recording the maximum value as Max;
(7) And calculating an edge threshold t=max×p according to the set edge threshold percentage P.
Preferably, the step S3: the image to be detected is processed to set an edge threshold percentage and an edge smoothing coefficient, the positions of center lines of repeated shapes in the detection area are detected along the set detection direction, and the number of the center lines, the maximum distance between adjacent center lines and the minimum distance between adjacent center lines are calculated, wherein the unit is a pixel.
Preferably, the step S4: outputting a detection result according to the processing result and the judging threshold value, wherein the detection result is the upper limit and the lower limit of the number of the central lines and the central line distance according to the calculated number of the central lines of the normal products and the maximum and minimum distances, and if the number of the central lines or the central line distance of the products to be detected exceeds the set upper limit and the lower limit, the products can be considered to be deformed, and the specific steps are as follows:
(1) Traversing all elements Q2[ i ] in Q2, when |Q2[ i ] | > T and |Q2[ i ] | is not less than |Q2[ i-1] | and |Q2[ i ] | is not less than |Q2[ i+1] |, considering that a position i has an obvious edge, and sequentially recording all the i meeting the conditions into an array Q3
(2) Traversing all elements Q3[ i ] in Q3, when i is even, forming a pair of even subscripts and adjacent elements of odd subscripts, calculating an average value a= (Q3i+Q3i+1)/2 0, wherein a is the position of two edge central lines, recording all a into an array Q4, and storing the positions of all the edge central lines by Q4.
Preferably, the same detection area is extracted, the positions of the center lines of the repeated shapes in the detection area are detected along the same detection direction, and the number of the center lines and the maximum distance and the minimum distance between the adjacent center lines are calculated, wherein the units are pixels.
Preferably, the number of center lines or the center line distance of the product to be detected exceeds the set upper limit and the set lower limit, deformation is considered to occur, a NG signal is output, and otherwise an OK signal is output.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (3)
1. A method for detecting deformation of a product comprises the following steps:
s1: detecting image importing; s1: the detected image is imported to register a reference image:
(1) The reference image is a normal product image shot by a user and is used for setting a detection area and detection conditions;
(2) The user selects a detection area for detecting deformation in the reference image, wherein the detection area comprises at least two repeated shapes;
(3) Setting a reference image detection area image as P0;
s2: importing an image for preprocessing; s2: the imported image preprocessing is to set the detection direction:
(1) The detection direction is divided into a horizontal direction and a vertical direction;
(2) Performing binarization processing on the P0 to obtain an image P1, and setting a binarization threshold value to be automatic;
(3) Processing P1 along a set detection direction by using a Sobel operator to obtain a gray level map P2;
s3: processing the detection image, S3: processing the detection image to set an edge threshold percentage and an edge smoothing coefficient, detecting the positions of center lines of repeated shapes in the detection area along the set detection direction, and calculating the number of the center lines and the maximum distance and the minimum distance between adjacent center lines, wherein the units are pixels:
(1) Setting an edge threshold percentage, marking as P, and setting an edge smoothing coefficient W;
(2) Integrating the gray level map P2 along the direction perpendicular to the set detection direction to obtain a one-dimensional array Q1;
(3) Smoothing the Q1 by using a Gaussian sliding average algorithm to obtain Q2, wherein the size of a smoothing window is a smoothing coefficient W set by a user;
s4: calculating an image threshold value, S4: the image threshold is calculated as the upper and lower limits of the number of the central lines and the central line distance according to the number of the central lines of the calculated normal products and the maximum and minimum distances, and if the number of the central lines or the central line distance of the products to be detected exceeds the set upper limit, the products can be considered to be deformed, and the specific steps are as follows:
(1) Calculating the maximum value in Q2 as Max, and calculating an edge threshold T=Max×P according to the set edge threshold percentage P;
(2) Traversing all elements Q2[ i ] in Q2, when |Q2[ i ] | > T and |Q2[ i ] | is not less than |Q2[ i-1] | and |Q2[ i ] | is not less than |Q2[ i+1] |, considering that a position i has an obvious edge, and sequentially recording all the i meeting the conditions into an array Q3
(3) Traversing all elements Q3[ i ] in Q3, when i is even, forming a pair of even subscripts and adjacent elements of odd subscripts, calculating an average value a= (Q3i+Q3i+1)/2 0, wherein a is the position of two edge central lines, recording all a into an array Q4, and storing the positions of all the edge central lines by Q4.
2. The method for detecting deformation of a product according to claim 1, wherein: the S4: and (3) extracting the same detection area from the image threshold value, detecting the positions of the center lines of the repeated shapes in the detection area along the same detection direction, and calculating the number of the center lines, the maximum distance and the minimum distance between the adjacent center lines, wherein the units are pixels.
3. The method for detecting deformation of a product according to claim 1, wherein: and if the number of the center lines or the center line distance of the product to be detected exceeds a set upper limit, the product is considered to be deformed, a NG signal is output, and otherwise, an OK signal is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463917.7A CN112541894B (en) | 2020-12-11 | 2020-12-11 | Product deformation detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463917.7A CN112541894B (en) | 2020-12-11 | 2020-12-11 | Product deformation detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112541894A CN112541894A (en) | 2021-03-23 |
| CN112541894B true CN112541894B (en) | 2023-12-08 |
Family
ID=75018535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011463917.7A Active CN112541894B (en) | 2020-12-11 | 2020-12-11 | Product deformation detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541894B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519359A (en) * | 2011-12-12 | 2012-06-27 | 山东明佳包装检测科技有限公司 | Method for detecting label of polyethylene terephthalate (PET) bottle |
| GB201507124D0 (en) * | 2015-04-27 | 2015-06-10 | Thermoteknix Systems Ltd | Conveyer belt monitoring system and method |
| CN104897463A (en) * | 2015-04-16 | 2015-09-09 | 广东工业大学 | Real-time detection apparatus and real-time detection method of steel-concrete combination member deformation due to force applying |
| CN105405142A (en) * | 2015-11-12 | 2016-03-16 | 冯平 | Edge defect detection method and system for glass panel |
| CN105548201A (en) * | 2016-01-15 | 2016-05-04 | 浙江野马电池有限公司 | Battery welding cap visual-inspection method |
| CN108564602A (en) * | 2018-04-16 | 2018-09-21 | 北方工业大学 | Airplane detection method based on airport remote sensing image |
| CN108734716A (en) * | 2018-04-21 | 2018-11-02 | 卞家福 | A kind of fire complex environment image detecting method based on improvement Prewitt operators |
| CN109447946A (en) * | 2018-09-26 | 2019-03-08 | 中睿通信规划设计有限公司 | A kind of Overhead optical cable method for detecting abnormality |
| CN109934839A (en) * | 2019-03-08 | 2019-06-25 | 北京工业大学 | A kind of workpiece inspection method of view-based access control model |
| CN110287752A (en) * | 2019-06-25 | 2019-09-27 | 北京慧眼智行科技有限公司 | A kind of dot matrix code detection method and device |
| CN110866486A (en) * | 2019-11-12 | 2020-03-06 | Oppo广东移动通信有限公司 | Subject detection method and apparatus, electronic device, and computer-readable storage medium |
| CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
| CN111754460A (en) * | 2020-05-25 | 2020-10-09 | 北京驿禄轨道交通工程有限公司 | Method, system and storage medium for automatically detecting gap of point switch |
| CN111829912A (en) * | 2019-04-22 | 2020-10-27 | 济南恒旭试验机技术有限公司 | Four-ball friction tester wear mark measuring method |
| CN111833366A (en) * | 2020-06-03 | 2020-10-27 | 佛山科学技术学院 | Edge detection method based on Canny algorithm |
-
2020
- 2020-12-11 CN CN202011463917.7A patent/CN112541894B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519359A (en) * | 2011-12-12 | 2012-06-27 | 山东明佳包装检测科技有限公司 | Method for detecting label of polyethylene terephthalate (PET) bottle |
| CN104897463A (en) * | 2015-04-16 | 2015-09-09 | 广东工业大学 | Real-time detection apparatus and real-time detection method of steel-concrete combination member deformation due to force applying |
| GB201507124D0 (en) * | 2015-04-27 | 2015-06-10 | Thermoteknix Systems Ltd | Conveyer belt monitoring system and method |
| CN105405142A (en) * | 2015-11-12 | 2016-03-16 | 冯平 | Edge defect detection method and system for glass panel |
| CN105548201A (en) * | 2016-01-15 | 2016-05-04 | 浙江野马电池有限公司 | Battery welding cap visual-inspection method |
| CN108564602A (en) * | 2018-04-16 | 2018-09-21 | 北方工业大学 | Airplane detection method based on airport remote sensing image |
| CN108734716A (en) * | 2018-04-21 | 2018-11-02 | 卞家福 | A kind of fire complex environment image detecting method based on improvement Prewitt operators |
| CN109447946A (en) * | 2018-09-26 | 2019-03-08 | 中睿通信规划设计有限公司 | A kind of Overhead optical cable method for detecting abnormality |
| CN109934839A (en) * | 2019-03-08 | 2019-06-25 | 北京工业大学 | A kind of workpiece inspection method of view-based access control model |
| CN111829912A (en) * | 2019-04-22 | 2020-10-27 | 济南恒旭试验机技术有限公司 | Four-ball friction tester wear mark measuring method |
| CN110287752A (en) * | 2019-06-25 | 2019-09-27 | 北京慧眼智行科技有限公司 | A kind of dot matrix code detection method and device |
| CN110866486A (en) * | 2019-11-12 | 2020-03-06 | Oppo广东移动通信有限公司 | Subject detection method and apparatus, electronic device, and computer-readable storage medium |
| CN111260629A (en) * | 2020-01-16 | 2020-06-09 | 成都地铁运营有限公司 | Pantograph structure abnormity detection algorithm based on image processing |
| CN111754460A (en) * | 2020-05-25 | 2020-10-09 | 北京驿禄轨道交通工程有限公司 | Method, system and storage medium for automatically detecting gap of point switch |
| CN111833366A (en) * | 2020-06-03 | 2020-10-27 | 佛山科学技术学院 | Edge detection method based on Canny algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 光栅投影测量物体三维轮廓的条纹中心线相对偏移量的获取;黄燕群, 田爱玲;应用光学(06);全文 * |
| 非连续数字图像相关方法在裂纹重构中的应用;汤文治 等;《力学学报》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112541894A (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084236B (en) | Image correction method and device | |
| EP2783328B1 (en) | Text detection using multi-layer connected components with histograms | |
| CN108416355B (en) | Industrial field production data acquisition method based on machine vision | |
| CN110335233B (en) | Highway guardrail plate defect detection system and method based on image processing technology | |
| KR101035768B1 (en) | Method for setting lip region for lip reading and apparatus for the same | |
| CN114863492B (en) | Method and device for repairing low-quality fingerprint image | |
| CN105740872B (en) | Image feature extraction method and device | |
| CN108171098B (en) | Bar code detection method and equipment | |
| CN117635609B (en) | Visual inspection method for production quality of plastic products | |
| CN112634262A (en) | Writing quality evaluation method based on Internet | |
| CN115063430A (en) | Electric pipeline crack detection method based on image processing | |
| CN112419207A (en) | Image correction method, device and system | |
| CN110348307B (en) | Path edge identification method and system for crane metal structure climbing robot | |
| CN117710399A (en) | Crack contour extraction method in geological survey based on vision | |
| CN112541894B (en) | Product deformation detection method | |
| Wagdy et al. | Document image skew detection and correction method based on extreme points | |
| CN110378337B (en) | Visual input method and system for drawing identification information of metal cutting tool | |
| CN112597868A (en) | Test paper identification and correction method based on no positioning point | |
| CN110705568B (en) | Optimization method for image feature point extraction | |
| CN114067122B (en) | Two-stage binarization image processing method | |
| CN116309780A (en) | Water gauge water level identification method based on target detection | |
| CN112085683B (en) | Depth map credibility detection method in saliency detection | |
| CN107545563B (en) | Strip punching counting system and counting method | |
| CN111428534A (en) | Decryption identification method based on dot matrix steganographic information coding | |
| Kurnia et al. | Object detection on hindered condition by using chain code-based angle detection |
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 |