CN114387272B - Cable bridge defective product detection method based on image processing - Google Patents
Cable bridge defective product detection method based on image processing Download PDFInfo
- Publication number
- CN114387272B CN114387272B CN202210290710.7A CN202210290710A CN114387272B CN 114387272 B CN114387272 B CN 114387272B CN 202210290710 A CN202210290710 A CN 202210290710A CN 114387272 B CN114387272 B CN 114387272B
- Authority
- CN
- China
- Prior art keywords
- image
- local entropy
- local
- category
- cable bridge
- 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
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a method for detecting defective products of a cable bridge based on image processing, which comprises the following steps: acquiring spectrograms of an image to be measured and a standard image of the cable bridge, acquiring an abnormal image according to the two spectrograms, acquiring local entropy of each pixel point of the abnormal image, clustering the local entropies to obtain a plurality of local entropy categories, determining filling degree according to the local entropies corresponding to all pixel points in the convex hull connected domain corresponding to the local entropy categories and the local entropies, acquiring a straight line formed by the central points of two convex hull connected domains in each local entropy category, then obtaining the slope value of the straight line, obtaining the light spot degree of each local entropy category by the slope value, the light spot slope value obtained in advance and the filling degree, according to all the light spot degrees and the quality of the preset threshold value cable bridge, the method distinguishes the light spot area from the defect area in the gray level mutation area on the image to be detected, and therefore accurate detection of the quality of the cable bridge is achieved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a cable bridge defective product detection method based on image processing.
Background
After the cable bridge is produced, the surface of the cable bridge is required to be uniform, and if the defects of bubbles, scratches, overburning and the like occur, the current cable bridge is considered to be not in accordance with the product acceptance standard and belongs to defective goods.
When the cable bridge is installed, connecting holes are formed in the two sides of the cable bridge in order to facilitate the installation and connection of the cable bridge, and the cable bridge is connected through the connecting holes and the connecting pieces.
In a cable bridge production line, after a galvanization treatment is completed on a cable bridge, a spectrum analysis is utilized to detect the uniformity degree of an image of the cable bridge, although the uniformity change of the surface of a product can be detected, light beams emitted by a light source on the production line can irradiate the surface of the cable bridge through a connecting hole, so that a light spot area appears on the surface of the cable bridge, the light spot area belongs to a gray level mutation area, and because the surface defect of the product is also represented as the gray level mutation area on the image of the cable bridge, the defect area and the light spot area in the gray level mutation area can not be distinguished when the quality detection of the cable bridge is performed, the quality detection of the cable bridge is mistakenly detected, and the accuracy of the quality detection is further reduced.
Therefore, a cable tray defect detecting method based on image processing is needed.
Disclosure of Invention
The invention provides a cable bridge defective product detection method based on image processing, and aims to solve the existing problems.
The invention discloses a method for detecting defective products of a cable bridge based on image processing, which adopts the following technical scheme: the method comprises the following steps:
acquiring spectrograms of an image to be detected and a standard image of the cable bridge, and acquiring an abnormal image according to the spectrograms of the image to be detected and the standard image;
obtaining the local entropy of each pixel point according to the abnormal image, and clustering continuous pixel points in the abnormal image according to the local entropy to obtain a plurality of local entropy categories;
acquiring a convex hull connected domain of each local entropy category, and determining the filling degree corresponding to each local entropy category according to the local entropy corresponding to all pixel points in the convex hull connected domain;
acquiring a distance value between every two convex hull connected domains, clustering equal distance values in all the distance values to obtain a plurality of distance value categories, acquiring a straight line formed by the central points of the convex hull connected domains of two local entropy categories in each distance value category, and acquiring a slope value of the straight line;
obtaining the light spot degree of each local entropy category according to the slope value, the light spot slope value between the light spots obtained in advance and the filling degree of the two local entropy categories corresponding to the distance value in each category of distance values;
and determining the quality of the cable bridge according to the light spot degree and a preset light spot degree threshold value.
Further, the step of obtaining the abnormal image according to the spectrogram of the image to be detected and the spectrogram of the standard image comprises:
the method comprises the steps of obtaining a difference image by subtracting corresponding spectral values in a spectrogram of an acquired image and a spectrogram of a standard image;
and performing inverse Fourier transform on the difference image to obtain an abnormal image.
Further, the step of obtaining the local entropy of each pixel point according to the abnormal image comprises:
setting the size of a local window selected by local entropy in an abnormal image;
acquiring a window image of each pixel point in the abnormal image by taking a local window as a window size;
and calculating the local entropy of each pixel point in the window image.
Further, the step of clustering continuous pixel points in the abnormal image according to the local entropy to obtain a plurality of local entropy categories comprises:
acquiring coordinates of each pixel point in the abnormal image;
and clustering the pixels with similar local entropies and continuous coordinates by adopting a dbscan clustering algorithm to obtain a plurality of local entropy categories.
Further, the step of determining the filling degree corresponding to each local entropy category according to the local entropies corresponding to all the pixel points in the convex hull connected domain comprises the following steps:
the filling degree was calculated according to the following formula (1):
wherein the content of the first and second substances,
representing the filling degree corresponding to the kth local entropy category;
representing the number of pixel points in the convex hull connected domain of the kth local entropy category;
and the local entropy of the jth pixel point in all pixel points in the connected domain of the convex hull of the kth local entropy category.
Further, the step of obtaining the distance value between every two convex hull connected domains includes:
acquiring coordinates of center points of all convex hull connected domains;
and obtaining the distance value of every two convex hull connected domains according to the coordinates of the central point.
Further, the step of obtaining the light spot degree of each local entropy category according to the slope value, the light spot slope value between the light spots obtained in advance and the filling degree of two types of local entropies corresponding to the distance value in each type of distance value comprises the following steps of;
the flare level is calculated according to the following formula (2):
wherein the content of the first and second substances,
the light spot degree of the local entropy category corresponding to the Nth distance value category is represented; f represents the number of distance values formed by the convex hull connected domain center points of the local entropy categories contained in the Nth category of distance values; f represents the traversal of F;
represents the slope formed by the central points of the convex hull connected domain of the local entropy category corresponding to the f-th distance value in the N-th distance value category,
representing spot slope values between spots;
indicating that a first center point corresponding to the f-th distance value in the N-th distance value category is formed
The degree of filling of the corresponding local entropy class,
indicating that the second center point corresponding to the f-th distance value in the N-th distance value category is formed
The degree of filling of the corresponding local entropy class.
Further, the step of determining the quality of the cable tray according to the light spot degree and a preset light spot degree threshold value comprises:
when the light spot degree of any one local entropy category is larger than a threshold value, determining that a gray level mutation area on the image to be detected is a defect area, namely that the cable bridge has defects and is an unqualified product;
when the light spot degrees of all the local entropy categories are smaller than the threshold value, determining that the gray level mutation area on the image to be detected is a light spot area, namely the area of the cable bridge is free of defects, and meanwhile, when other areas of the cable bridge are free of defects, the cable bridge is a qualified product.
The beneficial effects of the invention are: the invention relates to a cable bridge defective product detection method based on image processing, which comprises the steps of obtaining a spectrogram of an image to be detected, obtaining an abnormal image according to the spectrogram, obtaining local entropies of all pixel points of the abnormal image, clustering the local entropies to obtain a plurality of local entropy categories, determining filling degree according to the local entropies corresponding to all the pixel points in convex hull communication domains corresponding to the local entropy categories and the local entropy categories, obtaining a straight line formed by the central points of two convex hull communication domains in each local entropy category, then obtaining a slope value of the straight line, obtaining a light spot degree of each local entropy category according to the slope value, a pre-obtained light spot slope value and the filling degree, and distinguishing a light spot region from a defect region in a gray level mutation region on the image to be detected according to the light spot degree and the quality of a preset threshold cable bridge so as to detect the cable bridge which belongs to a real defect, and further improves the accuracy of detection.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart illustrating the general steps of an embodiment of a method for detecting defective cable trays based on image processing;
FIG. 2 is a spectrum diagram corresponding to a standard image of a cable tray;
FIG. 3 is a frequency spectrum diagram corresponding to an image to be detected with a light spot area of a cable bridge;
FIG. 4 is an anomaly image derived from FIGS. 3 and 2;
fig. 5 is a local entropy image corresponding to fig. 4.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a method for detecting defective products of a cable bridge based on image processing, which comprises the following steps:
s1, acquiring spectrograms of the image to be detected and the standard image of the cable bridge, and acquiring an abnormal image according to the spectrograms of the image to be detected and the standard image; specifically, S11, collecting an image to be detected in a groove at a connecting hole of the cable bridge, performing spectrum analysis on the standard image and the collected image to be detected, as shown in fig. 3, obtaining a spectrogram corresponding to the image to be detected and a spectrogram corresponding to the standard image, as shown in fig. 2, and subtracting corresponding spectral values in the spectrogram of the image to be detected and the spectrogram of the standard image to obtain a difference image; s12, as shown in fig. 4, the difference image is subjected to inverse fourier transform to obtain an abnormal image. The purpose of performing differential analysis by using Fourier transform is to directly use graphs for difference, which causes more noise, so the Fourier transform is selected for performing differential analysis, and the gray value change part is reserved.
S2, after the abnormal image is obtained, the more uneven the gray level distribution of the abnormal image is, the larger the entropy value of the uneven gray level distribution area of the abnormal image is, so that the uneven gray level distribution area in the abnormal image is found according to the entropy value, namely the local entropy of each pixel point is obtained according to the abnormal image, and continuous pixel points in the abnormal image are clustered according to the local entropy to obtain a plurality of local entropy categories; specifically, the step of obtaining the local entropy of each pixel point according to the abnormal image includes: s21, setting the size of the local window selected by the local entropy in the abnormal image; in this embodiment, the size of the local window is 25 × 25, S22, obtaining a window image in which each pixel in the abnormal image takes the local window as the window size, where S23 calculates the local entropy of each pixel in the window image, where the local entropy may be calculated by using a function entrypafilt in matlab, as shown in fig. 5, the local entropy image may be obtained by rounding the entropy value of the local entropy of each pixel in the window image, where S24 clusters the continuous pixels in the abnormal image according to the local entropy to obtain a plurality of local entropy categories includes: s241, obtaining coordinates of each pixel point in the abnormal image; and S242, clustering the pixels with similar local entropies and continuous coordinates by adopting a dbscan clustering algorithm to obtain a plurality of local entropy categories.
S3, because the light spots are light spot areas formed by blocks, as shown in FIG. 5, the smaller the sum of the local entropies in the light spot areas in the local entropy images is, the more uniform the description is, and the more dense the filling is, the convex hull connected domain of each local entropy category is obtained first, and the filling degree corresponding to each local entropy category is determined according to the local entropies corresponding to all the pixel points in the convex hull connected domain.
Specifically, the filling degree is calculated according to the following formula (1):
wherein, the first and the second end of the pipe are connected with each other,
representing the filling degree corresponding to the kth local entropy category;
the number of pixel points in the convex hull connected domain representing the kth local entropy category;
is the local entropy of the jth pixel point in all the pixel points in the convex hull connected domain of the kth local entropy category,
the smaller the intensity, the more uniform the intensity corresponding to the local entropy category, and the more likely it belongs to the flare.
S4, obtaining distance values between every two convex hull connected domains, clustering equal distance values in all the distance values to obtain a plurality of distance value categories, obtaining a straight line formed by the central points of the convex hull connected domains of two local entropy categories in each distance value category, and obtaining the slope value of the straight line, wherein the slope value is recorded as
(ii) a Specifically, the coordinates of the central point of all convex hull connected domains are obtained first, wherein the coordinates of the central point are recorded as:
(ii) a And obtaining the distance value of every two convex hull connected domains according to the coordinates of the central point.
And S5, acquiring the light spot degree of each local entropy category according to the slope value, the light spot slope value between the light spots acquired in advance and the filling degree of the two local entropy categories corresponding to the distance value in each category of distance values.
Specifically, as the distance between the light passing through the connecting holes is equal, the distance between the central points of the light spots is approximately equal when the light spot areas are formed, so that the slopes between the light spot areas are consistent and parallel to the edge of the cable bridge, and the light spot slope values between the light spots are recorded as the light spot slope values
。
The flare degree is calculated according to the following formula (2):
wherein the content of the first and second substances,
the light spot degree of the local entropy category corresponding to the Nth distance value category is represented; f represents the number of distance values formed by the convex hull connected domain center points of the local entropy categories contained in the Nth category of distance values; f represents the traversal of F;
represents the slope formed by the central points of the convex hull connected domain of the local entropy category corresponding to the f-th distance value in the N-th distance value category,
representing spot slope values between spots;
indicating that a first center point corresponding to the f-th distance value in the N-th distance value category is formed
The degree of filling of the corresponding local entropy class,
indicating that a second center point corresponding to the f-th distance value in the N-th distance value category is formed
Filling degree of corresponding local entropy category, wherein the facula degree
The lower the value of (d), the more likely it is that the pixel point of the convex hull connected component corresponding to the nth distance value class is a defect.
S6, determining the quality of the cable bridge according to the light spot degrees and a preset light spot degree threshold, specifically, when the light spot degree of any one local entropy category is greater than the threshold, determining that a gray level mutation area on the image to be detected is a defect area, namely the cable bridge has defects and is an unqualified product; when the light spot degrees of all the local entropy categories are smaller than the threshold value, determining that the gray level mutation area on the image to be detected is a light spot area, namely the area of the cable bridge is free of defects, and meanwhile, when other areas of the cable bridge are free of defects, the cable bridge is a qualified product.
In summary, the invention provides a method for detecting defective products of a cable bridge based on image processing, which includes obtaining a spectrogram of an image to be detected, obtaining an abnormal image according to the spectrogram, obtaining local entropies of pixels of the abnormal image, clustering the local entropies to obtain a plurality of local entropy categories, determining filling degrees according to the local entropies corresponding to all pixels in a convex hull connected domain corresponding to the local entropy categories and the local entropy categories, obtaining a straight line formed by central points of two convex hull connected domains in each local entropy category, then obtaining a slope value of the straight line, obtaining a light spot degree of each local entropy category according to the slope value, a pre-obtained light spot slope value and the filling degree, and distinguishing a light spot region from a defect region in a gray level mutation region on the image to be detected according to the light spot degree and the quality of a preset threshold cable bridge, thereby detecting the cable bridge belonging to a real defect, and further improves the accuracy of detection.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The method for detecting the defective products of the cable bridge based on image processing is characterized by comprising the following steps of:
acquiring spectrograms of an image to be detected and a standard image of the cable bridge, and acquiring an abnormal image according to the spectrograms of the image to be detected and the standard image;
obtaining the local entropy of each pixel point according to the abnormal image, and clustering continuous pixel points in the abnormal image according to the local entropy to obtain a plurality of local entropy categories;
acquiring a convex hull connected domain of each local entropy category, and determining the filling degree corresponding to each local entropy category according to the local entropy corresponding to all pixel points in the convex hull connected domain;
acquiring a distance value between every two convex hull connected domains, clustering equal distance values in all the distance values to obtain a plurality of distance value categories, acquiring a straight line formed by the central points of the convex hull connected domains of two local entropy categories in each distance value category, and acquiring a slope value of the straight line;
acquiring the light spot degree of each local entropy category according to the slope value, the pre-acquired light spot slope value between the light spots and the filling degree of the two local entropy categories corresponding to the distance value in each category of distance values;
and determining the quality of the cable bridge according to all the facula degrees and a preset threshold value of the facula degrees.
2. The method for detecting the defective products on the cable tray based on the image processing as claimed in claim 1, wherein the step of obtaining the abnormal image according to the spectrogram of the image to be detected and the spectrogram of the standard image comprises:
the method comprises the steps of obtaining a difference image by subtracting corresponding spectral values in a spectrogram of an acquired image and a spectrogram of a standard image;
and performing inverse Fourier transform on the difference image to obtain an abnormal image.
3. The method for detecting the defective products on the cable bridge based on the image processing as claimed in claim 1, wherein the step of obtaining the local entropy of each pixel point according to the abnormal image comprises:
setting the size of a local window selected by local entropy in an abnormal image;
acquiring a window image of each pixel point in the abnormal image by taking a local window as a window size;
and calculating the local entropy of each pixel point in the window image.
4. The method for detecting the cable bridge defect products based on the image processing as claimed in claim 1, wherein the step of clustering continuous pixel points in the abnormal images according to the local entropy to obtain a plurality of local entropy categories comprises:
acquiring coordinates of each pixel point in the abnormal image;
and clustering the pixels with similar local entropies and continuous coordinates by adopting a dbscan clustering algorithm to obtain a plurality of local entropy categories.
5. The method for detecting the defective products of the cable bridge based on the image processing as claimed in claim 1, wherein the step of determining the filling degree corresponding to each local entropy category according to the local entropies corresponding to all the pixel points in the convex hull connected domain comprises:
the filling degree was calculated according to the following formula (1):
wherein the content of the first and second substances,
representing the filling degree corresponding to the kth local entropy category;
representing the number of pixel points in the convex hull connected domain of the kth local entropy category;
and the local entropy of the jth pixel point in all pixel points in the convex hull connected domain of the kth local entropy category.
6. The method for detecting the defective cable tray based on the image processing as claimed in claim 1, wherein the step of obtaining the distance value between every two convex hull connected domains comprises:
acquiring coordinates of center points of all convex hull connected domains;
and obtaining the distance value of every two convex hull connected domains according to the coordinates of the central point.
7. The method for detecting the defective products on the cable tray based on the image processing as claimed in claim 1, wherein the step of obtaining the degree of the light spots of each local entropy category according to the slope value, the light spot slope values between the light spots obtained in advance, and the filling degree of the two types of local entropies corresponding to the distance values in each type of distance values comprises:
the flare degree is calculated according to the following formula (2):
wherein, the first and the second end of the pipe are connected with each other,
the light spot degree of the local entropy category corresponding to the Nth distance value category is represented; f represents the number of distance values formed by the convex hull connected domain center points of the local entropy categories contained in the Nth category of distance values; f represents the traversal of F;
represents the slope formed by the central points of the convex hull connected domain of the local entropy category corresponding to the f-th distance value in the N-th distance value category,
representing spot slope values between spots;
indicating that a first center point corresponding to the f-th distance value in the N-th distance value category is formed
The degree of filling of the corresponding local entropy class,
indicating that a second center point corresponding to the f-th distance value in the N-th distance value category is formed
The degree of filling of the corresponding local entropy class.
8. The image processing-based cable tray defect detection method of claim 1, wherein the step of determining the quality of the cable tray according to all the light spot degrees and the preset threshold of the light spot degrees comprises:
when the light spot degree of any one local entropy category is larger than a threshold value, determining that a gray level mutation area on the image to be detected is a defect area, namely that the cable bridge has defects and is an unqualified product;
when the light spot degrees of all the local entropy categories are smaller than the threshold value, determining that the gray level mutation area on the image to be detected is a light spot area, namely the area of the cable bridge is free of defects, and meanwhile, when other areas of the cable bridge are free of defects, the cable bridge is a qualified product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290710.7A CN114387272B (en) | 2022-03-23 | 2022-03-23 | Cable bridge defective product detection method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290710.7A CN114387272B (en) | 2022-03-23 | 2022-03-23 | Cable bridge defective product detection method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114387272A CN114387272A (en) | 2022-04-22 |
| CN114387272B true CN114387272B (en) | 2022-05-24 |
Family
ID=81206042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210290710.7A Active CN114387272B (en) | 2022-03-23 | 2022-03-23 | Cable bridge defective product detection method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387272B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115115616B (en) * | 2022-07-26 | 2022-11-18 | 南通浩盛汽车科技有限公司 | Defect detection method for automobile stamping part based on variable light source |
| CN115019077A (en) * | 2022-08-09 | 2022-09-06 | 江苏思伽循环科技有限公司 | Method for identifying and controlling shaking table separator in waste battery recycling process |
| CN115100202B (en) * | 2022-08-25 | 2022-11-11 | 聊城市宏伟电器有限公司 | Cable quality detection method based on image processing |
| CN115115864B (en) * | 2022-08-26 | 2022-11-15 | 济宁安泰矿山设备制造有限公司 | Dynamic balance testing method and system for pump precision rotor shaft |
| CN115272737B (en) * | 2022-09-30 | 2023-10-20 | 佛山顺德和煦胶业科技有限公司 | Rubber ring flow mark identification method |
| CN116597188B (en) * | 2023-07-17 | 2023-09-05 | 山东北国发展集团有限公司 | Vision-based solid waste resource utilization method and system |
| CN116823825B (en) * | 2023-08-29 | 2023-12-05 | 山东海德尼克液压科技有限公司 | Intelligent identification method for casting defects of valve fittings |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8879813B1 (en) * | 2013-10-22 | 2014-11-04 | Eyenuk, Inc. | Systems and methods for automated interest region detection in retinal images |
| CN106127776A (en) * | 2016-06-28 | 2016-11-16 | 北京工业大学 | Based on multiple features space-time context robot target identification and motion decision method |
| CN110443806A (en) * | 2019-04-30 | 2019-11-12 | 浙江大学 | A kind of transparent floating harmful influence image partition method of the water surface based on targets improvement processing |
| CN111308682A (en) * | 2019-11-18 | 2020-06-19 | 天津大学 | Super-resolution reconstruction method based on structured light illumination |
| CN113808138A (en) * | 2021-11-22 | 2021-12-17 | 山东鹰联光电科技股份有限公司 | Artificial intelligence-based wire and cable surface defect detection method |
-
2022
- 2022-03-23 CN CN202210290710.7A patent/CN114387272B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8879813B1 (en) * | 2013-10-22 | 2014-11-04 | Eyenuk, Inc. | Systems and methods for automated interest region detection in retinal images |
| CN106127776A (en) * | 2016-06-28 | 2016-11-16 | 北京工业大学 | Based on multiple features space-time context robot target identification and motion decision method |
| CN110443806A (en) * | 2019-04-30 | 2019-11-12 | 浙江大学 | A kind of transparent floating harmful influence image partition method of the water surface based on targets improvement processing |
| CN111308682A (en) * | 2019-11-18 | 2020-06-19 | 天津大学 | Super-resolution reconstruction method based on structured light illumination |
| CN113808138A (en) * | 2021-11-22 | 2021-12-17 | 山东鹰联光电科技股份有限公司 | Artificial intelligence-based wire and cable surface defect detection method |
Non-Patent Citations (2)
| Title |
|---|
| Carlo Baldassi等.《Local entropy as a measure for sampling solutions in Constraint Satisfaction Problems》.《arXiv》.2016, * |
| 蒋颖 等.《基于聚类与局部统计的水平集医学图像分割》.《计算机工程与设计》.2015,第37卷(第11期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114387272A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114387272B (en) | Cable bridge defective product detection method based on image processing | |
| CN107255641B (en) | A method of Machine Vision Detection is carried out for self-focusing lens surface defect | |
| CN116758061B (en) | Casting surface defect detection method based on computer vision | |
| CN116843678A (en) | Hard carbon electrode production quality detection method | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN110473194A (en) | Fruit surface defect detection method based on more image block Threshold Segmentation Algorithms | |
| JP2005277395A5 (en) | ||
| CN107301637A (en) | Nearly rectangle plane shape industrial products surface flaw detecting method | |
| CN103903008A (en) | Power transmission line fog level recognition method and system based on images | |
| CN116012346B (en) | Power transmission line monitoring method and system | |
| CN105869135A (en) | Tire defect detection method and device | |
| CN115861307B (en) | Fascia gun power supply driving plate welding fault detection method based on artificial intelligence | |
| CN115311284A (en) | Production quality detection method for glass fiber mat | |
| CN116363126A (en) | Welding quality detection method for data line USB plug | |
| CN114937035A (en) | Image processing-based power transformer silicon steel sheet quality detection method and system | |
| CN116758056B (en) | Electrical terminal production defect detection method | |
| CN107037053A (en) | Apparatus and method for detecting spot defect | |
| JP2004144685A (en) | Method and system for adjusting instrumental error for visual inspection device in semiconductor device manufacturing line | |
| JP2012159376A (en) | Surface defect detector and surface defect detection method | |
| CN116087208A (en) | Plastic product detecting system based on image recognition | |
| CN115222735B (en) | Metal mold quality detection method based on pockmark defects | |
| CN114937041B (en) | Method and system for detecting defects of copper bush of oil way of automobile engine | |
| CN109191439A (en) | A kind of target workpiece surface knife mark defect inspection method | |
| CN115115616A (en) | Defect detection method for automobile stamping part based on variable light source | |
| CN112669321B (en) | Sand blasting unevenness detection method based on feature extraction and algorithm classification |
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 |