CN112651936A - Steel plate surface defect image segmentation method and system based on image local entropy - Google Patents

Steel plate surface defect image segmentation method and system based on image local entropy Download PDF

Info

Publication number
CN112651936A
CN112651936A CN202011530627.XA CN202011530627A CN112651936A CN 112651936 A CN112651936 A CN 112651936A CN 202011530627 A CN202011530627 A CN 202011530627A CN 112651936 A CN112651936 A CN 112651936A
Authority
CN
China
Prior art keywords
image
defect
steel plate
local
histogram
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
Application number
CN202011530627.XA
Other languages
Chinese (zh)
Other versions
CN112651936B (en
Inventor
陈文建
刘轮
李武森
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN202011530627.XA priority Critical patent/CN112651936B/en
Publication of CN112651936A publication Critical patent/CN112651936A/en
Application granted granted Critical
Publication of CN112651936B publication Critical patent/CN112651936B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
    • G06V10/507—Summing image-intensity values; Histogram projection analysis
    • 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)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention discloses a steel plate surface defect image segmentation method and a steel plate surface defect image segmentation system based on image local entropy, wherein the method comprises the following steps: converting the steel plate image into a gray image; carrying out illumination unevenness correction on the steel plate image; obtaining a global histogram of the corrected gray level image, and calculating back projection of each pixel according to the global histogram to obtain a back projection image of the original image; obtaining a local histogram of the corrected gray level image, and calculating a one-dimensional information entropy of the local histogram to obtain an information entropy image of the original image; calculating the probability of each pixel belonging to the defect according to the information entropy image and the reverse projection image to obtain a defect probability map; and performing threshold segmentation on the defect probability map and performing morphological processing to obtain a final segmentation image, and separating the defect from the background. The method is simple to operate, has robustness to noise, and can accurately segment defects.

Description

Steel plate surface defect image segmentation method and system based on image local entropy
Technical Field
The invention belongs to the field of digital image processing, and particularly relates to a steel plate surface defect image segmentation method and system based on image local entropy.
Background
The steel has important significance for modern society and is widely applied to the fields of bridges, ships, armors, automobiles and the like. China is a large population country, social development has great demand on steel, and simultaneously China is a large steel production country, and the national steel yield is 9.9 hundred million tons in 2019. During the rolling process of the steel plate, due to the reasons of continuous casting of steel billets, rolling equipment, rolling process and the like, defects are formed on the surface of the rolled plate, so that the plate is not attractive and the service life and the performance of the plate are influenced. The traditional detection method uses manual visual inspection, is greatly influenced by human factors, and has low detection efficiency. With the development and progress of technology, machine vision is applied to industrial production. The algorithm is the core of the machine vision surface detection technology, so that a proper, universal and modularized algorithm framework is developed, the defect characteristics are effectively extracted, the defects are accurately classified and identified, the defect identification rate is improved, the error identification rate is reduced, and the method is the development direction of the surface detection technology.
Commonly used image segmentation methods mainly include threshold-based methods, edge-based methods, region-based methods, and the like. The image segmentation method based on the threshold value is to divide the image into a plurality of sub-regions according to the difference between the set threshold value and the pixel value of the image. Wherein, the size of the threshold value directly determines the image segmentation effect. The methods commonly used include the Maximum inter-class variance (OTSU) method and the Maximum Entropy (Maximum Entropy) method. The image segmentation method based on the threshold value does not consider the spatial position information of the target in the image, and particularly, when the difference between the pixel values of the target and the background in the image is not large or the background is complex, the phenomenon of over-segmentation or under-segmentation can occur. The region-based image segmentation method is to form a plurality of uniform sub-regions by aggregating pixels with the same attribute together according to a similarity criterion set in advance. The commonly used methods include a region growing method, a region splitting and merging method, a watershed method and the like. The image segmentation method based on the region needs to artificially set similarity criteria, and the calculation complexity is high. The edge-based image segmentation method is to find the contour or boundary of an object in an image through a differential operator by using the characteristics of discontinuity or catastrophe of gray scale, color or texture in the image. Common differential operators include Canny operator, Sobel operator, Laplacian operator, LoG operator, DoG operator, and the like. Edge-based image segmentation methods are extremely sensitive to noise, and it is difficult to find the exact contour of an object when the boundary between the object and the background in the image is not sharp.
Disclosure of Invention
The invention aims to provide a steel plate surface defect image segmentation method and system based on image local entropy aiming at the problems in the prior art.
The technical solution for realizing the purpose of the invention is as follows: a steel plate surface defect image segmentation method based on image local entropy comprises the following steps:
step 1, acquiring a steel plate image, and converting the steel plate image into a gray scale image;
step 2, carrying out illumination unevenness correction on the gray level image obtained in the step 1;
step 3, solving a global histogram from the image in the step 2;
step 4, carrying out back projection on each pixel of the image in the step 2 according to the histogram in the step 3, and carrying out normalization;
step 5, obtaining a local histogram of an S-S area for each pixel of the image in the step 2;
step 6, solving information entropy according to the local histogram in the step 5, and normalizing;
step 7, calculating the probability of each pixel belonging to the defect according to the back projection graph in the step 4 and the information entropy graph in the step 6 to obtain a defect probability graph;
and 8, performing threshold segmentation on the defect probability map obtained in the step 7, and performing image morphological processing to obtain a final defect segmentation map.
Further, the illumination unevenness correction formula in step 2 is:
Figure BDA0002851921660000022
wherein gamma is normalNumber, g (x, y) is a grayscale image, g(x,y)*GaussianThe image illumination component is obtained by convolution of the gray image and a Gaussian filter kernel, and f (x, y) is the image after illumination unevenness correction.
Further, the back projection formula in step 4 is:
B(x,y)＝1-H(I(x,y))
in the formula, B (x, y) is the back projection corresponding to the image in step 2, I (x, y) is the gray scale value at (x, y) in the image in step 2, and H (I (x, y)) is the histogram obtained in step 3.
Further, in step 6, the information entropy solving formula is as follows:
Figure BDA0002851921660000021
in the formula, E (x, y) is an information entropy diagram corresponding to the image in the step 2, H1(I) For the local histogram obtained in step 5, I is the gray value at (x, y) in the image in step 2.
Further, the defect probability calculation formula in step 7 is:
P(x,y)＝[B(x,y)]α·[E(x,y)]β
in the formula, P (x, y) is a defect probability map, and α and β are constant parameters.
A steel plate surface defect image segmentation system based on image local entropy, the system comprising:
the image conversion module is used for acquiring a steel plate image and converting the steel plate image into a gray scale image;
the correction module is used for carrying out illumination unevenness correction on the gray level image;
the global histogram acquisition module is used for solving a global histogram for the corrected gray level image;
the back projection module is used for carrying out back projection on each pixel of the corrected gray level image according to the global histogram and carrying out normalization;
the local histogram acquisition module is used for solving a local histogram of an S & ltS & gt region for each pixel of the corrected gray level image;
the information entropy calculating module is used for calculating the information entropy according to the local histogram and carrying out normalization;
the defect probability map acquisition module is used for calculating the probability of each pixel belonging to the defect according to the reverse projection map and the information entropy map to obtain a defect probability map;
and the threshold segmentation module is used for performing threshold segmentation on the defect probability map and performing image morphological processing to obtain a final defect segmentation map.
Compared with the prior art, the invention has the following remarkable advantages: 1) the image is subjected to illumination unevenness correction, so that the method can be suitable for wider scenes; 2) the histogram-based algorithm has stronger robustness to noise; 3) and the reverse projection graph and the local information entropy graph are fused, so that the defects can be segmented more accurately.
The present invention is described in further detail below with reference to the attached drawing figures.
Drawings
FIG. 1 is a flow chart of the steel plate surface defect image segmentation based on the image local entropy.
Fig. 2 is a comparison graph of segmentation effect in an embodiment, in which (a) is an original image of three steel plate defects, (b) is an inverse projection image of a gray scale image, (c) is a local information entropy image of the gray scale image, (d) is a defect probability image of the gray scale image, and (e) is a segmentation effect graph.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
With reference to fig. 1, the present invention provides a steel plate surface defect image segmentation method based on image local entropy, which includes the following steps:
step 1, acquiring a steel plate image, and converting the steel plate image into a gray scale image;
step 2, carrying out illumination unevenness correction on the gray-scale image obtained in the step 1, wherein the illumination unevenness correction formula is as follows:
Figure BDA0002851921660000041
wherein γ is a constant, g (x, y) is a gray image, g(x,y)*GaussianThe image illumination component is obtained by convolution of the gray image and a Gaussian filter kernel, and f (x, y) is the image after illumination unevenness correction.
Step 3, obtaining a global histogram from the image obtained in the step 2, specifically: dividing the gray scale interval of 0-255 into N sections, calculating the number of pixels in each section and dividing the number of pixels by the total number of pixels.
Step 4, carrying out back projection on each pixel of the image in the step 2 according to the histogram in the step 3, and carrying out normalization; wherein, the back projection formula is:
B(x,y)＝1-H(I(x,y))
in the formula, B (x, y) is the back projection corresponding to the image in step 2, I (x, y) is the gray scale value at (x, y) in the image in step 2, and H (I (x, y)) is the histogram obtained in step 3.
And 5, obtaining a local histogram of the S-S area for each pixel of the image in the step 2.
And 6, solving the information entropy according to the local histogram in the step 5, and normalizing, wherein the information entropy solving formula is as follows:
Figure BDA0002851921660000042
in the formula, E (x, y) is an information entropy diagram corresponding to the image in the step 2, H1(I) For the local histogram obtained in step 5, I is the gray value at (x, y) in the image in step 2.
And 7, calculating the probability of each pixel belonging to the defect according to the back projection graph in the step 4 and the information entropy graph in the step 6 to obtain a defect probability graph, wherein the defect probability calculation formula is as follows:
P(x,y)＝[B(x,y)]α·[E(x,y)]β
in the formula, P (x, y) is a defect probability map, and α and β are constant parameters.
Here, α ═ β ═ 2 is preferred.
And 8, performing threshold segmentation on the defect probability map obtained in the step 7, and performing image morphological processing to obtain a final defect segmentation map.
A steel plate surface defect image segmentation system based on image local entropy, the system comprising:
the image conversion module is used for acquiring a steel plate image and converting the steel plate image into a gray scale image;
the correction module is used for carrying out illumination unevenness correction on the gray level image;
the global histogram acquisition module is used for solving a global histogram for the corrected gray level image;
the back projection module is used for carrying out back projection on each pixel of the corrected gray level image according to the global histogram and carrying out normalization;
the local histogram acquisition module is used for solving a local histogram of an S & ltS & gt region for each pixel of the corrected gray level image;
the information entropy calculating module is used for calculating the information entropy according to the local histogram and carrying out normalization;
the defect probability map acquisition module is used for calculating the probability of each pixel belonging to the defect according to the reverse projection map and the information entropy map to obtain a defect probability map;
and the threshold segmentation module is used for performing threshold segmentation on the defect probability map and performing image morphological processing to obtain a final defect segmentation map.
For specific limitations of the steel plate surface defect image segmentation system based on the image local entropy, reference may be made to the above limitations on the steel plate surface defect image segmentation method based on the image local entropy, which are not described herein again. The modules in the steel plate surface defect image segmentation system based on the image local entropy can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The following is a more detailed description with reference to examples.
Examples
In this embodiment, the method for segmenting the surface defect image of the steel plate based on the local entropy of the image by processing three groups of steel plate images includes the following steps:
1. acquiring a steel plate image and converting the steel plate image into a gray image as shown in fig. 2 (a);
2. carrying out illumination unevenness correction on the gray level image;
3. the back projection image of the calculated image is shown in FIG. 2 (b);
4. the local information entropy image of the computed image is shown in fig. 2 (c);
5. calculating the probability image of the defect as shown in fig. 2 (d);
6. the threshold segmentation and morphological processing of the defect probability map are shown in fig. 2 (e).
The method disclosed by the invention is simple to operate, has stronger robustness on noise, has higher positioning precision on defects, and has a good application prospect.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (7)

1. A steel plate surface defect image segmentation method based on image local entropy is characterized by comprising the following steps:
step 1, acquiring a steel plate image, and converting the steel plate image into a gray scale image;
step 2, carrying out illumination unevenness correction on the gray level image obtained in the step 1;
step 3, solving a global histogram from the image in the step 2;
step 4, carrying out back projection on each pixel of the image in the step 2 according to the histogram in the step 3, and carrying out normalization;
step 5, obtaining a local histogram of an S-S area for each pixel of the image in the step 2;
step 6, solving information entropy according to the local histogram in the step 5, and normalizing;
step 7, calculating the probability of each pixel belonging to the defect according to the back projection graph in the step 4 and the information entropy graph in the step 6 to obtain a defect probability graph;
and 8, performing threshold segmentation on the defect probability map obtained in the step 7, and performing image morphological processing to obtain a final defect segmentation map.
2. The method for segmenting the image of the surface defect of the steel plate based on the local entropy of the image as claimed in claim 1, wherein the illumination unevenness correction formula in the step 2 is as follows:
Figure FDA0002851921650000011
wherein γ is a constant, g (x, y) is a gray image, g(x,y)*GaussianThe image illumination component is obtained by convolution of the gray image and a Gaussian filter kernel, and f (x, y) is the image after illumination unevenness correction.
3. The method for segmenting the surface defect image of the steel plate based on the local entropy of the image as claimed in claim 2, wherein the back projection formula in the step 4 is as follows:
B(x,y)＝1-H(I(x,y))
in the formula, B (x, y) is the back projection corresponding to the image in step 2, I (x, y) is the gray scale value at (x, y) in the image in step 2, and H (I (x, y)) is the histogram obtained in step 3.
4. The method for segmenting the steel plate surface defect image based on the image local entropy as claimed in claim 3, wherein the information entropy in the step 6 is obtained by the following formula:
Figure FDA0002851921650000012
in the formula, E (x, y) is an information entropy diagram corresponding to the image in the step 2, H1(I) For the local histogram obtained in step 5, I is the gray value at (x, y) in the image in step 2.
5. The method for segmenting the steel plate surface defect image based on the image local entropy as claimed in claim 4, wherein the defect probability calculation formula in the step 7 is as follows:
P(x,y)＝[B(x,y)]α·[E(x,y)]β
in the formula, P (x, y) is a defect probability map, and α and β are constant parameters.
6. The method for segmenting the image of the surface defect of the steel plate based on the local entropy of the image is characterized in that the alpha, beta, 2.
7. Steel plate surface defect image segmentation system based on image local entropy for realizing the method of any one of claims 1 to 6, characterized in that the system comprises:
the image conversion module is used for acquiring a steel plate image and converting the steel plate image into a gray scale image;
the correction module is used for carrying out illumination unevenness correction on the gray level image;
the global histogram acquisition module is used for solving a global histogram for the corrected gray level image;
the back projection module is used for carrying out back projection on each pixel of the corrected gray level image according to the global histogram and carrying out normalization;
the local histogram acquisition module is used for solving a local histogram of an S & ltS & gt region for each pixel of the corrected gray level image;
the information entropy calculating module is used for calculating the information entropy according to the local histogram and carrying out normalization;
the defect probability map acquisition module is used for calculating the probability of each pixel belonging to the defect according to the reverse projection map and the information entropy map to obtain a defect probability map;
and the threshold segmentation module is used for performing threshold segmentation on the defect probability map and performing image morphological processing to obtain a final defect segmentation map.
CN202011530627.XA 2020-12-22 2020-12-22 Steel plate surface defect image segmentation method and system based on image local entropy Active CN112651936B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011530627.XA CN112651936B (en) 2020-12-22 2020-12-22 Steel plate surface defect image segmentation method and system based on image local entropy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011530627.XA CN112651936B (en) 2020-12-22 2020-12-22 Steel plate surface defect image segmentation method and system based on image local entropy

Publications (2)

Publication Number Publication Date
CN112651936A true CN112651936A (en) 2021-04-13
CN112651936B CN112651936B (en) 2023-06-13

Family

ID=75359158

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011530627.XA Active CN112651936B (en) 2020-12-22 2020-12-22 Steel plate surface defect image segmentation method and system based on image local entropy

Country Status (1)

Country Link
CN (1) CN112651936B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113129290A (en) * 2021-04-23 2021-07-16 攀钢集团攀枝花钢铁研究院有限公司 Spangle image recognition method, spangle image recognition device, spangle image recognition equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101706959A (en) * 2009-10-21 2010-05-12 苏州有色金属研究院有限公司 Method for extracting surface defects of metal sheets and strips on basis of two-dimensional information entropy
CN105719275A (en) * 2015-12-10 2016-06-29 中色科技股份有限公司 Parallel combination image defect segmentation method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101706959A (en) * 2009-10-21 2010-05-12 苏州有色金属研究院有限公司 Method for extracting surface defects of metal sheets and strips on basis of two-dimensional information entropy
CN105719275A (en) * 2015-12-10 2016-06-29 中色科技股份有限公司 Parallel combination image defect segmentation method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GAGAN KISHORE NAND等: "Defect Detection Of Steel Surface Using Entropy Segmentation", 《2014 ANNUAL IEEE INDIA CONFERENCE》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113129290A (en) * 2021-04-23 2021-07-16 攀钢集团攀枝花钢铁研究院有限公司 Spangle image recognition method, spangle image recognition device, spangle image recognition equipment and storage medium

Also Published As

Publication number Publication date
CN112651936B (en) 2023-06-13

Similar Documents

Publication Publication Date Title
CN113781402B (en) Method and device for detecting scratch defects on chip surface and computer equipment
US11443437B2 (en) Vibe-based three-dimensional sonar point cloud image segmentation method
CN106960208B (en) Method and system for automatically segmenting and identifying instrument liquid crystal number
CN106815583B (en) Method for positioning license plate of vehicle at night based on combination of MSER and SWT
CN111598897B (en) Infrared image segmentation method based on Otsu and improved Bernsen
CN110674812B (en) Civil license plate positioning and character segmentation method facing complex background
CN109781737B (en) Detection method and detection system for surface defects of hose
CN110648330B (en) Defect detection method for camera glass
CN114219773B (en) Pre-screening and calibrating method for bridge crack detection data set
CN111507971A (en) Tunnel surface defect detection method
CN111354047B (en) Computer vision-based camera module positioning method and system
CN109850518B (en) Real-time mining adhesive tape early warning tearing detection method based on infrared image
CN111476804A (en) Method, device and equipment for efficiently segmenting carrier roller image and storage medium
CN111738256A (en) Composite material CT image segmentation method based on improved watershed algorithm
CN112508913A (en) Cable section edge detection method based on image detection
Li et al. Automatic infrared ship target segmentation based on structure tensor and maximum histogram entropy
CN112651936B (en) Steel plate surface defect image segmentation method and system based on image local entropy
CN113971681A (en) Edge detection method for belt conveyor in complex environment
Fang et al. 1-D barcode localization in complex background
CN112184619A (en) Metal part surface defect detection method based on deep learning
CN114494165A (en) Clustering-based light bar extraction method and device
CN115187788A (en) Crop seed automatic counting method based on machine vision
CN111191534B (en) Road extraction method in fuzzy aviation image
CN110298799B (en) PCB image positioning correction method
CN112381088A (en) License plate recognition method and system for oil tank truck

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