CN112785547A - Electrode contact surface damage identification method and system - Google Patents
Electrode contact surface damage identification method and system Download PDFInfo
- Publication number
- CN112785547A CN112785547A CN202011253909.XA CN202011253909A CN112785547A CN 112785547 A CN112785547 A CN 112785547A CN 202011253909 A CN202011253909 A CN 202011253909A CN 112785547 A CN112785547 A CN 112785547A
- Authority
- CN
- China
- Prior art keywords
- damage
- damaged
- image
- area
- original image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004891 communication Methods 0.000 claims abstract description 24
- 238000003708 edge detection Methods 0.000 claims abstract description 18
- 230000000877 morphologic effect Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000015654 memory Effects 0.000 description 14
- 238000012545 processing Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 8
- 235000013399 edible fruits Nutrition 0.000 description 7
- 238000003709 image segmentation Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000010339 dilation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003902 lesion Effects 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an electrode contact surface damage identification method and system, comprising the following steps: collecting an original image of the surface of the electrode contact; dividing the contact surface into a plurality of damaged portions based on the original image; selecting a damage part, carrying out edge detection based on a damage image of the damage part, and marking a detected damage edge; dividing a damaged area on the surface of the contact along the marked damaged edge, and representing the divided damaged area and other areas of the image by using a binary image; performing morphological operation on the divided damage area; performing expansion operation on the damaged area to obtain a closed damaged communication area; repeating the steps until the damage communication areas of all the damaged parts are obtained, and marking all the damage communication areas to finish the identification. The method can quickly and accurately extract the damaged area of the surface of the contact, and combines an MATLAB tool box with a GUI graphical user interface, so that the treatment process of the surface damage of the contact is more visual, and the method has good interactivity and practicability.
Description
Technical Field
The invention relates to an electrode contact surface damage identification method and system, which are applied to a high-voltage vacuum arc extinguish chamber and belong to the field of arc extinguish chamber research and development design.
Background
The surface state of the vacuum contact switch and the size of a metal molten pool are important bases for distinguishing the damage degree of the contact. The servicing and maintenance of the switching contacts has long been generally carried out manually. The overhauling method is easily influenced by factors such as subjective identification capability and emotion of people, deviation is large, a large amount of labor force is needed, working efficiency is low, and some safety problems are hidden sometimes. With the rapid development of computer technology, the application of machine vision technology in the field of vacuum arc-extinguishing chambers is more and more common. The machine vision technology has the characteristics of high speed, multiple functions and high efficiency. Taking the automatic detection of the appearance characteristics of the fruits based on MATLAB as an example, the method can finish the grading of the integrity, the shape, the size, the damage and the defects of the fruit stalks, the fruit faces, the damage and the defects of the fruit faces and the like at one time, can finish a plurality of tasks which are hard to be performed by other detection methods, can measure quantitative indexes such as the sizes of the fruits and the specific numerical values of the damage areas of the fruit faces, and can classify the fruits according to the numerical values.
Disclosure of Invention
The invention aims to provide an electrode contact surface damage identification method and system, which are used for solving the problems of low labor and material consumption efficiency in judging the damage degree of a switch contact.
In order to achieve the above object, the scheme of the invention comprises:
the invention discloses a method for identifying surface damage of an electrode contact, which comprises the following steps:
1) collecting an image of the surface of the electrode contact to obtain an original image;
2) dividing the contact surface into a plurality of damaged portions based on the original image;
3) selecting a damage part, carrying out edge detection on the basis of a damage image of the damage part, and marking a detected damage edge to obtain an edge marking image;
4) dividing a damaged area on the surface of the contact along the marked damaged edge, and representing the divided damaged area and other areas of the image by using a binary image;
5) performing morphological operation on the divided damaged area to eliminate other areas of the image in the damaged area; performing expansion operation on the damaged area to obtain a closed damaged communication area;
6) and repeating the steps 3) to 5) to obtain the damage communication areas of all the damaged parts, and marking all the damage communication areas to finish identification.
According to the method, machine vision is utilized, after a contact surface image is obtained, the edge of an arc-drawing burnt damage part on the original flat and smooth contact surface can be effectively identified and marked through an edge detection algorithm, then a damage area in the image is divided based on the identified damage edge, the damage area is displayed through a binary image, then the damage area is filled through morphological operation, finally the damage area is completely covered (the identification boundary exceeds the edge of the damage area) through expansion operation, the adjacent damage areas are communicated to form a damage communication area, and the completely connected damage communication area is marked and identified. The method realizes the uniform and standard rapid and accurate identification of the surface damage area of the contact, and the identification result is visual and easy to read.
Further, displaying the original image in step 1); displaying the edge mark image in step 3); displaying the binary image of the segmented damage area in the step 4); and 5) displaying the damaged area after morphological operation and displaying a damaged communication area after expansion operation.
Each step of processing of the image for realizing damage identification in the computer is displayed in real time, so that an operator can monitor the processing process conveniently, the deviation caused by the interference of the image in the processing process can be intervened in time, and the accuracy of damage identification is improved; meanwhile, when a large deviation exists in the recognition result, the step of image processing in which the deviation occurs can be timely and accurately known.
Further, in step 2), before dividing the surface of the contact into a plurality of damaged portions, the original image is further preprocessed, where the preprocessing includes: eliminating random noise in the original image by adopting median filtering, and displaying the processed original image; and (5) increasing the contrast of the original image by histogram equalization, and displaying the processed original image.
Random noise is eliminated through preprocessed 5 multiplied by 5 median filtering, and image contrast is enhanced through histogram equalization so as to highlight a damaged area, which is beneficial to next recognition and increases recognition accuracy.
Further, in step 3), after one of the incompletely identified damaged parts is selected, the original image is rotated and the damaged part is enlarged, and a damaged image of the damaged part is obtained and displayed.
Grouping the contact surface images, regarding the damage areas close to each other in distance as a group (a damage part), amplifying the corresponding group, and identifying the damage areas in the group by group, wherein the identification difficulty of each group is reduced, and the identification accuracy is further improved; meanwhile, the images of each group are amplified during identification of each group, and accuracy of edge detection and damage identification is facilitated.
Further, in step 3), edge detection is performed by using a Canny operator of MATLAB.
The invention discloses an electrode contact surface damage identification system, which comprises a display, a camera and a processor for controlling and connecting the camera and the display, wherein the processor executes instructions for realizing the following method:
1) collecting an image of the surface of the electrode contact to obtain an original image;
2) dividing the contact surface into a plurality of damaged portions based on the original image;
3) selecting a damage part, carrying out edge detection on the basis of a damage image of the damage part, and marking a detected damage edge to obtain an edge marking image;
4) dividing a damaged area on the surface of the contact along the marked damaged edge, and representing the divided damaged area and other areas of the image by using a binary image;
5) performing morphological operation on the divided damaged area to eliminate other areas of the image in the damaged area; performing expansion operation on the damaged area to obtain a closed damaged communication area;
6) and (5) repeating the steps 3) to 5) to obtain the damage communication areas of each damaged part, marking all the damage communication areas and displaying the marked damage communication areas on a display to finish recognition.
Further, displaying the original image in step 1); displaying the edge mark image in step 3); displaying the binary image of the segmented damage area in the step 4); and 5) displaying the damaged area after morphological operation and displaying a damaged communication area after expansion operation.
Further, in step 2), before dividing the surface of the contact into a plurality of damaged portions, the original image is further preprocessed, where the preprocessing includes: eliminating random noise in the original image by adopting median filtering, and displaying the processed original image; and (5) increasing the contrast of the original image by histogram equalization, and displaying the processed original image.
Further, in step 3), after one of the incompletely identified damaged parts is selected, the original image is rotated and the damaged part is enlarged, and a damaged image of the damaged part is obtained and displayed.
Further, in step 3), edge detection is performed by using a Canny operator of MATLAB.
Drawings
FIG. 1 is a flow chart of the present invention for identifying surface damage to an electrode contact;
FIG. 2 is a schematic diagram of a human-computer interaction interface of the electrode contact surface damage recognition system of the present invention;
FIG. 3 is a schematic diagram of an original image obtained by the method for identifying damage to the surface of an electrode contact according to the present invention;
FIG. 4 is a schematic diagram illustrating the preprocessing of an original image by the method for identifying damage to the surface of an electrode contact according to the present invention;
FIG. 5 is a schematic diagram illustrating edge detection of a damaged portion by the method for identifying damage to a surface of an electrode contact according to the present invention;
FIG. 6 is a schematic diagram of morphological operations performed by the method for identifying damage to the surface of an electrode contact according to the present invention;
FIG. 7 is a schematic diagram illustrating the marking of damaged communication areas by the method for identifying damage to the surface of an electrode contact according to the present invention;
fig. 8 is a schematic diagram of the electrode contact surface damage identification system of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The method comprises the following steps:
as shown in fig. 2 and fig. 3, the schematic diagram of the human-computer interaction interface of the electrode contact surface damage recognition system of the present invention includes two parts, namely, an image processing display area 1 and a key control area 2, where the key control area 2 is divided into an original image operation area 21, an image preprocessing operation area 22 and a damage extraction operation area 23. Through the function keys of the key control area 2, the process from reading the collected original image of the surface of the electrode contact to the image preprocessing process and then to the process of extracting the damage of the surface of the contact can be realized. Firstly, acquiring surface image information of a vacuum switch contact by using a CCD (charge coupled device) camera, and transmitting the image information to a computer memory; and reading the acquired original image of the surface of the electrode contact from the memory through the image reading key, wherein the read original image can be displayed in the left image processing display area 1. According to the image quality or the requirement, the tool keys in the image preprocessing operation area 22 can be utilized to preprocess the image so as to improve the image quality and facilitate the subsequent identification of the damaged area. Then, the image recognition process is performed on the preprocessed image through keys in the damage extraction operation area 23, and the preparation work of damage recognition is completed through edge detection, image segmentation and morphological operation in sequence. And finally, identifying and marking the damaged area through the damaged marking key to finish the acquisition and storage of the damaged position.
In the process from the original image to the image preprocessing and then to the damage extraction, the image of the surface of the electrode contact is always displayed in the image processing display area 1, and the change of the image processing in each step can be visually reflected on the image. For the operator to observe and refer. For example, a piece of reflected light on the surface of the contact in the original image forms a white spot after the histogram is enhanced, and is marked in the edge detection, and there is a high possibility that the white spot is erroneously recognized as a damaged area, and at this time, the operator can intervene in time to manually cut off the image with the reflected light through other tools in the image preprocessing operation region 22, such as a rotation and cutting key.
The method for identifying the surface damage of the electrode contact is specifically shown in figure 1, acquires a vacuum contact surface image through a CCD camera, performs pretreatment and edge detection on the image to determine the damage position, and marks the damage area of the contact surface after morphological operation, and comprises the following steps:
s1, image acquisition: the acquisition module adopts an infrared LED light source, the illumination mode is foreground illumination, and the reflection and shadow are eliminated by matching with a camera box; an area array CCD camera GS3-U3-14S5M-C is selected for image acquisition; an FA1602A lens and an infrared filter of a C-type interface with a focal length of 16mm are selected to be used together with the camera; transmitting the collected image information to a computer;
s2, image preprocessing step, as shown in FIG. 4: firstly, selecting 5-by-5 median filtering to process random noise; then, carrying out image enhancement processing on the image, and increasing the image resolution by using a histogram equalization method to highlight the damaged area; finally, according to the spatial distribution condition, dividing the damage positions with close distances into one group, dividing one or more groups of damage positions (each group of damage is a damage part) on the whole contact surface image, and then identifying the damage in each group one by one. Firstly, selecting a group of damage, rotating the images, segmenting the group of images by using an image cutting function, then amplifying the group of images, and displaying the amplified images of the group of damage (the damaged images of the damaged part) in an image processing display area 1, wherein the group of the amplified images of the damage are materials for subsequent edge detection;
s3, an edge analysis step, as shown in FIG. 5: carrying out damage edge detection on the preprocessed damage image of the contact surface by using a Canny edge detection operator of MATLAB, and preliminarily determining the defect position;
S4-S5. Damage identification step, as shown in FIG. 6: firstly, carrying out image segmentation on a preprocessed image according to a detected damaged edge to obtain a damaged area after the image segmentation, displaying the damaged area by using a binary image, wherein the damaged area can be displayed in a dark color, other areas can be displayed in a light color, and meanwhile, the damaged area can be displayed in the light color through an image reverse key, and other areas can be displayed in the dark color; then, performing morphological operation on the image to eliminate color points or color blocks of a non-damaged area in the damaged area, and then performing dilation operation (dilation operation also belongs to one of morphological operations, so that the dilation operation can be understood as performing two morphological operations) to completely and completely cover the corresponding damaged part in the damaged area, and finally obtaining a closed and completely covered image of the damaged connected area;
and S6, finally, marking the damage connected region of the image as shown in figure 7. Consecutive lesion contiguous areas, or contiguous lesion contiguous areas, are identified as the same lesion and numbered.
The invention relates to a user interface design of an electrode contact surface damage recognition system, which comprises the following steps: the MATLAB tool box is combined with a GUI graphical user interface, and processing operation on the contact surface image is designed into an interface form through different button forms. The interface form can well observe the implementation process of the contact surface image preprocessing, and can carry out visual processing on the contact image segmentation, morphological operation and damage identification processes more clearly, so that the whole system has good interactivity and practicability, and the image processing result is more visual.
The embodiment of the system is as follows:
the embodiment provides an electrode contact surface damage identification system, as shown in fig. 8, which includes a memory, a processor and an internal bus, wherein the processor and the memory are communicated with each other through the internal bus.
The processor can be a microprocessor MCU, a programmable logic device FPGA and other processing devices.
The memory can be various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as a hard disk, a floppy disk, a magnetic tape, a core memory, a bubble memory, a usb disk, etc.; various types of memory that store information optically, such as CDs, DVDs, etc., are used. Of course, there are other types of memory, such as quantum memory, graphene memory, and the like.
The processor can call the logic instructions in the memory and write or read the original picture data into the memory at the same time so as to realize the electrode contact surface damage identification method. The method is described in detail in the method embodiment, and is not described herein again.
Claims (10)
1. A method for identifying surface damage of an electrode contact is characterized by comprising the following steps:
1) collecting an image of the surface of the electrode contact to obtain an original image;
2) dividing the contact surface into a plurality of damaged portions based on the original image;
3) selecting a damage part, carrying out edge detection on the basis of a damage image of the damage part, and marking a detected damage edge to obtain an edge marking image;
4) dividing a damaged area on the surface of the contact along the marked damaged edge, and representing the divided damaged area and other areas of the image by using a binary image;
5) performing morphological operation on the divided damaged area to eliminate other areas of the image in the damaged area; performing expansion operation on the damaged area to obtain a closed damaged communication area;
6) and repeating the steps 3) to 5) to obtain the damage communication areas of all the damaged parts, and marking all the damage communication areas to finish identification.
2. The method for identifying surface damage of an electrode contact according to claim 1, wherein an original image is displayed in step 1); displaying the edge mark image in step 3); displaying the binary image of the segmented damage area in the step 4); and 5) displaying the damaged area after morphological operation and displaying a damaged communication area after expansion operation.
3. The method for identifying damage to the surface of an electrode contact according to claim 1 or 2, wherein in step 2), the original image is further preprocessed before the contact surface is divided into a plurality of damaged portions, and the preprocessing includes: eliminating random noise in the original image by adopting median filtering, and displaying the processed original image; and (5) increasing the contrast of the original image by histogram equalization, and displaying the processed original image.
4. The method for identifying damage to a surface of an electrode contact as claimed in claim 3, wherein in step 3), after selecting one of the incompletely identified damaged portions, the original image is rotated and the damaged portion is enlarged to obtain and display a damaged image of the damaged portion.
5. The method for identifying surface damage to an electrode contact according to claim 1, wherein in step 3), edge detection is performed using the Canny operator of MATLAB.
6. An electrode contact surface damage identification system is characterized by comprising a display, a camera and a processor for controlling connection between the camera and the display, wherein the processor executes instructions for realizing the following method:
1) collecting an image of the surface of the electrode contact to obtain an original image;
2) dividing the contact surface into a plurality of damaged portions based on the original image;
3) selecting a damage part, carrying out edge detection on the basis of a damage image of the damage part, and marking a detected damage edge to obtain an edge marking image;
4) dividing a damaged area on the surface of the contact along the marked damaged edge, and representing the divided damaged area and other areas of the image by using a binary image;
5) performing morphological operation on the divided damaged area to eliminate other areas of the image in the damaged area; performing expansion operation on the damaged area to obtain a closed damaged communication area;
6) and (5) repeating the steps 3) to 5) to obtain the damage communication areas of each damaged part, marking all the damage communication areas and displaying the marked damage communication areas on a display to finish recognition.
7. The electrode contact surface damage identification system of claim 6, wherein an original image is displayed in step 1); displaying the edge mark image in step 3); displaying the binary image of the segmented damage area in the step 4); and 5) displaying the damaged area after morphological operation and displaying a damaged communication area after expansion operation.
8. The electrode contact surface damage identification system of claim 6 or 7, wherein in step 2), the raw image is further preprocessed before dividing the contact surface into the plurality of damaged portions, the preprocessing comprising: eliminating random noise in the original image by adopting median filtering, and displaying the processed original image; and (5) increasing the contrast of the original image by histogram equalization, and displaying the processed original image.
9. The electrode contact surface damage identification system of claim 8, wherein in step 3), after selecting an unfinished identified damaged portion, the original image is rotated and the damaged portion is enlarged to obtain and display a damaged image of the damaged portion.
10. The electrode contact surface damage identification system of claim 6, wherein in step 3), edge detection is performed using the Canny operator of MATLAB.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011253909.XA CN112785547A (en) | 2020-11-11 | 2020-11-11 | Electrode contact surface damage identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011253909.XA CN112785547A (en) | 2020-11-11 | 2020-11-11 | Electrode contact surface damage identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112785547A true CN112785547A (en) | 2021-05-11 |
Family
ID=75750516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011253909.XA Pending CN112785547A (en) | 2020-11-11 | 2020-11-11 | Electrode contact surface damage identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112785547A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178367A (en) * | 2007-09-21 | 2008-05-14 | 天津大学 | Ceramic working surface damnification detecting system |
| CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| CN110930405A (en) * | 2020-01-19 | 2020-03-27 | 南京理工大学 | Cutter damage detection method based on image area division |
-
2020
- 2020-11-11 CN CN202011253909.XA patent/CN112785547A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178367A (en) * | 2007-09-21 | 2008-05-14 | 天津大学 | Ceramic working surface damnification detecting system |
| CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| CN110930405A (en) * | 2020-01-19 | 2020-03-27 | 南京理工大学 | Cutter damage detection method based on image area division |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022062812A1 (en) | Screen defect detection method, apparatus, and electronic device | |
| CN108562589B (en) | Method for detecting surface defects of magnetic circuit material | |
| CN109822398B (en) | Numerical control machine tool broken cutter detection system and method based on deep learning | |
| CN111275679B (en) | Image-based solar cell defect detection system and method | |
| JP5706860B2 (en) | Method for measuring the appearance quality of white rice and brown rice | |
| CN107038446B (en) | Night double-fruit overlapping tomato identification method based on overlapping edge detection under active illumination | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN111582294A (en) | Method for constructing convolutional neural network model for surface defect detection and application thereof | |
| CN113298776B (en) | Method for detecting appearance defects of metal closed water pump impeller | |
| CN113674226A (en) | Tea leaf picking machine tea leaf bud tip detection method based on deep learning | |
| CN106097368A (en) | A kind of recognition methods in veneer crack | |
| CN113781486A (en) | IC card image defect detection method | |
| CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
| CN111122590A (en) | Ceramic surface defect detection device and detection method | |
| CN108020554A (en) | A kind of steel strip surface defect recognition detection method | |
| CN110544262A (en) | cervical cell image segmentation method based on machine vision | |
| CN110288616B (en) | Method for segmenting hard exudation in fundus image based on fractal and RPCA | |
| CN107356232B (en) | Image processing method for visual inspection system | |
| CN106900601A (en) | A kind of fast accurate identification prawn image shrimp head method of the point with shrimp tail point | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| CN112785547A (en) | Electrode contact surface damage identification method and system | |
| CN111707672A (en) | Method for detecting surface defects of wind power rotary supporting piece | |
| CN110987957A (en) | Intelligent defect removing method based on machine vision and laser processing | |
| CN117036259A (en) | Metal plate surface defect detection method based on deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210511 |