CN114565556B - Method for identifying the state of plasma electrolytic oxidation reaction based on image processing - Google Patents
Method for identifying the state of plasma electrolytic oxidation reaction based on image processing Download PDFInfo
- Publication number
- CN114565556B CN114565556B CN202210042095.8A CN202210042095A CN114565556B CN 114565556 B CN114565556 B CN 114565556B CN 202210042095 A CN202210042095 A CN 202210042095A CN 114565556 B CN114565556 B CN 114565556B
- Authority
- CN
- China
- Prior art keywords
- spark
- image
- target
- electrolytic oxidation
- plasma electrolytic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007745 plasma electrolytic oxidation reaction Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 claims description 13
- 238000003491 array Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims 1
- 238000006243 chemical reaction Methods 0.000 abstract description 16
- 239000011159 matrix material Substances 0.000 description 6
- 229910052751 metal Inorganic materials 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 239000000919 ceramic Substances 0.000 description 3
- 239000003792 electrolyte Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010891 electric arc Methods 0.000 description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 1
- 238000002679 ablation Methods 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 229910052749 magnesium Inorganic materials 0.000 description 1
- 239000011777 magnesium Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 239000010936 titanium Substances 0.000 description 1
- 229910052719 titanium Inorganic materials 0.000 description 1
- -1 titanium metals Chemical class 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- 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
- G06T2207/30136—Metal
-
- 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
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Analytical Chemistry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
本发明公开了基于图像处理的等离子体电解氧化反应状态识别的方法，包括：获取待处理火花图像，并得到工件表面的面积S；对待处理火花图像进行灰度化；将灰度化后的待处理火花图像的火花、背景进行分割，得到目标火花图像；对目标火花图像进行形态学处理，得到互相分离的火花目标；提取目标火花图像中每个火花目标的边缘特征；采用连通域的方法对边缘特征进行连通，得到火花总数量，并除以工件表面的面积S获得单位面积的火花数量，根据单位面积的火花数量识别当前时刻的等离子体电解氧化反应状态。提高了识别等离子体电解氧化的反应状态的准确性，更利于精确调节反应过程。
The invention discloses a method for identifying the state of plasma electrolytic oxidation reaction based on image processing, comprising: obtaining a spark image to be processed and obtaining the area S of the workpiece surface; graying the spark image to be processed; segmenting the spark and background of the grayed spark image to be processed to obtain a target spark image; morphologically processing the target spark image to obtain mutually separated spark targets; extracting the edge features of each spark target in the target spark image; connecting the edge features using a connected domain method to obtain the total number of sparks, and dividing it by the area S of the workpiece surface to obtain the number of sparks per unit area, and identifying the plasma electrolytic oxidation reaction state at the current moment according to the number of sparks per unit area. The accuracy of identifying the reaction state of plasma electrolytic oxidation is improved, and it is more conducive to accurately adjusting the reaction process.
Description
Technical Field
The invention belongs to the technical field of image processing, and relates to a plasma electrolytic oxidation reaction state identification method based on image processing.
Background
The plasma electrolytic oxidation technology is applied to the surface treatment of aluminum, magnesium, titanium metals and alloys thereof. The principle is that under the condition of proper electrolyte and the action of pulse electric field, complex chemical, electrochemical and plasma spark discharge reactions are generated on the surface of the metal workpiece serving as the anode, and under the action of instantaneous high temperature and high pressure generated by discharge, a ceramic layer which takes matrix metal oxide as a main component and is assisted by electrolyte component grows on the surface of the metal workpiece, so that the metal workpiece has the advantages of stronger corrosion resistance, wear resistance, insulativity, environmental protection of the electrolyte and the like.
The plasma electrolytic oxidation reaction state is closely related to the ceramic layer growth process, and the microcosmic appearance and the protective performance of the finally grown ceramic layer are greatly influenced. The plasma electrolytic oxidation discharge reaction process mainly comprises 3 stages, wherein a large number of bubbles are generated on the surface of a workpiece subjected to the plasma discharge reaction at first, the metallic luster gradually disappears, and sparks are slightly flashed from scratch to the spot. This stage is the anodic oxidation stage. After a few minutes, a dense small spark appears on the surface of the material, which is the spark discharge phase. The spark then gradually evolves to a large sparse spark, which is the micro-arc discharge phase, where a large arc discharge also occurs if ablation occurs. The specific reaction state is related to the number of sparks, but as the discharge sparks are too small in scale and too dense in distribution, and the characteristics of the discharge sparks are not obvious enough, the change of the number of the tiny discharge sparks observed by naked eyes can only be divided into three stages, and the plasma electrolytic oxidation reaction state and the specific evolution process at a certain moment can not be accurately identified.
Disclosure of Invention
The invention aims to provide a plasma electrolytic oxidation reaction state identification method based on image processing, which solves the problem that the number of discharge sparks cannot be accurately obtained in the prior art.
The technical scheme adopted by the invention is that the method for identifying the plasma electrolytic oxidation reaction state based on image processing comprises the following steps:
step 1, acquiring a spark image to be processed, and obtaining the area S of the surface of a workpiece;
step2, graying the spark image to be processed;
step 3, dividing sparks and backgrounds of the grey-scale spark image to be processed to obtain a target spark image;
Step 4, performing morphological processing on the target spark image to obtain mutually separated spark targets;
Step 5, extracting edge characteristics of each spark target in the target spark image;
And 6, communicating the edge features by adopting a communicating domain method to obtain the total number of sparks, dividing the total number of sparks by the area S of the surface of the workpiece to obtain the number of sparks in unit area, and identifying the plasma electrolytic oxidation reaction state at the current moment according to the number of sparks in unit area.
The invention is also characterized in that:
The specific process of the step2 is that the color of the pixel point in the spark image to be processed is converted into gray scale by a weighted average method.
The specific process of the step 3 is that firstly, a gray value M of a spark image to be processed after graying is taken, a gray value T is arbitrarily selected to divide a gray histogram of the image into a front part A and a rear part B, the average value of the two parts A and B is MA and MB, the proportion of the pixel number of the part A to the total pixel number is marked as PA, the proportion of the pixel number of the part B to the total pixel number is marked as PB, the maximum inter-class variance is calculated and is used as a gray threshold T, and then the gray threshold T is used for dividing the image into a binary image, so that a target spark image is obtained.
The specific process of the step 4 is that the target spark image is firstly corroded and then expanded to obtain spark targets separated from each other.
The step 5 specifically comprises the following steps:
step 5.1, convolving the target spark image by using a Gaussian filter to obtain a filtered pixel point e;
Step 5.2, convolving a 3x3 window in the target spark image with a Sobel operator by using a pair of convolution arrays S x,Sy to obtain gradient values of the pixel point e in x and y directions as G X and G y respectively, and then calculating gradient strength G and gradient direction theta of the pixel point e;
step 5.3, performing non-maximum suppression on the gradient amplitude according to the gradient direction to obtain edge points;
and 5.4, processing the edge points by using the high and low thresholds to obtain the edge characteristics of each spark target.
The specific process of the step 5.3 is that the gradient direction is divided into E, NE, N, NW, W, SW, S, SE, wherein 0 represents 0-45 degrees, 1 represents 45-90 degrees, 2 represents-90-45 degrees, 3 represents-45-0 degrees, the gradient direction of a pixel point P is theta, gradient linear interpolation G P1 and G p2 of the pixel points P1 and P2 are obtained, the gradient intensity G of the current pixel is compared with a pixel G P1、Gp2 along the positive and negative gradient directions, the pixel point smaller than the pixel G P1、Gp2 is restrained, and the pixel point larger than the pixel G P1、Gp2 is taken as an edge point;
And 6, connecting eight connected areas, traversing the image statistics to obtain 1 spark point, expanding the eight neighborhood of the spark point to search the area, counting +1 when the searched area is not expanding, continuously searching the next new point, and repeating the operation until the whole image is searched to obtain the total number of sparks.
The method for identifying the plasma electrolytic oxidation reaction state based on the image processing has the advantages that the number of sparks in unit area generated on the surface of a sample at a certain moment is accurately detected through an image processing technology to identify the reaction state of the plasma electrolytic oxidation at the moment, the reaction process is further accurately controlled according to the evolution of the sparks, the accuracy of identifying the reaction state of the plasma electrolytic oxidation is improved, and the accurate adjustment of the reaction process is facilitated.
Drawings
FIG. 1 is a flow chart of a method of plasma electrolytic oxidation reaction state identification based on image processing in accordance with the present invention;
FIG. 2 is a spark image to be processed in the method of plasma electrolytic oxidation reaction state identification based on image processing of the present invention;
FIG. 3 is a target spark image in the method of plasma electrolytic oxidation reaction state identification based on image processing of the present invention;
FIG. 4 is a graph of mutually separated target sparks in a method of plasma electrolytic oxidation reaction state identification based on image processing in accordance with the present invention;
FIG. 5 is an edge feature of a spark in the method of plasma electrolytic oxidation reaction state identification based on image processing of the present invention;
Fig. 6 is a spark image in the method of plasma electrolytic oxidation reaction state recognition based on image processing of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The method for identifying the plasma electrolytic oxidation reaction state based on image processing, as shown in fig. 1, comprises the following steps:
step 1, photographing and imaging the surface of a workpiece by adopting high-resolution photographing equipment, as shown in fig. 2, to obtain a spark image to be processed and the area S of the surface of the workpiece;
step2, graying the spark image to be processed;
specifically, the color of a pixel point in a spark image to be processed is converted into gray scale by a weighted average method, and the conversion formula is as follows:
I(x,y)=0.3*I_R(x,y)+0.59*I_G(x,y)+0.11*I_B(x,y) (1);
In the above equation, 0.3,0.59,0.11 is the weighting coefficient adjusted by the human brightness sensing system. Converting an RGB color image into a gray scale image is accomplished by eliminating image hue and saturation information while preserving brightness.
Step 3, dividing the sparks and the background of the grey-scale spark image to be processed to obtain a target spark image, as shown in fig. 3;
Specifically, firstly, taking a gray value mean value M of a gray image to be processed, arbitrarily selecting a gray value T to divide a gray histogram of the image into a front part A and a rear part B, wherein the average value of the two parts A and B is MA and MB respectively, the proportion of the pixel number of the part A to the total pixel number is marked as PA, the proportion of the pixel number of the part B to the total pixel number is marked as PB, the maximum inter-class variance is calculated and is used as a gray threshold value T, and the maximum inter-class variance is defined as:
ICV=PAα*(MA-M)2+PBα*(MB-M)2 (2);
In the above equation, α is 0.8, and the threshold t=icv is 200.
The image is then segmented into binarized images with a gray threshold T:
T=T[x,y,p(x,y),f(x,y)] (3);
In the above formula, x, y represents the abscissa of the pixel, p (x, y) represents the local characteristic of the pixel, f (x, y) represents the gray value of the pixel, and the thresholded image is a binary image defined as:
The pixel indicated by 0 is the target spark and the target spark image is obtained.
Step 4, performing morphological processing on the target spark images to obtain mutually separated target spark images;
Specifically, in the plasma electrolytic oxidation process, the spark causes the problem of adhesion of the spark in the image due to arc mapping, and the accuracy of counting is affected. And performing corrosion operation on the target spark image, and then expanding to obtain spark targets separated from each other. The processing method plays roles of smoothing the target outline, breaking the narrow connecting part and removing the tiny bulges, so that each target spark is in a mutually separated state, the counting error is effectively reduced, and the subsequent processing is convenient, as shown in fig. 4.
Step 5, extracting edge characteristics of each spark target in the target spark image;
Step 5.1 in order to reduce as much as possible the effect of noise present in the spark image on the spark edge detection result, the noise must be filtered out to prevent false detection caused by the noise. To smooth the image, a gaussian filter is used to convolve the image to reduce the apparent noise effects on the edge detector. Specifically, a Gaussian filter is used for convolving the target spark image to obtain a filtered pixel point e;
In this embodiment, a gaussian filter kernel of (2k+1) x (2k+1) is used, and the equation is:
in the above formula, i and j are the row and column of the gaussian convolution kernel matrix, σ is the variance, k determines the dimension of the kernel matrix, and the gaussian convolution kernel with the dimension of 3x3 (k=1) is taken as:
let a 3x3 window in the target spark image be a, and the pixel point to be filtered be e, after gaussian filtering, the brightness value of the pixel point e is:
Where, is a convolution symbol, sum represents the sum of all elements in the matrix, h is the coefficient of the gaussian convolution kernel matrix, and a-i is the coefficient of window a.
Step 5.2, convolving a 3x3 window in the target spark image with a Sobel operator by using a pair of convolution arrays S x,Sy, where the convolution array S x,Sy is:
In the above formula, S x represents a Sobel operator in the x direction for detecting an edge in the y direction, and S y represents a Sobel operator in the y direction for detecting an edge in the x direction;
The gradient values of the pixel point e in the x and y directions obtained after convolution are G X and G y respectively:
In the above formula, the symbols are convolution symbols, and sum represents the sum of all elements in the matrix;
then calculating the gradient strength G and gradient direction theta of the pixel point e;
step 5.3, performing non-maximum suppression on the gradient amplitude according to the gradient direction to obtain edge points;
Specifically, the gradient direction is divided into E, NE, N, NW, W, SW, S, SE, wherein 0 represents 0-45 degrees, 1 represents 45-90 degrees, 2 represents-90-45 degrees, 3 represents-45-0 degrees, the gradient direction of the pixel point P is theta, gradient linear interpolation G P1 and G p2 of the pixel points P1 and P2 are obtained,
tanθ=Gy/Gx (14);
GP1=(1-tan(θ))*E+tan(θ)*NE (15);
GP2=(1-tan(θ))*W+tan(θ)*SW (16);
Comparing the gradient intensity G of the current pixel with the pixel G P1、Gp2 along the positive and negative gradient directions, suppressing the pixel point smaller than the pixel G P1、Gp2, and taking the pixel point larger than the pixel G P1、Gp2 as an edge point;
And 5.4, processing the edge points by using the high and low thresholds to obtain the edge characteristics of each spark target. Specifically, the edge pixels are filtered with weak gradient intensity, and the edge pixels with high gradient intensity are reserved to solve the spurious response, wherein the high-low threshold ratio of 2:1 is taken to obtain the edge characteristic of each spark target, as shown in fig. 5.
And 6, communicating the edge features by adopting a communicating domain method to obtain the total number of sparks, dividing the total number of sparks by the area S of the surface of the workpiece to obtain the number of sparks in unit area, and identifying the plasma electrolytic oxidation reaction state at the current moment according to the number of sparks in unit area, so that the evolution state of the plasma electrolytic oxidation is accurately known, and a basis is provided for further accurate control of the reaction process.
Specifically, the values after the binarization process are only 0 and 1, and the spark edge clearly appears. The pixel denoted by 0 represents the spark edge to be counted, and the adjacent pixel denoted by 0 assumes a connected state. Connecting the eight connected areas of the pixel represented by 0, namely, the upper, lower, left, right, upper left, upper right, lower left and lower right, traversing the image statistics to obtain 1 spark point, expanding the eight neighborhood of the spark point to search the area, when the searched area is not expanding, indicating that the area is searched completely, counting +1, continuously searching for the next new point, repeating the operation until the whole image is searched, and obtaining the total number of sparks as shown in fig. 6.
According to the method for identifying the plasma electrolytic oxidation reaction state based on image processing, the number of sparks in unit area generated on the surface of the sample at a certain moment is accurately detected through an image processing technology, so that the reaction state of the plasma electrolytic oxidation at the moment is identified, the reaction process is further accurately controlled according to the evolution of the sparks, the accuracy of identifying the reaction state of the plasma electrolytic oxidation is improved, and the accurate adjustment of the reaction process is facilitated.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210042095.8A CN114565556B (en) | 2022-01-14 | 2022-01-14 | Method for identifying the state of plasma electrolytic oxidation reaction based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210042095.8A CN114565556B (en) | 2022-01-14 | 2022-01-14 | Method for identifying the state of plasma electrolytic oxidation reaction based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114565556A CN114565556A (en) | 2022-05-31 |
| CN114565556B true CN114565556B (en) | 2025-03-14 |
Family
ID=81711929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210042095.8A Active CN114565556B (en) | 2022-01-14 | 2022-01-14 | Method for identifying the state of plasma electrolytic oxidation reaction based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114565556B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958139B (en) * | 2023-09-20 | 2023-11-21 | 深圳市盘古环保科技有限公司 | Advanced oxidation intelligent monitoring method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114529548A (en) * | 2022-04-24 | 2022-05-24 | 南通重矿金属新材料有限公司 | Mechanical part stress corrosion detection method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636824B (en) * | 2018-12-20 | 2022-10-11 | 巢湖学院 | Multi-target counting method based on image recognition technology |
| CN111415363B (en) * | 2020-04-20 | 2023-04-18 | 电子科技大学中山学院 | Image edge identification method |
| CN113516091B (en) * | 2021-07-27 | 2024-03-29 | 福建工程学院 | A method for identifying electric spark images in substations |
-
2022
- 2022-01-14 CN CN202210042095.8A patent/CN114565556B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114529548A (en) * | 2022-04-24 | 2022-05-24 | 南通重矿金属新材料有限公司 | Mechanical part stress corrosion detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114565556A (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116721106B (en) | Profile flaw visual detection method based on image processing | |
| CN114399522B (en) | An edge detection method based on Canny operator with high and low thresholds | |
| WO2022205525A1 (en) | Binocular vision-based autonomous underwater vehicle recycling guidance false light source removal method | |
| CN109242853B (en) | An intelligent detection method for PCB defects based on image processing | |
| CN107808383B (en) | Rapid detection method for SAR image target under strong sea clutter | |
| CN111598897B (en) | Infrared image segmentation method based on Otsu and improved Bernsen | |
| CN102426649A (en) | Simple high-accuracy steel seal digital automatic identification method | |
| Er-Sen et al. | An adaptive edge-detection method based on the canny operator | |
| CN110717872A (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
| CN115060754B (en) | Stainless steel product surface quality detection method | |
| CN111738256A (en) | Composite CT image segmentation method based on improved watershed algorithm | |
| CN109472788B (en) | A method for detecting flaws on the surface of aircraft rivets | |
| CN104268872A (en) | Consistency-based edge detection method | |
| US20170309017A1 (en) | Device and method for finding cell nucleus of target cell from cell image | |
| CN106096491B (en) | An automated method for identifying microaneurysms in fundus color photographic images | |
| CN111145216B (en) | A Tracking Method of Video Image Target | |
| CN110687122A (en) | Method and system for detecting surface cracks of ceramic tile | |
| CN114565556B (en) | Method for identifying the state of plasma electrolytic oxidation reaction based on image processing | |
| CN105225244A (en) | Based on the noise detection method that minimum local mean square deviation calculates | |
| CN111369570A (en) | Multi-target detection tracking method for video image | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| CN111429461A (en) | Novel segmentation method for overlapped exfoliated epithelial cells | |
| CN112634222A (en) | SAR image ship target detection method | |
| CN113781413B (en) | Electrolytic capacitor positioning method based on Hough gradient method | |
| CN115409778A (en) | A Threshold Segmentation Method for Images of Infrared Small Targets with Background Suppression |
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 |