CN114037657A - Lithium battery tab defect detection method combining region growth and annular correction - Google Patents

Lithium battery tab defect detection method combining region growth and annular correction Download PDF

Info

Publication number
CN114037657A
CN114037657A CN202111185362.9A CN202111185362A CN114037657A CN 114037657 A CN114037657 A CN 114037657A CN 202111185362 A CN202111185362 A CN 202111185362A CN 114037657 A CN114037657 A CN 114037657A
Authority
CN
China
Prior art keywords
lithium battery
tab
image
defects
defect
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
Application number
CN202111185362.9A
Other languages
Chinese (zh)
Inventor
毛晓
李林升
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.)
Shanghai Dianji University
Original Assignee
Shanghai Dianji University
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 Shanghai Dianji University filed Critical Shanghai Dianji University
Priority to CN202111185362.9A priority Critical patent/CN114037657A/en
Publication of CN114037657A publication Critical patent/CN114037657A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/187Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to a lithium battery tab defect detection method combining region growth and annular correction, which comprises the following steps of 1) obtaining a lithium battery image to be detected, and preprocessing the lithium battery image to be detected; 2) dividing the lug and the coating in the preprocessed lithium battery image to be detected to obtain a lug defect area and a coating area; 3) removing snow interference from the divided coating area; 4) detecting the outline information of a tab defect area, externally connecting a rectangle to perform outline positioning, and calculating tab defect key parameters; 5) on the basis of calculating the key parameters of the defects of the pole lugs, the key parameters of the defects of the pole lugs are corrected, and therefore accurate detection of the defects is achieved. Compared with the prior art, the invention has the advantages of high detection precision, high detection efficiency and the like.

Description

Lithium battery tab defect detection method combining region growth and annular correction
Technical Field
The invention relates to the technical field of machine vision automatic detection, in particular to a lithium battery tab defect detection method combining region growth and annular correction.
Background
The lithium ion battery has the advantages of low self-discharge, high energy density, no memory effect, environmental protection, long cycle service life and the like. However, the lithium battery tab is easily affected by the tab cutting machine in the production and processing process, so that various defects such as tab loss, tab wrinkles, tab splicing strips and the like can occur. At present, many lithium battery production plants have low defect detection efficiency and high labor intensity, and some tiny defects are easy to miss detection and the like.
The defect detection method based on machine vision is a non-contact and non-damage automatic detection method. When the machine vision technology is used for defect detection, the method mainly comprises the steps of image acquisition, image preprocessing, feature extraction, defect area key parameter calculation and the like. The image acquisition adopts an industrial camera to acquire a picture, the image preprocessing usually inhibits a background region and enhances a defect region, the commonly adopted methods comprise Gaussian filtering, mean filtering, median filtering and the like, and the feature extraction usually adopts a Sobel edge detection algorithm, an OTSU algorithm and a Canny edge detection algorithm. The defect region key parameter calculation is obtained by using an image gradient-based calculation method. However, the lithium battery tab defect detection research after cutting by the tab cutting machine is less at present, and a technology for detecting tab defect key parameters and positioning tab defects by using a machine vision technology does not exist.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a lithium battery tab defect detection method combining region growth and annular correction.
The purpose of the invention can be realized by the following technical scheme:
a lithium battery tab defect detection method combining region growth and annular correction comprises the following steps:
s1: and acquiring an image of the lithium battery to be detected, and preprocessing the image of the lithium battery to be detected. The pretreatment comprises the following steps: and processing the lithium battery image to be detected by utilizing a method of piecewise linear transformation and determining pixel nodes by combining a three-dimensional image. The concrete contents are as follows:
determining pixel nodes a and b of an original lithium battery image to be detected through the three-dimensional body and the front side of a lithium battery tab; acquiring the pixel value of the lithium battery image to be detected after piecewise linear transformation by utilizing a piecewise linear transformation formula, wherein the piecewise linear transformation formula is as follows:
Figure BDA0003298969010000021
in the formula, f (x, y) is the pixel value of an original lithium battery image to be detected, and g (x, y) is the image pixel value after piecewise linear transformation; a. b is the pixel node of the original lithium battery image to be detected, and c and d are the pixel nodes of the image after piecewise linear transformation.
S2: and segmenting the lug and the coating in the preprocessed lithium battery image to be detected to obtain a lug defect area and a coating area.
Further, the preprocessed lithium battery image to be detected is divided into the electrode lugs and the coating by using a region growing algorithm.
S3: and removing snow interference on the divided coating area.
Furthermore, the snow interference on the divided coating area is removed by adopting an opening operator in the morphological processing.
S4: detecting the outline information of the tab defect area, positioning the outline by externally connecting a rectangle, and calculating the key parameters of the tab defect.
Further, Canny edge detection algorithm is adopted to detect the outline information of the defect. The expression of the contour information of the defect detected by adopting the Canny edge detection algorithm is as follows:
Figure BDA0003298969010000022
in the formula (f)x(i, j) is the difference in the horizontal direction, fy(i, j) is the difference in the vertical direction, M (i, j) is the gradient magnitude of Canny edge detection, θ (i, j) is the gradient direction of Canny edge detection, and (i, j) isAll point coordinates in the entire image.
Further, the image gradient is adopted to calculate the relative outline area and the relative circumference of the lug defect. The computational expression of relative profile area versus relative perimeter is:
Figure BDA0003298969010000023
Figure BDA0003298969010000031
in the formula, S is the area of the tab defect, A is the tab defect area, and (i, j) is the coordinate in the defect area; c is the perimeter of the tab defect, and P is the defect edge detected by a Canny operator.
S5: on the basis of calculating the key parameters of the defects of the pole lugs, the key parameters of the defects of the pole lugs are corrected, and therefore accurate detection of the defects is achieved.
And further, correcting key parameters of the defects of the tabs by adopting an annular correction method.
Compared with the prior art, the lithium battery tab defect detection method combining the growth of the area and the annular correction at least has the following beneficial effects:
1) in the image preprocessing process, the method for detecting the defects of the lithium battery tabs adopts a piecewise linear transformation method to realize the maximum enhancement of the defect area and the inhibition of the background area;
2) the tab and the coating can be quickly segmented by adopting a region growing algorithm, and the coating becomes a background so that the tab can be highlighted;
3) the perimeter and area parameters of the tab are corrected by adopting an annular correction method, and the detection precision of the defective area of the lithium battery tab can be improved by the annular correction method through the detection effect of a standard image;
4) the detection method can effectively detect various defects of the lithium battery tab, such as tab loss, tab wrinkle, tab splicing and the like, has high detection efficiency, can meet the production requirements of enterprises, and has important significance in realizing automatic detection of the defects of the lithium battery tab.
Drawings
Fig. 1 shows the types of defect detection of the lithium battery tab, wherein sub-diagram (a) shows the tab missing, sub-diagram (b) shows the tab folding, and sub-diagram (c) shows the tab connecting belt;
FIG. 2 is a flowchart of a defect detection algorithm;
fig. 3 is a sectional linear transformation of a lithium battery tab, wherein, sub-diagram (a) is a three-dimensional stereo diagram of the lithium battery tab, sub-diagram (b) is a front diagram of the lithium battery tab, and sub-diagram (c) is a sectional linear transformation result;
FIG. 4 is a region growing algorithm; wherein, the subgraph (a) is the growth result of a tab missing region, the subgraph (b) is the growth result of a tab folding region, and the subgraph (c) is the growth result of a tab connecting region;
fig. 5 is a comparison graph of a tab band treated by morphology, wherein, a subgraph (a) is a snowflake noise enhancement tab band diagram, and a subgraph (b) is a tab band diagram treated by morphology;
FIG. 6 is a Canny edge detection diagram;
fig. 7 is a diagram of the tab splicing detection effect;
FIG. 8(a) is a principle of correction of parameters S and C;
FIG. 8(b) is a diagram illustrating the correction principles of parameters TL, BR, W and H;
FIG. 9 is a comparison graph of standard defect detection, in which a sub-graph (a) is a graph of detection results without circular correction, and a sub-graph (b) is a graph of detection results with circular correction;
fig. 10 shows the result of the tab splicing detection with the ring correction;
fig. 11 is a diagram showing the detection effect of various tab defects, wherein sub-diagrams (a) and (b) are the tab missing detection results of different production lines in coating areas with different sizes, and sub-diagrams (c) and (d) are the tab wrinkle detection results, wherein the sub-diagram (c) has two tab wrinkle defects, and the sub-diagram (d) has one tab wrinkle defect; and subgraphs (e) and (f) are the detection results of the tab connection belt, wherein the subgraph (e) is the twisted tab connection belt, and the subgraph (f) is the flat tab connection belt.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
The invention relates to a lithium battery tab defect detection method combining region growth and annular correction, which comprises the following steps of:
step one, obtaining an image of a lithium battery to be detected, and preprocessing the image. Specifically, the pretreatment is as follows: the method for determining pixel nodes by utilizing piecewise linear transformation and combining a three-dimensional image realizes the unchanged coating area, the enhanced defect area and the suppressed background area of the image.
The background area of the lithium battery tab image interferes with the subsequent tab defect segmentation, so that the background area needs to be restrained. When the tab is wrinkled, a shadow with a low pixel value may exist, as shown in fig. 1, so that the defect area needs to be enhanced. The method for determining the pixel nodes by utilizing piecewise linear transformation and combining the three-dimensional image realizes the purposes of keeping the coating area of the image unchanged, enhancing the defect area and inhibiting the background area.
The formula of the piecewise linear transformation is shown in formula (1).
Figure BDA0003298969010000051
In the formula (1), f (x, y) is a pixel value of an original image, and g (x, y) is a pixel value of an image after piecewise linear transformation. a. b is the pixel node of the original image, and c and d are the pixel nodes of the image after the piecewise linear transformation. Pixel nodes a and b of the original image are determined by observing pixel value ranges of a background area, a defect area and a coating area of a three-dimensional and front side of the lithium battery tab, as shown in subgraphs (a) and (b) in fig. 3, and the result of the lithium battery tab strip-connected input image after the segmented linear transformation of the formula (1) is shown in the subgraph (c) in fig. 3, so that the defect area is obviously enhanced compared with the subgraph (c) in the lithium battery tab strip-connected graph 1.
And step two, rapidly dividing the tab and the coating by using a region growing algorithm, wherein the coating becomes a background, so that the tab can be highlighted.
Since a clear boundary line exists between the tab defect area and the coating area, the segmentation is carried out by adopting an area growing algorithm. The region growing means that adjacent pixels are gradually added from the seed point pixels according to a certain criterion, and when a certain condition is met, the region growing is terminated. The selected seed point is an image central point, the difference between the gray value of the seed point and the gray value of the surrounding 8 neighborhood growing points is less than 10, the seed point is judged to be a similar point, the similar point is used as the seed point of the next growing, and when no pixel point meeting the growing criterion exists, the growing is stopped. The region growing algorithm can rapidly divide the tab and the coating, and the coating becomes a background, so that the tab can be highlighted. The results of the segmentation by the region growing algorithm are shown in fig. 4.
Step three, because some points with high pixel values in the coating area are not removed, a plurality of snowflake noise interferences can occur. Therefore, the invention selects an opening operator in the morphological processing to remove snowflake interference.
A morphologically processed tab and strap pair is shown in fig. 5. The effect of the morphological opening operator after processing is shown in fig. 5(b), and it can be seen that the snowflake noise interference is removed.
And step four, detecting the outline information of the defect by adopting a Canny edge detection algorithm, externally connecting a rectangle to position the outline, and calculating key parameters such as the area, the perimeter and the like of the tab based on the image gradient. The data processed by the Canny edge detection algorithm in the step is data after morphological open operation, namely the sub-image (b) of the figure 5.
The Canny operator has strong noise resistance and accurate positioning. The gradient amplitude is calculated by adopting a 3 x 3 neighborhood, and a calculation formula of the gradient amplitude M (i, j) and the gradient direction theta (i, j) of Canny edge detection is shown as a formula (2).
Figure BDA0003298969010000061
The horizontal axis direction of the image is the horizontal direction, and the vertical axis direction of the image is the vertical and horizontal direction. In the formula (2), fx(i, j) is the difference in the horizontal direction, fy(i, j) is the difference in the vertical direction. The Canny edge detection results are shown in fig. 6. And comparing the tab pictures after morphological processing, and accurately detecting the edges of the tab pictures by using a Canny operator. The (i, j) in the formula (2) represents all the point coordinates of the entire image.
Most of defects of the lithium battery tab are polygons with irregular shapes, and the absolute area and the perimeter are difficult to calculate, so that the relative area and the relative perimeter can be calculated (in the image processing process, for the irregular shapes, the calculation of the area and the perimeter can be realized only through pixel point accumulation, and the numerical value is just the relative area and the relative perimeter). And calculating the outline area and the perimeter of the lug defect based on the image gradient, wherein the essence is the accumulation of pixels, the calculation unit is the pixels, and the mathematical expressions are respectively shown as (3) and (4).
Figure BDA0003298969010000062
Figure BDA0003298969010000063
In the formula (3), S represents the area of the defect, a represents the defective region, and (i, j) is the coordinate in the defective region. In the formula (4), C represents the perimeter of the defect, and P represents the edge of the defect detected by the Canny operator. The (i, j) in the formulas (3) and (4) represents only the coordinates within the defect region. In order to facilitate observation of the effect of the tab defect detection, a defect outline is drawn on an original image in a multilateral fitting mode, and meanwhile, a circumscribed rectangle of the defect outline is drawn to achieve positioning of the defect outline. The tab defect detection effect is shown in fig. 7.
And step five, on the basis of calculating the key parameters of the defects of the lugs, providing an annular correction method to correct the key parameters so as to realize accurate detection of the defects.
The lug defect area is integrally detected, the size of S and C is influenced by morphological processing and Canny edge detection in an algorithm, the line width of an external rectangle influences TL, BR, W, H and other related parameters of the lug defect area, the maximum width W and the maximum height H of the lug defect area, a combination TL of the minimum transverse axis value and the minimum longitudinal axis value of the lug defect area, a combination BR of the maximum transverse axis value and the maximum longitudinal axis value of the lug defect area, and the parameters TL and BR realize the positioning of the lug defect area. The detection precision can not meet the actual application requirement, and the relevant parameters need to be further corrected. The principle of the pole lug defect area parameters is shown in fig. 8(a) and 8(b), and the correction formula of the pole lug defect area parameters of the lithium battery is shown in formula (5).
Figure BDA0003298969010000071
In the formula (6), S ', C ', W ', H ', and (TL 'x,TL′y)、(BR′xBR′y) And respectively representing relevant parameters of the corrected tab defect area, wherein alpha represents the annular width, beta represents a random parameter, delta represents a fixed value, and epsilon represents the sum of the line width of the circumscribed rectangle and the annular width. The comparison of the standard defect detection of the invention is shown in fig. 9, which illustrates that the annular correction provided by the invention can improve the detection precision of the defective region of the lithium battery tab. The detection result of the lithium battery tab connecting belt through the annular correction algorithm is shown in fig. 10, and compared with fig. 7, the detection result shows that the key parameters of the lithium battery tab defect area are all corrected, so that the detection precision of the lithium battery tab defect area is relatively improved. In fig. 11, subgraphs (c) and (d) are tab fold detection results, the defect detection number of the subgraph (c) is 2, the defect detection number of the subgraph (d) is 1, and the algorithm can detect a plurality of defects at the same time. In FIG. 11, subgraphs (e) and (f) are the tab and strap detection junctionsAnd if the sub-graph (e) is a distorted tab connecting belt, and the sub-graph (f) is a flat tab connecting belt, the algorithm obtains good detection effect on the tab defects with different shapes.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and those skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A lithium battery tab defect detection method combining region growth and annular correction is characterized by comprising the following steps:
1) acquiring a lithium battery image to be detected, and preprocessing the lithium battery image to be detected;
2) dividing the lug and the coating in the preprocessed lithium battery image to be detected to obtain a lug defect area and a coating area;
3) removing snow interference from the divided coating area;
4) detecting the outline information of a tab defect area, externally connecting a rectangle to perform outline positioning, and calculating tab defect key parameters;
5) on the basis of calculating the key parameters of the defects of the pole lugs, the key parameters of the defects of the pole lugs are corrected, and therefore accurate detection of the defects is achieved.
2. The method for detecting defects of a lithium battery tab combining region growth and annular correction according to claim 1, wherein in the step 1), the pretreatment is: and processing the lithium battery image to be detected by utilizing a method of piecewise linear transformation and determining pixel nodes by combining a three-dimensional image.
3. The lithium battery tab defect detection method combining region growth and annular correction as claimed in claim 2, wherein the specific contents of processing the lithium battery image to be detected by using the piecewise linear transformation and the method of determining the pixel node by combining the three-dimensional image are as follows:
determining pixel nodes a and b of an original lithium battery image to be detected through the three-dimensional body and the front side of a lithium battery tab; acquiring the pixel value of the lithium battery image to be detected after piecewise linear transformation by utilizing a piecewise linear transformation formula, wherein the piecewise linear transformation formula is as follows:
Figure FDA0003298969000000011
in the formula, f (x, y) is the pixel value of an original lithium battery image to be detected, and g (x, y) is the image pixel value after piecewise linear transformation; a. b is the pixel node of the original lithium battery image to be detected, and c and d are the pixel nodes of the image after piecewise linear transformation.
4. The method for detecting the defects of the lithium battery tab combining the region growing and the annular correction as claimed in claim 1, wherein in the step 2), the tab and the coating in the pre-processed image of the lithium battery to be detected are segmented by using a region growing algorithm.
5. The method for detecting the defects of the lithium battery tab combining the region growth and the annular correction as claimed in claim 1, wherein in the step 3), the snow interference is removed from the segmented coating region by using an opening operator in the morphological treatment.
6. The method for detecting defects of a lithium battery tab combining region growth and annular correction according to claim 1, wherein in the step 4), contour information of the defects is detected by using a Canny edge detection algorithm.
7. The method for detecting the defects of the lithium battery tab combining the region growth with the annular correction as claimed in claim 6, wherein the expression of the contour information of the defects detected by adopting the Canny edge detection algorithm is as follows:
Figure FDA0003298969000000021
in the formula (f)x(i, j) is the difference in the horizontal direction, fy(i, j) is the difference in the vertical direction, M (i, j) is the gradient magnitude of Canny edge detection, θ (i, j) is the gradient direction of Canny edge detection, and (i, j) is the coordinates of all points in the entire image.
8. The method for detecting defects of a lithium battery tab combining zone growth and annular correction as claimed in claim 7, wherein in the step 4), the relative outline area and the relative circumference of the tab defect are calculated by using image gradient.
9. The method for detecting defects of a lithium battery tab combining region growth and annular correction as claimed in claim 8, wherein the computational expression of relative outline area and relative circumference is:
Figure FDA0003298969000000022
Figure FDA0003298969000000023
in the formula, S is the area of the tab defect, A is the tab defect area, and (i, j) is the coordinate in the defect area; c is the perimeter of the tab defect, and P is the defect edge detected by a Canny operator.
10. The method for detecting the defects of the lithium battery tab combining the region growing and the annular correction as claimed in claim 1, wherein in the step 5), the critical parameters of the tab defects are corrected by adopting an annular correction method.
CN202111185362.9A 2021-10-12 2021-10-12 Lithium battery tab defect detection method combining region growth and annular correction Pending CN114037657A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111185362.9A CN114037657A (en) 2021-10-12 2021-10-12 Lithium battery tab defect detection method combining region growth and annular correction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111185362.9A CN114037657A (en) 2021-10-12 2021-10-12 Lithium battery tab defect detection method combining region growth and annular correction

Publications (1)

Publication Number Publication Date
CN114037657A true CN114037657A (en) 2022-02-11

Family

ID=80134804

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111185362.9A Pending CN114037657A (en) 2021-10-12 2021-10-12 Lithium battery tab defect detection method combining region growth and annular correction

Country Status (1)

Country Link
CN (1) CN114037657A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116823924A (en) * 2023-08-24 2023-09-29 杭州百子尖科技股份有限公司 Determination method and device for defect area, electronic equipment and storage medium
CN116912188A (en) * 2023-07-06 2023-10-20 钛玛科(北京)工业科技有限公司 Method, device, equipment and storage medium for extracting boundary cap hole of lithium battery
CN117232425A (en) * 2023-11-14 2023-12-15 钛玛科(北京)工业科技有限公司 Method, device, equipment and medium for measuring cutting depth of anode material of lithium battery

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107730477A (en) * 2017-10-13 2018-02-23 西安科技大学 Substation equipment infrared intelligent monitoring system and monitoring image feature extracting method
CN112233133A (en) * 2020-10-29 2021-01-15 上海电力大学 Power plant high-temperature pipeline defect detection and segmentation method based on OTSU and region growing method
CN112669295A (en) * 2020-12-30 2021-04-16 上海电机学院 Lithium battery pole piece defect detection method based on secondary threshold segmentation theory
CN113160132A (en) * 2021-03-10 2021-07-23 上海应用技术大学 Detection processing method and system for weld defect image
WO2021169335A1 (en) * 2020-02-25 2021-09-02 华南理工大学 Visual online detection method for laser welding point of lithium battery tab

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107730477A (en) * 2017-10-13 2018-02-23 西安科技大学 Substation equipment infrared intelligent monitoring system and monitoring image feature extracting method
WO2021169335A1 (en) * 2020-02-25 2021-09-02 华南理工大学 Visual online detection method for laser welding point of lithium battery tab
CN112233133A (en) * 2020-10-29 2021-01-15 上海电力大学 Power plant high-temperature pipeline defect detection and segmentation method based on OTSU and region growing method
CN112669295A (en) * 2020-12-30 2021-04-16 上海电机学院 Lithium battery pole piece defect detection method based on secondary threshold segmentation theory
CN113160132A (en) * 2021-03-10 2021-07-23 上海应用技术大学 Detection processing method and system for weld defect image

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
宿丁;张启衡;谢盛华;: "一种强海杂波多目标分形分割算法", 计算机工程与应用, no. 16, 1 June 2006 (2006-06-01) *
许旻;牛照东;陈曾平;: "一种新的低信噪比红外舰船目标自动检测方法", 红外与激光工程, no. 2, 15 October 2007 (2007-10-15) *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116912188A (en) * 2023-07-06 2023-10-20 钛玛科(北京)工业科技有限公司 Method, device, equipment and storage medium for extracting boundary cap hole of lithium battery
CN116912188B (en) * 2023-07-06 2024-07-09 钛玛科(北京)工业科技有限公司 Method, device, equipment and storage medium for extracting boundary cap hole of lithium battery
CN116823924A (en) * 2023-08-24 2023-09-29 杭州百子尖科技股份有限公司 Determination method and device for defect area, electronic equipment and storage medium
CN116823924B (en) * 2023-08-24 2023-12-12 杭州百子尖科技股份有限公司 Determination method and device for defect area, electronic equipment and storage medium
CN117232425A (en) * 2023-11-14 2023-12-15 钛玛科(北京)工业科技有限公司 Method, device, equipment and medium for measuring cutting depth of anode material of lithium battery
CN117232425B (en) * 2023-11-14 2024-02-13 钛玛科(北京)工业科技有限公司 Method, device, equipment and medium for measuring cutting depth of anode material of lithium battery

Similar Documents

Publication Publication Date Title
CN114037657A (en) Lithium battery tab defect detection method combining region growth and annular correction
CN107808378B (en) Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features
CN108921176B (en) Pointer instrument positioning and identifying method based on machine vision
CN110992326B (en) QFN chip pin image rapid inclination correction method
CN107194919B (en) Mobile phone screen defect detection method based on regular texture background reconstruction
CN109727244B (en) Magnetic shoe surface crack detection method
Hao et al. Improved self-adaptive edge detection method based on Canny
CN110933926B (en) Automatic correction method for angle of suction nozzle element of chip mounter based on angular point detection
CN105913415A (en) Image sub-pixel edge extraction method having extensive adaptability
CN112884708A (en) Method for detecting burrs of circular injection molding piece
CN113034452A (en) Weldment contour detection method
CN107480662B (en) Mould image identification method and device
CN115908415B (en) Edge-based defect detection method, device, equipment and storage medium
CN105139391B (en) A kind of haze weather traffic image edge detection method
CN111582000B (en) Bar code positioning method, bar code positioning device and related equipment
CN107680086B (en) Method for detecting material contour defects with arc-shaped edges and linear edges
CN111667470A (en) Industrial pipeline flaw detection inner wall detection method based on digital image
CN111524156A (en) Overlapped citrus segmentation method based on distance transformation and angular point detection
CN111754538A (en) Threshold segmentation method for USB surface defect detection
CN112669295A (en) Lithium battery pole piece defect detection method based on secondary threshold segmentation theory
CN114612410A (en) Novel clothing detects device
CN112435272B (en) High-voltage transmission line connected domain removing method based on image contour analysis
CN108986160A (en) A kind of image laser center line extraction method containing specular light interference
CN113487563A (en) Photovoltaic module subfissure self-adaptive detection method based on EL image
CN116128873A (en) Bearing retainer detection method, device and medium based on image recognition

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