CN108053404B - Efficient positioning method for lithium battery coating boundary - Google Patents
Efficient positioning method for lithium battery coating boundary Download PDFInfo
- Publication number
- CN108053404B CN108053404B CN201810028750.8A CN201810028750A CN108053404B CN 108053404 B CN108053404 B CN 108053404B CN 201810028750 A CN201810028750 A CN 201810028750A CN 108053404 B CN108053404 B CN 108053404B
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- boundary
- coating
- projection
- 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
- 239000011248 coating agent Substances 0.000 title claims abstract description 46
- 238000000576 coating method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 32
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 21
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 29
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 6
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 abstract description 3
- 229910052782 aluminium Inorganic materials 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 239000011888 foil Substances 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 239000000463 material Substances 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 abstract 2
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 239000002002 slurry Substances 0.000 description 4
- 239000000758 substrate Substances 0.000 description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 229910001416 lithium ion Inorganic materials 0.000 description 3
- 239000010406 cathode material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000010008 shearing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005587 bubbling Effects 0.000 description 1
- 239000011162 core material Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009830 intercalation Methods 0.000 description 1
- 230000002687 intercalation Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000007921 spray Substances 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
- 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
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention discloses a high-efficiency positioning method for a lithium battery coating boundary, which utilizes image processing and a corresponding image boundary processing algorithm to achieve high-efficiency and high-precision positioning extraction of the coating boundary, wherein the image boundary extraction algorithm comprises the following steps: (1) performing direction boundary detection on an original coating image; (2) binarizing the edge image; (3) Traversing the whole image by adopting a longitudinal projection searching edge algorithm to obtain a non-zero pixel position; (4) Removing interference noise in the projection value by adopting a neighborhood difference method based on longitudinal projection; (5) And acquiring the position of the coating boundary by adopting a local rapid ordering algorithm. The efficient positioning method for the lithium battery coating boundary fully considers the characteristic of coating operation from the engineering application point of view, and overcomes the inherent defects of long time consumption and inaccurate positioning of a common edge solving algorithm; meanwhile, the problem of poor real-time monitoring accuracy caused by abnormal change of a coating boundary due to uneven tension in the coating operation process due to thinner aluminum foil base material is solved, and the method has high efficiency and better robustness.
Description
Technical Field
The invention belongs to the technical field of lithium ion battery manufacturing, and particularly relates to a high-efficiency positioning method for a lithium battery coating boundary.
Background
When the lithium battery works, the charge and discharge are completed through the migration of lithium ions between the anode and the cathode, the battery pole piece is used as the basis of the lithium battery, and the coating quality of the battery pole piece influences the performance of the battery. The cathode of the battery is usually composed of lithium intercalation oxide, is used for releasing lithium ions during charging, is the most critical part in the lithium battery, and accounts for about one third of the cost of the core material of the lithium battery, and directly determines the charge and discharge capacity of the battery, so that the improvement and improvement of the quality of cathode materials is an important research direction of the battery industry.
When the cathode plate of the battery is produced, cathode materials are prepared into slurry liquid, the slurry liquid is sprayed on a substrate made of aluminum foil through a coater, and the slurry liquid is dried through an oven. To fully utilize the substrate space, one side of the substrate is typically coated with a plurality of cathode films, typically 1, 2, 3 or 4, commonly referred to in production as 1 out 2, 1 out 4, 1 out 6 and 1 out 8. And after the double-sided production of the coated double surfaces of the multiple films is finished, the single-sided coating is formed by later cutting, so that the further deep processing is realized. In order to make the cut coating more accurate, accurate measurement of the position and size of each film is required to ensure alignment of the film boundaries on the upper and lower surfaces, preventing false shearing of the boundaries during shearing.
Since the width and position of the film are ensured by the spray die, once the die is properly adjusted, it is generally considered that the film width does not vary too much, so current research on coating detection is mainly focused on defect detection and thickness detection, while for coating film width detection, on-line measurement is mostly performed by manual sampling. However, in practice, the film width varies within a certain period of time due to the deviation correction vibration during the production process, the influence of factors such as pressure (slurry is sprayed on the substrate through the die head after being pressurized), temperature, and the like. Because the manual measurement error is larger (generally more than +/-0.5 mm), and the sampling measurement can not know the change condition of the film width in time. Therefore, an on-line automatic detection technique of the coating film width needs to be studied.
The key technology of coating measurement is edge positioning, which is how to quickly and accurately find the boundary of coating for an image. At present, the conventional boundary obtaining method mainly comprises edge operators such as Canny, sobel, laplacian, which are long in time consumption and inaccurate in positioning, and the lithium battery is coated widely, so that the field of view of an image is large (usually about 800 mm), the phenomenon that the light rays are uneven after the linear array light source lights due to different reflectivities of different coating areas is generated, and in the coating operation process, the abnormal change of the coating boundary is easily caused by uneven tension due to thinner aluminum foil base materials, so that the difficulty is brought to real-time accurate detection of the coating boundary.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides an efficient positioning method for the coating boundary of the lithium battery with both efficiency and robustness on the basis of fully considering the coating operation characteristics from the engineering application point of view.
The invention realizes the aim through the following technical scheme, and the high-efficiency positioning method for the coating boundary of the lithium battery comprises the following steps:
(1) Detecting the direction edge of the original coating image;
(2) Binarizing the edge image;
(3) Traversing the whole image by adopting a longitudinal projection searching edge algorithm to obtain a non-zero pixel position;
(4) Removing interference noise in the projection value by adopting a neighborhood difference method based on longitudinal projection;
(5) And acquiring the position of the coating boundary by adopting a local rapid ordering algorithm.
In the above technical solution, the direction edge detection method includes:
(1)
in the formula, I%i,j) Is the original image, I ¢%i,j) Is a directional edge image.
In the above technical solution, the projection vector of the longitudinal projection search edge algorithm is:
() (2)
in the method, in the process of the invention,represents the j-th pixel value of the i-th row in the binarized image, and +.>Width represents the width of the image and height represents the height of the image.
In the above technical solution, the neighborhood difference method is mainly used for searching the maximum contrast in the neighborhood, and its formula is as follows:
(3)
where, delta is the neighborhood span,is a projection neighborhood difference vector.
In the above technical solution, the local rapid ordering algorithm includes the following steps:
a. initializing an edge vector E (k), and setting a detection threshold Tu and a merging threshold Tc;
b. traversing projection neighborhood difference vectorsJudging whether the detection threshold Tu is larger than or equal to the detection threshold Tu;
c. if the neighborhood differential vectorTraversing the edge vector E if the detection threshold Tu is larger than the detection threshold Tu, and judging whether the edge vector E (k) is larger than the edge vector E;
d. if the difference vector is larger than the edge vector E (k), calculating a projection neighborhood difference vectorThe distance Dis (j, pos (E (k))) between the j-th position and the position corresponding to E (k), and comparing the distance with a merging threshold Tc;
e. if the distance is less than the combining threshold Tc, then the same effective peak is considered;
f. and outputting edge vectors E, namely k boundaries.
In general, compared with the prior art, the above technical solution conceived by the present invention can achieve the following beneficial effects: in the process of one traversal, only limited peaks need to be compared, so that priori knowledge (the number of boundaries) can be fully utilized to accelerate searching; meanwhile, since the C ¢ value of the boundary is often much larger than the non-boundary value, the search frequency can be greatly reduced on the basis of setting the detection threshold Tu, for example, tu=max (C ¢)/4, and the time complexity of the boundary positioning algorithm is about O (k) 2 ) O (n multiplied by k), and under the condition of fewer boundaries in the image, the boundary of the lithium battery coating can be rapidly positioned so as to be obtained.
Drawings
The invention is described in further detail below with reference to the attached drawing figures, wherein:
FIG. 1 is an original coating image taken by an industrial camera on a lithium battery coating line;
FIG. 2 is a binarized lithium battery coated image;
FIG. 3 is a boundary projection view of a longitudinal projection of a coated image using a longitudinal projection find edge algorithm according to the present invention;
FIG. 4 is a boundary projection differential neighborhood graph obtained when the neighborhood span value is 8;
FIG. 5 is a block flow diagram of a local fast ordering algorithm according to the present invention;
FIG. 6 is a schematic diagram of locating boundary coordinates using the local fast ordering algorithm of the present invention.
Detailed Description
The invention realizes the aim through the following technical scheme, and the high-efficiency positioning method for the coating boundary of the lithium battery comprises the following steps:
(1) Detecting the direction edge of the original coating image;
(2) Performing binarization processing on the edge image;
(3) Traversing the whole image by adopting a longitudinal projection searching edge algorithm to obtain a non-zero pixel position;
(4) Removing interference noise in the projection value by adopting a neighborhood difference method based on longitudinal projection;
(5) And acquiring the position of the coating boundary by adopting a local rapid ordering algorithm.
When the boundary positioning method is used, an industrial camera is used for photographing the lithium battery coating, as shown in fig. 1, an original coating image photographed by the industrial camera on a lithium battery coating production line is obtained, and then the direction edge detection and the binarization processing are carried out, and the processed coating boundary image is shown in fig. 2.
In the actual production process, the coating edges are longitudinally distributed, so that the detection method adopts the detection of the directional edges, and the detection method comprises the following steps:
(1)
in the formula, I%i,j) Is the original image, I ¢%i,j) Is a directional edge image.
The direction edge binarization image adopts a longitudinal projection search edge algorithm to traverse the whole image to obtain a non-zero pixel position, and the projection vector is as follows:
() (2)
in the method, in the process of the invention,represents the j-th pixel value of the i-th row in the binarized image, and +.>Width represents the width of the image and height represents the height of the image.
After the processing of the longitudinal projection search edge algorithm, the boundary projection of the longitudinal projection of the coated image is shown in fig. 3, and for a relatively clear boundary, the longitudinal projection can correctly reflect the boundary positions, such as the positions E2 and E3 in fig. 3, but if the image boundary has interference, such as the positions E1 and E4 in fig. 3, the saliency of the boundary is less obvious, and the existing interference peak value can cause misjudgment of the boundary.
In order to solve the interference, the invention adopts a neighborhood difference method based on longitudinal projection to find the maximum contrast in the neighborhood, and the formula is as follows:
(3)
where, delta is the neighborhood span,the vectors are looked up for the projection neighborhood.
As shown in FIG. 4, when the neighborhood span delta value in the formula is 8, the obtained boundary projection differential neighborhood graph can be seen that most of interference values are reduced, and the step edge value is well reserved.
In order to further obtain the position coordinates of the coating boundary, the invention sets the distance between two adjacent extremum values, when the distance between the two extremum values is smaller than a given value, the two extremum values can be combined, the two extremum values are taken to be larger, and meanwhile, a local quick ordering algorithm is provided, and fig. 5 is a flow chart of the local quick ordering algorithm.
In this flowchart, dis (j, pos (E (k))) represents a projection neighborhood difference vectorThe distance between the j-th position and the position corresponding to E (k), and End (X) represents the length of the vector. As can be seen from fig. 5, only the limited peak value needs to be subjected to contrast bubbling in one traversal process, so that the search can be accelerated by fully utilizing priori knowledge (the number of boundaries); meanwhile, since the boundary value of C ¢ is often much larger than the non-boundary value, the search frequency can be greatly reduced on the basis of setting the condition Tu, such as Tu=max (C ¢)/4, and the time complexity of the local fast ordering algorithm is about O (k 2 ) O (n multiplied by k), when the number of boundaries in the image is small, boundary position information can be obtained rapidly, and the method is more suitable for being applied to engineering practice of lithium battery coating boundary positioning.
Table 1 shows a comparison of the efficiency of 1000 orders for a vector of dimension 8192, from which it can be seen that the algorithm has a significant improvement in efficiency. FIG. 6 shows the coordinates of the coating boundary obtained by one-time positioning, wherein the upper square is the position coordinates, and the lower square is the C ¢ value.
TABLE 1
Type(s) | Quick search algorithm | Local rapid ordering algorithm |
Time (ms) | 242 | 111 |
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (1)
1. A high-efficiency positioning method for a lithium battery coating boundary is characterized by comprising the following steps: the coating boundary positioning method comprises the following steps:
(1) The original coating image is subjected to direction edge detection, and the direction edge detection method comprises the following steps:
wherein I (I, j) is an original image, I' (I, j) is a directional edge image;
(2) Performing binarization processing on the edge image;
(3) Traversing the whole image by adopting a longitudinal projection searching edge algorithm to obtain a non-zero pixel position, wherein the projection vector of the longitudinal projection searching edge algorithm is as follows:
wherein R is ij Represents the j pixel value of the ith row in the binarized image, and R ij E {0,1}, width represents the width of the image, height represents the height of the image;
(4) The method is characterized in that a neighborhood difference method based on longitudinal projection is adopted to remove interference noise in a projection value, and the main purpose of the neighborhood difference method is to find the maximum contrast in the neighborhood, wherein the formula is as follows:
C′(j)=C(j)-min{C(k)|j-Δ<k<j} (3)
wherein delta is the neighborhood span, and C' (j) is the projection neighborhood difference vector;
(5) The position of the coating boundary is obtained by adopting a local quick ordering algorithm, and the local quick ordering algorithm comprises the following steps:
a. initializing an edge vector E (k), and setting a detection threshold Tu and a merging threshold Tc;
b. traversing the projection neighborhood difference vector C' (j) and judging whether the projection neighborhood difference vector is larger than a detection threshold Tu or not;
c. if the neighborhood difference vector C '(j) is larger than the detection threshold Tu, traversing the edge vector E again, and judging whether the neighborhood difference vector C' (j) is larger than the edge vector E (k);
d. if the distance is larger than the edge vector E (k), calculating a distance Dis (j, pos (E (k))) between a j-th position in the projection neighborhood differential vector C' (j) and a position corresponding to the E (k), and comparing the distance with a merging threshold Tc;
e. if the distance is less than the combining threshold Tc, then the same effective peak is considered;
f. and outputting an edge vector E, namely k boundaries to be found and positioned.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810028750.8A CN108053404B (en) | 2018-01-12 | 2018-01-12 | Efficient positioning method for lithium battery coating boundary |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810028750.8A CN108053404B (en) | 2018-01-12 | 2018-01-12 | Efficient positioning method for lithium battery coating boundary |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108053404A CN108053404A (en) | 2018-05-18 |
CN108053404B true CN108053404B (en) | 2024-01-09 |
Family
ID=62126655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810028750.8A Active CN108053404B (en) | 2018-01-12 | 2018-01-12 | Efficient positioning method for lithium battery coating boundary |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053404B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115808126B (en) * | 2023-02-03 | 2023-05-30 | 杭州百子尖科技股份有限公司 | Lithium electrode sheet coating boundary positioning method based on machine vision scanning data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09180735A (en) * | 1995-12-25 | 1997-07-11 | Fuji Photo Film Co Ltd | Electrode sheet positioner of battery winding machine |
JP2006023199A (en) * | 2004-07-08 | 2006-01-26 | Yamatake Corp | Edge detection method and detector |
CN103150722A (en) * | 2013-01-17 | 2013-06-12 | 东南大学 | Method for extracting peripheral blood leucocyte edges with application of quaternion division and graph theory optimization |
JP2014078448A (en) * | 2012-10-11 | 2014-05-01 | Toyota Industries Corp | Edge detection method |
CN104197841A (en) * | 2014-09-09 | 2014-12-10 | 深圳市斯尔顿科技有限公司 | Method for detecting boundaries of lithium battery winding layer |
CN106093068A (en) * | 2016-08-10 | 2016-11-09 | 武汉科技大学 | The imaging system of lithium battery pole slice surface defect detection apparatus and using method thereof |
JP2017212081A (en) * | 2016-05-24 | 2017-11-30 | エリーパワー株式会社 | End position detection system of electrode for electrochemical cell and manufacturing method |
-
2018
- 2018-01-12 CN CN201810028750.8A patent/CN108053404B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09180735A (en) * | 1995-12-25 | 1997-07-11 | Fuji Photo Film Co Ltd | Electrode sheet positioner of battery winding machine |
JP2006023199A (en) * | 2004-07-08 | 2006-01-26 | Yamatake Corp | Edge detection method and detector |
JP2014078448A (en) * | 2012-10-11 | 2014-05-01 | Toyota Industries Corp | Edge detection method |
CN103150722A (en) * | 2013-01-17 | 2013-06-12 | 东南大学 | Method for extracting peripheral blood leucocyte edges with application of quaternion division and graph theory optimization |
CN104197841A (en) * | 2014-09-09 | 2014-12-10 | 深圳市斯尔顿科技有限公司 | Method for detecting boundaries of lithium battery winding layer |
JP2017212081A (en) * | 2016-05-24 | 2017-11-30 | エリーパワー株式会社 | End position detection system of electrode for electrochemical cell and manufacturing method |
CN106093068A (en) * | 2016-08-10 | 2016-11-09 | 武汉科技大学 | The imaging system of lithium battery pole slice surface defect detection apparatus and using method thereof |
Non-Patent Citations (3)
Title |
---|
刘怀广等.一种锂电池涂布在线测量边缘拟合方法.《光电工程》.2019,第46卷(第10期),1-11. * |
王玉槐 ; 王琦晖 ; 寿周翔 ; 赵鑫权 ; .应用改进Canny法检测工业零件含噪图像边缘.轻工机械.2012,(第04期),77-80. * |
赵晓云 ; 郑治华 ; 韩洪伟 ; 谢仁义 ; 王凯 ; 徐志强 ; .锂电池极片表面缺陷特征提取方法研究.河南科技.2017,(第05期),137-139. * |
Also Published As
Publication number | Publication date |
---|---|
CN108053404A (en) | 2018-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106855520B (en) | Workpiece defect detection method based on machine vision | |
CN113989232B (en) | Battery cell defect detection method and device, electronic equipment and storage medium | |
US7684611B2 (en) | Photoresist edge bead removal measurement | |
CN112819845B (en) | Flexible package substrate contour, line width and line distance defect detection method, medium and equipment | |
CN109580652A (en) | A kind of quality of battery pole piece detection method, electronic equipment and storage medium | |
KR20160127046A (en) | Automated inline inspection and metrology using shadow-gram images | |
Li et al. | Automatic saw-mark detection in multicrystalline solar wafer images | |
US20200038929A1 (en) | Apparatus, method, and program for monitoring operation of high frequency resistance welding and induction heating welding of electric resistance welded steel pipe | |
JP7398483B2 (en) | Metrics for asymmetric wafer shape characterization | |
WO2023193213A1 (en) | Method and apparatus for detecting defect of insulating coating of battery electrode plate, and computer device | |
CN110530278B (en) | Method for measuring clearance surface difference by utilizing multi-line structured light | |
CN108053404B (en) | Efficient positioning method for lithium battery coating boundary | |
CN113393463B (en) | Soft package battery roll core detection and shell entering method | |
CN115330796B (en) | Copper wire tinning defect identification method | |
CN106064389B (en) | A kind of electrodes of lithium-ion batteries cutting method | |
CN115965623A (en) | Surface flaw detection method and system in transformer production | |
CN114549393B (en) | Image labeling method, device, equipment and computer storage medium | |
CN116773559A (en) | Laminated lithium ion battery detection method and device and image processing equipment | |
Liu et al. | An automatic defects detection scheme for lithium-ion battery electrode surface | |
CN112730459B (en) | Bearing inner ring end surface defect detection method based on multi-angle light source shooting image | |
CN116228798A (en) | Intelligent iron tower cutting detection method based on machine vision | |
EP4230953A1 (en) | Deviation detection method and deviation detection device | |
CN114619152B (en) | Intelligent cutting system for aluminum veneer production and manufacturing | |
CN114882032B (en) | Grooving detection and intelligent sensing processing method and system for semiconductor | |
CN116385418B (en) | Image processing method of whole-stacked silicon wafer and silicon wafer whole-stacked detection system |
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 |