CN103345743A - Image segmentation method for intelligent flaw detection of cell tail end - Google Patents

Image segmentation method for intelligent flaw detection of cell tail end Download PDF

Info

Publication number
CN103345743A
CN103345743A CN2013102438251A CN201310243825A CN103345743A CN 103345743 A CN103345743 A CN 103345743A CN 2013102438251 A CN2013102438251 A CN 2013102438251A CN 201310243825 A CN201310243825 A CN 201310243825A CN 103345743 A CN103345743 A CN 103345743A
Authority
CN
China
Prior art keywords
image
tail end
src
pixel
battery tail
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2013102438251A
Other languages
Chinese (zh)
Other versions
CN103345743B (en
Inventor
胡文华
田丹
朱柯润
罗净
李坤艳
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.)
NINGBO CHENGDIAN TAIKE ELECTRONIC INFORMATION TECHNOLOGY DEVELOPMENT Co Ltd
Original Assignee
NINGBO CHENGDIAN TAIKE ELECTRONIC INFORMATION TECHNOLOGY DEVELOPMENT Co Ltd
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 NINGBO CHENGDIAN TAIKE ELECTRONIC INFORMATION TECHNOLOGY DEVELOPMENT Co Ltd filed Critical NINGBO CHENGDIAN TAIKE ELECTRONIC INFORMATION TECHNOLOGY DEVELOPMENT Co Ltd
Priority to CN201310243825.1A priority Critical patent/CN103345743B/en
Publication of CN103345743A publication Critical patent/CN103345743A/en
Application granted granted Critical
Publication of CN103345743B publication Critical patent/CN103345743B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Secondary Cells (AREA)

Abstract

The invention discloses an image segmentation method for flaw detection of a cell tail end. Firstly, an initial BGR image at the cell tail end is converted into a gray scale image by considering image characteristics of intelligent flaw detection of the cell tail end, then the gray scale image is subjected to binaryzation processing so as to obtain a binaryzation image, and then coordinates of four key pixel points on the outer contour of the cell tail end are determined on the binaryzation image. The size of an ROI rectangular area where the cell tail end exists is determined according to the coordinates of the four key pixel points on the outer contour of the cell tail end, therefore the ROI rectangular area where the cell end tail exists is marked off in the initial BGR image, and a target area is not damaged. High accuracy in image dividing is ensured, operation is simple, and an early-stage guarantee is provided for accuracy of follow-up processing algorithms (such as the image characteristic extracting and matching algorithm). In addition, the ROI rectangular area is marked off in the initial BGR image, so that the processing of the whole image comprising the background with the follow-up processing algorithms is avoided, detecting efficiency of a cell is improved, and detecting cost is reduced.

Description

A kind of image segmentation algorithm for battery tail end smart flaw detection
Technical field
The present invention relates to a kind of battery tail end smart flaw detection technology, especially relate to a kind of image segmentation algorithm for battery tail end smart flaw detection.
Background technology
Machine vision technique just progressively is applied in each manufacturing at present, and battery is applied to battery tail end wound with mechanical vision inspection technology and detects the detection efficiency that can greatly improve battery as the great a kind of product of demand in the manufacturing industry.And image segmentation algorithm is a kind of algorithm that extracts target area in the pending image, it is the whose forwardmost end portions in the smart flaw detection flow process, therefore the quality of its Processing Algorithm will directly have influence on follow-up processing flow, and studying a kind of tail end of battery accurately and effectively partitioning algorithm is significant to the smart flaw detection process of battery tail end.
On production line for manufacturing battery, camera is in the process of gathering battery afterbody image, because the influence of objective factors such as the delay of camera subject trigger circuit and camera shutter parameter, the position of battery in photo is at random, and we only are concerned about the rectangular area at battery target place in the image, we are referred to as interesting image regions (ROI) this zone, so need carry out rough handling to picture shot, namely cut out the image that only comprises the battery end section.
Be that outline with battery in the image fits to ellipse at the main methods of battery tail end segmentation problem at present, orient battery part in the image by the parameter of ellipse, thereby realize cutting apart.These method concrete steps are as follows: adopt lower segmentation threshold to carry out binary conversion treatment to original-gray image, obtain binary image, follow the tracks of by profile then and calculate the contour pixel point set that obtains the bianry image connected region, i.e. two-dimentional point set; Use least square method to carry out ellipse fitting to two-dimentional point set, obtain centre coordinate and axle radius; According to centre coordinate and major axis radius, minor axis radius, the validity that detects target is differentiated; If detect target effective, behind the location with it as the ROI zone and from original image, separate, algorithm finishes.
The method that above-mentioned parameter by ellipse is oriented battery part in the image adopts the mode of curve match that battery tail end outline in the image is detected, the curve match is a kind of approximate disposal route, the pixel that can not absolutely guarantee battery end section in the image is not cut, so adopt this method accuracy bad, may excise the cell image part by mistake.Have computings such as a large amount of multiplication, division, evolution, differentiate in the computing of this method in addition, operand is bigger.
Summary of the invention
Technical matters to be solved by this invention provides a kind of accuracy rate height, and computing simply is used for the image segmentation algorithm of battery tail end smart flaw detection.Image segmentation algorithm of the present invention can be partitioned into the minimum image that comprises the battery tail end accurately and efficiently, and algorithm principle is simple, reliability is high.
The present invention solves the problems of the technologies described above the technical scheme that adopts: a kind of image segmentation algorithm for battery tail end smart flaw detection comprises the steps:
The initial BGR image of the battery tail end that 1. camera is collected is designated as src, and its size is expressed as M * N, the columns of M presentation video wherein, and the line number of N presentation video, the line number of src image is 0~N-1, the column number of src image is 0~M-1;
2. (src, src_gray are gray level image with the src image transitions CV_BGR2GRAY), and the gray level image that obtains is designated as src_gray, and wherein CV_BGR2GRAY represents with the BGR image transitions to be the mode of gray level image to adopt OpenCV built-in function cvtColor;
3. adopt Otsu binary conversion treatment function cvThresholdOtsu (src_gray, binary_img) gray level image src_gray is carried out binary conversion treatment and save as bianry image, this bianry image is designated as binary_img, and the line number of bianry image binary_img is identical with the src image with columns;
4. determine the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img, the coordinate of four crucial pixels is: the summit pixel f of battery tail end outline Top(top_x, top_y), the end of battery tail end outline point pixel f Bottom(bottom_x, bottom_y), the high order end pixel f of battery tail end outline Left(left_x, left_y) and the low order end pixel f of battery tail end outline Right(right_x, right_y), wherein top_x represents the horizontal ordinate of battery tail end outline summit pixel, top_y represents the ordinate of battery tail end outline summit pixel, bottom_x represents the horizontal ordinate of some pixel at the bottom of the battery tail end outline, bottom_y represents the ordinate of some pixel at the bottom of the battery tail end outline, left_x represents the horizontal ordinate of battery tail end outline high order end pixel, left_y represents the ordinate of battery tail end outline high order end pixel, right_x represents the horizontal ordinate of battery tail end outline low order end pixel, and right_y represents the ordinate of battery tail end outline low order end pixel;
5. calculate width and the height of the ROI rectangular area at battery tail end outline place according to formula W=right_x-left_x+1 and H=bottom_y-top_y+1, wherein W represents the width of ROI rectangular area, H represents the height of ROI rectangular area, adopt OpenCV built-in function CvSize size=cvSize (W, H) size that the ROI rectangular area is set is W * H;
6. adopt OpenCV built-in function cvSetImageROI (src, cvRect (left_x, top_y, W, H)) from the src image, mark off size and be the ROI rectangular area at the battery tail end outline place of W * H, wherein cvRect (left_x, top_y, W, H) function of the ROI rectangular area at expression battery tail end outline place;
7. adopt OpenCV built-in function cut_image=cvCreateImage (size, src->depth, src->nChannels) picture cut_image is cut apart in establishment, wherein to represent to cut apart the degree of depth of picture cut_image identical with the degree of depth of src image for size->depth, and the port number that size->nChannels represents to cut apart picture cut_image is identical with the port number of src image;
8. (src, the ROI rectangular area at the battery tail end outline place that cut_image) will mark off from the src image is deposited into to be cut apart among the picture cut_image, obtains battery tail end split image to adopt function cvCopy.
Described step determines that the concrete steps of the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img are in 4.:
4.-1 from the 0th row of bianry image binary_img, order is found out the wherein pixel coordinate of first non-zero by row traversal bianry image binary_img, and this coordinate is the coordinate f of the battery tail end outline summit pixel among the bianry image binary_img Top(top_x, top_y);
4.-2 the N-1 from bianry image binary_img is capable, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate of first non-zero, this coordinate is the coordinate f of some pixel at the bottom of the battery tail end outline among the bianry image binary_img Bottom(bottom_x, bottom_y);
4.-3 be listed as from the 0th of bianry image binary_img, order is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline high order end pixel among the bianry image binary_img Left(left_x, left_y);
4.-4 the M-1 from bianry image binary_img is listed as, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline low order end pixel among the bianry image binary_img Right(right_x, right_y).
Compared with prior art, the invention has the advantages that the picture characteristics at battery tail end smart flaw detection, at first the initial BGR image transitions with the battery tail end is gray level image, then gray level image is carried out binary conversion treatment and obtain bianry image, then determine the coordinate of four crucial pixels on the battery tail end outline at bianry image, determine the size of the ROI rectangular area at battery tail end place according to the coordinate of four crucial pixels on the battery tail end outline, thereby in initial BGR image, mark off the ROI rectangular area at battery tail end place, can not damage the target area thus, guarantee the accuracy rate height that image is cut apart, and computing for providing in earlier stage, the accuracy of subsequent treatment algorithm (as image characteristics extraction and matching algorithm) ensures simply; From initial BGR image, be partitioned into the ROI rectangular area in addition and avoided the subsequent treatment algorithm that the entire image that comprises background is handled, greatly improved the detection efficiency of battery, reduced the detection cost;
Travel through the coordinate time that the method for seeking first non-zero pixels point to battery target outline obtains four crucial pixels from the bianry image edge when adopting, this method begins to travel through pixel from image top, bottom, high order end and low order end respectively, effectively reduced the pixel number of traversal, further simplify algorithm, improved efficient.
Description of drawings
Fig. 1 is theory diagram of the present invention;
Fig. 2 is the initial BGR image of embodiment;
Fig. 3 is the gray level image of embodiment;
Fig. 4 is the bianry image of embodiment;
Fig. 5 is the battery tail end split image of embodiment.
Embodiment
Describe in further detail below in conjunction with the present invention of accompanying drawing embodiment.
As shown in Figure 1, the invention discloses a kind of image segmentation algorithm for battery tail end smart flaw detection, comprise the steps:
The initial BGR image of the battery tail end that 1. camera is collected is designated as src, and its size is expressed as M * N, the columns of M presentation video wherein, and the line number of N presentation video, the line number of src image is 0~N-1, the column number of src image is 0~M-1;
2. (src, src_gray are gray level image with the src image transitions CV_BGR2GRAY), and the gray level image that obtains is designated as src_gray, and wherein CV_BGR2GRAY represents with the BGR image transitions to be the mode of gray level image to adopt OpenCV built-in function cvtColor;
3. adopt Otsu binary conversion treatment function cvThresholdOtsu (src_gray, binary_img) gray level image src_gray is carried out binary conversion treatment and save as bianry image, this bianry image is designated as binary_img, and the line number of bianry image binary_img is identical with the src image with columns;
4. determine the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img, the coordinate of four crucial pixels is: the summit pixel f of battery tail end outline Top(top_x, top_y), the end of battery tail end outline point pixel f Bottom(bottom_x, bottom_y), the high order end pixel f of battery tail end outline Left(left_x, left_y) and the low order end pixel f of battery tail end outline Right(right_x, right_y), wherein top_x represents the horizontal ordinate of battery tail end outline summit pixel, top_y represents the ordinate of battery tail end outline summit pixel, bottom_x represents the horizontal ordinate of some pixel at the bottom of the battery tail end outline, bottom_y represents the ordinate of some pixel at the bottom of the battery tail end outline, left_x represents the horizontal ordinate of battery tail end outline high order end pixel, left_y represents the ordinate of battery tail end outline high order end pixel, right_x represents the horizontal ordinate of battery tail end outline low order end pixel, and right_y represents the ordinate of battery tail end outline low order end pixel;
5. calculate width and the height of the ROI rectangular area at battery tail end outline place according to formula W=right_x-left_x+1 and H=bottom_y-top_y+1, wherein W represents the width of ROI rectangular area, H represents the height of ROI rectangular area, adopt OpenCV built-in function CvSize size=cvSize (W, H) size that the ROI rectangular area is set is W * H;
6. adopt OpenCV built-in function cvSetImageROI (src, cvRect (left_x, top_y, W, H)) from the src image, mark off size and be the ROI rectangular area at the battery tail end outline place of W * H, wherein cvRect (left_x, top_y, W, H) function of the ROI rectangular area at expression battery tail end outline place;
7. adopt OpenCV built-in function cut_image=cvCreateImage (size, src->depth, src->nChannels) picture cut_image is cut apart in establishment, wherein to represent to cut apart the degree of depth of picture cut_image identical with the degree of depth of src image for size->depth, and the port number that size->nChannels represents to cut apart picture cut_image is identical with the port number of src image;
8. (src, the ROI rectangular area at the battery tail end outline place that cut_image) will mark off from the src image is deposited into to be cut apart among the picture cut_image, obtains battery tail end split image to adopt function cvCopy.
Embodiment: a kind of image segmentation algorithm for battery tail end smart flaw detection comprises the steps:
The initial BGR image of the battery tail end that 1. camera is collected is designated as src, the size of src image is 1392 * 1040, the columns of 1392 expression src images wherein, the line number of 1040 expression src images, the line number of src image is 0~1039, the column number of src image is 0~1391, and initial BGR image as shown in Figure 2;
2. adopt OpenCV built-in function cvtColor (src, src_gray, CV_BGR2GRAY) with the src image transitions be as shown in Figure 3 gray level image, the gray level image that obtains is designated as src_gray, and wherein CV_BGR2GRAY represents with the BGR image transitions to be the mode of gray level image;
3. adopt Otsu binary conversion treatment function cvThresholdOtsu (src_gray, binary_img) gray level image src_gray is carried out binary conversion treatment and save as shown in Figure 4 bianry image, this bianry image is designated as binary_img, and the line number of bianry image binary_img is identical with the src image with columns;
4. determine the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img, the coordinate of four crucial pixels is: the summit pixel f of battery tail end outline Top(top_x, top_y), the end of battery tail end outline point pixel f Bottom(bottom_x, bottom_y), the high order end pixel f of battery tail end outline Left(left_x, left_y) and the low order end pixel f of battery tail end outline Right(right_x, right_y), wherein top_x represents the horizontal ordinate of battery tail end outline summit pixel, top_y represents the ordinate of battery tail end outline summit pixel, bottom_x represents the horizontal ordinate of some pixel at the bottom of the battery tail end outline, bottom_y represents the ordinate of some pixel at the bottom of the battery tail end outline, left_x represents the horizontal ordinate of battery tail end outline high order end pixel, left_y represents the ordinate of battery tail end outline high order end pixel, right_x represents the horizontal ordinate of battery tail end outline low order end pixel, and right_y represents the ordinate of battery tail end outline low order end pixel; The concrete steps of determining the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img are:
4.-1 from the 0th row of bianry image binary_img, order is found out the wherein pixel coordinate of first non-zero by row traversal bianry image binary_img, and this coordinate is the coordinate f of the battery tail end outline summit pixel among the bianry image binary_img Top(544,224);
4.-2 go from the 1039th of bianry image binary_img, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate of first non-zero, this coordinate is the coordinate f of some pixel at the bottom of the battery tail end outline among the bianry image binary_img Bottom(327,1039);
4.-3 be listed as from the 0th of bianry image binary_img, order is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline high order end pixel among the bianry image binary_img Left(111,643);
4.-4 be listed as from the 1391st of bianry image binary_img, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline low order end pixel among the bianry image binary_img Right(985,648);
5. calculate width and the height of the ROI rectangular area at battery tail end outline place according to formula W=right_x-left_x+1 and H=bottom_y-top_y+1, wherein W represents the width of ROI rectangular area, H represents the height of ROI rectangular area, calculate W=875, H=816, the size that adopts OpenCV built-in function CvSize size=cvSize (875,816) that the ROI rectangular area is set is 875 * 816;
6. adopt OpenCV built-in function cvSetImageROI (src, cvRect (111,224,875,816)) mark off the ROI rectangular area that size is 875 * 816 battery tail end outline place from the src image, wherein cvRect (111,224,875,816) function of the ROI rectangular area at expression battery tail end outline place;
7. adopt OpenCV built-in function cut_image=cvCreateImage (size, src->depth, src->nChannels) picture cut_image is cut apart in establishment, wherein to represent to cut apart the degree of depth of picture cut_image identical with the degree of depth of src image for size->depth, and the port number that size->nChannels represents to cut apart picture cut_image is identical with the port number of src image;
8. (src, the ROI rectangular area at the battery tail end outline place that cut_image) will mark off from the src image is deposited into to be cut apart among the picture cut_image, obtains battery tail end split image as shown in Figure 5 to adopt function cvCopy.
Method of the present invention has been partitioned into the image of a width of cloth battery target rectangle area size exactly as can be seen from Figure 5, and any damaged condition does not appear in the battery part.
In the present embodiment, the coordinate of summit, end point, high order end and low order end pixel by battery tail end outline in the bianry image delimited the ROI rectangular area, characteristic according to battery tail end edge image, only need by traveling through bianry image binary_img differently, can effectively find the coordinate of these four crucial pixels rapidly, algorithm is simple, and the accuracy height.

Claims (2)

1. an image segmentation algorithm that is used for battery tail end smart flaw detection is characterized in that comprising the steps:
The initial BGR image of the battery tail end that 1. camera is collected is designated as src, and its size is expressed as M * N, the columns of M presentation video wherein, and the line number of N presentation video, the line number of src image is 0~N-1, the column number of src image is 0~M-1;
2. (src, src_gray are gray level image with the src image transitions CV_BGR2GRAY), and the gray level image that obtains is designated as src_gray, and wherein CV_BGR2GRAY represents with the BGR image transitions to be the mode of gray level image to adopt OpenCV built-in function cvtColor;
3. adopt Otsu binary conversion treatment function cvThresholdOtsu (src_gray, binary_img) gray level image src_gray is carried out binary conversion treatment and save as bianry image, this bianry image is designated as binary_img, and the line number of bianry image binary_img is identical with the src image with columns;
4. determine the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img, the coordinate of four crucial pixels is: the summit pixel f of battery tail end outline Top(top_x, top_y), the end of battery tail end outline point pixel f Bottom(bottom_x, bottom_y), the high order end pixel f of battery tail end outline Left(left_x, left_y) and the low order end pixel f of battery tail end outline Right(right_x, right_y), wherein top_x represents the horizontal ordinate of battery tail end outline summit pixel, top_y represents the ordinate of battery tail end outline summit pixel, bottom_x represents the horizontal ordinate of some pixel at the bottom of the battery tail end outline, bottom_y represents the ordinate of some pixel at the bottom of the battery tail end outline, left_x represents the horizontal ordinate of battery tail end outline high order end pixel, left_y represents the ordinate of battery tail end outline high order end pixel, right_x represents the horizontal ordinate of battery tail end outline low order end pixel, and right_y represents the ordinate of battery tail end outline low order end pixel;
5. calculate width and the height of the ROI rectangular area at battery tail end outline place according to formula W=right_x-left_x+1 and H=bottom_y-top_y+1, wherein W represents the width of ROI rectangular area, H represents the height of ROI rectangular area, adopt OpenCV built-in function CvSize size=cvSize (W, H) size that the ROI rectangular area is set is W * H;
6. adopt OpenCV built-in function cvSetImageROI (src, cvRect (left_x, top_y, W, H)) from the src image, mark off size and be the ROI rectangular area at the battery tail end outline place of W * H, wherein cvRect (left_x, top_y, W, H) function of the ROI rectangular area at expression battery tail end outline place;
7. adopt OpenCV built-in function cut_image=cvCreateImage (size, src->depth, src->nChannels) picture cut_image is cut apart in establishment, wherein to represent to cut apart the degree of depth of picture cut_image identical with the degree of depth of src image for size->depth, and the port number that size->nChannels represents to cut apart picture cut_image is identical with the port number of src image;
8. (src, the ROI rectangular area at the battery tail end outline place that cut_image) will mark off from the src image is deposited into to be cut apart among the picture cut_image, obtains battery tail end split image to adopt function cvCopy.
2. a kind of image segmentation algorithm for battery tail end smart flaw detection according to claim 1 is characterized in that determining during described step is 4. that the concrete steps of the coordinate of four crucial pixels on the battery tail end outline among the bianry image binary_img are:
4.-1 from the 0th row of bianry image binary_img, order is found out the wherein pixel coordinate of first non-zero by row traversal bianry image binary_img, and this coordinate is the coordinate f of the battery tail end outline summit pixel among the bianry image binary_img Top(top_x, top_y);
4.-2 the N-1 from bianry image binary_img is capable, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate of first non-zero, this coordinate is the coordinate f of some pixel at the bottom of the battery tail end outline among the bianry image binary_img Bottom(bottom_x, bottom_y);
4.-3 be listed as from the 0th of bianry image binary_img, order is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline high order end pixel among the bianry image binary_img Left(left_x, left_y);
4.-4 the M-1 from bianry image binary_img is listed as, backward is by row traversal bianry image binary_img, find out the wherein pixel coordinate note of first non-zero, this coordinate is the coordinate f of the battery tail end outline low order end pixel among the bianry image binary_img Right(right_x, right_y).
CN201310243825.1A 2013-06-18 2013-06-18 A kind of image partition method for battery tail end smart flaw detection Expired - Fee Related CN103345743B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310243825.1A CN103345743B (en) 2013-06-18 2013-06-18 A kind of image partition method for battery tail end smart flaw detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310243825.1A CN103345743B (en) 2013-06-18 2013-06-18 A kind of image partition method for battery tail end smart flaw detection

Publications (2)

Publication Number Publication Date
CN103345743A true CN103345743A (en) 2013-10-09
CN103345743B CN103345743B (en) 2016-05-25

Family

ID=49280536

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310243825.1A Expired - Fee Related CN103345743B (en) 2013-06-18 2013-06-18 A kind of image partition method for battery tail end smart flaw detection

Country Status (1)

Country Link
CN (1) CN103345743B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617619A (en) * 2013-12-04 2014-03-05 天津普达软件技术有限公司 Image segmentation method for cup noodles in which forks are thrown through throwing machine
CN103632152A (en) * 2013-12-04 2014-03-12 天津普达软件技术有限公司 Method for detecting forks for drummed instant noodle
CN110136132A (en) * 2019-05-24 2019-08-16 国网河北省电力有限公司沧州供电分公司 Detection method, detection device and the terminal device of equipment heating failure
CN110286126A (en) * 2019-06-17 2019-09-27 浙江大学 A kind of wafer surface defects subregion area detecting method of view-based access control model image
CN110490865A (en) * 2019-08-22 2019-11-22 易思维(杭州)科技有限公司 Stud point cloud segmentation method based on the high light-reflecting property of stud
CN110826571A (en) * 2019-11-01 2020-02-21 云南电网有限责任公司信息中心 Image traversal algorithm for image rapid identification and feature matching
CN110910401A (en) * 2019-10-31 2020-03-24 五邑大学 Semi-automatic image segmentation data annotation method, electronic device and storage medium
CN111563550A (en) * 2020-04-30 2020-08-21 北京百度网讯科技有限公司 Sperm morphology detection method and device based on image technology

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009237614A (en) * 2008-03-25 2009-10-15 Seiko Epson Corp Setting of face area corresponding to face image in target image
CN103134807A (en) * 2011-08-19 2013-06-05 康耐视公司 System and method for identifying defects in a material

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009237614A (en) * 2008-03-25 2009-10-15 Seiko Epson Corp Setting of face area corresponding to face image in target image
CN103134807A (en) * 2011-08-19 2013-06-05 康耐视公司 System and method for identifying defects in a material

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ZHU ZHENTAO等: "Fast Capsule Image Segmentation Based on Linear Region Growing", 《2011 IEEE INTERNATIONAL COMPUTER SCIENCE AND AUTOMATION ENGINEERING》, 12 June 2011 (2011-06-12), pages 99 - 103 *
孙力: "基于ROI与自适应Ostu相结合的图像分割算法", 《现代电子技术》, vol. 34, no. 6, 15 March 2011 (2011-03-15), pages 1 - 3 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617619A (en) * 2013-12-04 2014-03-05 天津普达软件技术有限公司 Image segmentation method for cup noodles in which forks are thrown through throwing machine
CN103632152A (en) * 2013-12-04 2014-03-12 天津普达软件技术有限公司 Method for detecting forks for drummed instant noodle
CN110136132A (en) * 2019-05-24 2019-08-16 国网河北省电力有限公司沧州供电分公司 Detection method, detection device and the terminal device of equipment heating failure
CN110286126A (en) * 2019-06-17 2019-09-27 浙江大学 A kind of wafer surface defects subregion area detecting method of view-based access control model image
CN110286126B (en) * 2019-06-17 2021-09-14 浙江大学 Wafer surface defect regional detection method based on visual image
CN110490865A (en) * 2019-08-22 2019-11-22 易思维(杭州)科技有限公司 Stud point cloud segmentation method based on the high light-reflecting property of stud
CN110490865B (en) * 2019-08-22 2022-04-01 易思维(杭州)科技有限公司 Stud point cloud segmentation method based on high light reflection characteristic of stud
CN110910401A (en) * 2019-10-31 2020-03-24 五邑大学 Semi-automatic image segmentation data annotation method, electronic device and storage medium
CN110826571A (en) * 2019-11-01 2020-02-21 云南电网有限责任公司信息中心 Image traversal algorithm for image rapid identification and feature matching
CN110826571B (en) * 2019-11-01 2023-10-20 云南电网有限责任公司信息中心 Image traversal algorithm for rapid image identification and feature matching
CN111563550A (en) * 2020-04-30 2020-08-21 北京百度网讯科技有限公司 Sperm morphology detection method and device based on image technology
CN111563550B (en) * 2020-04-30 2023-08-25 北京百度网讯科技有限公司 Sperm morphology detection method and device based on image technology

Also Published As

Publication number Publication date
CN103345743B (en) 2016-05-25

Similar Documents

Publication Publication Date Title
CN103345743A (en) Image segmentation method for intelligent flaw detection of cell tail end
CN110084095B (en) Lane line detection method, lane line detection apparatus, and computer storage medium
US10140529B2 (en) Method, apparatus and device for detecting lane lines
CN107045629B (en) Multi-lane line detection method
JP6259928B2 (en) Lane data processing method, apparatus, storage medium and equipment
CN103226834B (en) A kind of image motion target signature point method for fast searching
Yuan et al. Robust lane detection for complicated road environment based on normal map
Gomez et al. Traffic lights detection and state estimation using hidden markov models
Yan et al. A method of lane edge detection based on Canny algorithm
CN107092871B (en) Remote sensing image building detection method based on multiple dimensioned multiple features fusion
WO2018107525A1 (en) Detection method for mold of electric injection molding machine
CN107784652B (en) Tower rapid detection method based on unmanned aerial vehicle image
CN115049700A (en) Target detection method and device
CN113221861B (en) Multi-lane line detection method, device and detection equipment
US9747507B2 (en) Ground plane detection
EP2813973A1 (en) Method and system for processing video image
CN109724988B (en) PCB defect positioning method based on multi-template matching
CN110751619A (en) Insulator defect detection method
CN106327464A (en) Edge detection method
CN108154114B (en) Lane line detection method
CN103942809A (en) Method for detecting joint fissures in rock images
CN103793923A (en) Method and device for acquiring moving object in image
CN104036514A (en) Circle detection method based on histogram peak value search
CN102663781A (en) Sub-pixel level welding center extraction method based on visual sense
Hung et al. Skyline localization for mountain images

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160525

Termination date: 20170618