CN112950623A - Mark identification method and system - Google Patents
Mark identification method and system Download PDFInfo
- Publication number
- CN112950623A CN112950623A CN202110334594.XA CN202110334594A CN112950623A CN 112950623 A CN112950623 A CN 112950623A CN 202110334594 A CN202110334594 A CN 202110334594A CN 112950623 A CN112950623 A CN 112950623A
- Authority
- CN
- China
- Prior art keywords
- image
- printing
- template
- printing image
- template image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000000605 extraction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 239000003550 marker Substances 0.000 claims description 5
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000005764 inhibitory process Effects 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/35—Determination of transform parameters for the alignment of images, i.e. image registration using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30144—Printing quality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a shipping mark identification method, which comprises the following steps: the method comprises the following steps: acquiring a template image corresponding to the shipping mark; step two: processing the template image to form a transparent floating layer image; step three: acquiring an actual printing image corresponding to the shipping mark; step four: extracting the template image and the printing image through features and calculating the similarity; step five: registering the template image and the printing image after the similarity reaches a threshold value; step six: outputting the corrected printing image to be compared with the transparent floating layer image; according to the embodiment of the invention, the image with the highest goodness of fit is output, so that the recognition efficiency and the recognition accuracy are improved, and further the human resources are improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a shipping mark identification method and system.
Background
As the industry develops, large batches of cartons are efficiently manufactured. Therefore, efficiency needs to be improved for product detection (printing objects on the carton), and the traditional manual visual comparison is low in matching degree between the printing objects on the carton and the original design drawing and low in efficiency.
Summary of the invention
In order to overcome the defects of the prior art, the invention provides a mark identification method which is used for solving the technical problems of low identification efficiency and low identification accuracy rate of the traditional manual vision comparison.
The technical scheme adopted by the invention for solving the technical problems is as follows: the mark identification method comprises the following steps:
the method comprises the following steps: acquiring a template image corresponding to the shipping mark;
step two: processing the template image to form a transparent floating layer image;
step three: acquiring an actual printing image corresponding to the shipping mark;
step four: extracting the template image and the printing image through features and calculating the similarity;
step five: registering the template image and the printing image after the similarity reaches a threshold value;
step six: and outputting the corrected printing image to be compared with the transparent floating layer image.
Preferably, the template image is processed to form a transparent float layer image, and the steps include:
and performing edge extraction on the standard image by adopting a Canny operator so as to obtain the transparent floating layer image.
Further preferably, the Canny operator is adopted to perform edge extraction on the standard image so as to obtain the transparent floating layer image, and the step includes:
using a Gaussian filter to smooth the image and filter out noise;
calculating the gradient strength and direction of each pixel point in the standard image, and eliminating stray effect caused by edge detection by applying non-maximum value inhibition;
determining real and potential edges by applying dual threshold detection, and completing edge detection by suppressing isolated weak edges;
after the standard image edges are extracted and shown on the camera to form the transparent float layer image.
Preferably, before acquiring the actual printed image corresponding to the mark, the steps further include:
and transmitting each frame of image captured by the camera to an algorithm operation center for processing in real time at the frequency of 60 frames per second.
Preferably, the template image and the printing image are subjected to feature extraction and similarity calculation, and the steps include:
respectively extracting edge features of the standard image and the printed image by using sobel, and eliminating interference factors by gray level stretching;
selecting an area according to a set threshold value to form two single connected domains;
respectively performing circular expansion and rectangular expansion on the two single connected domains;
and subtracting the pixel points of the two single connected domains after the circular expansion and the rectangular expansion are respectively carried out to obtain the similarity.
Preferably, after the similarity reaches a threshold, the template image and the printing image are registered, the steps including:
extracting feature points and matching the feature points of the printed image and the template image through SIFT + RANSAC;
performing affine matrix calculation on the feature point coordinates of the printing image and the template image according to the feature point coordinates of the printing image and the template image;
converting the printing image matrix and cutting to obtain a cut printing image;
and registering the cut printing image and the template image again in a GMS + ORB mode, and finely adjusting the cut printing image.
Preferably, the output corrected printed image is compared with the transparent relief image, the steps comprising:
and after outputting the corrected printing image through an algorithm operation center, comparing the corrected printing image with the transparent floating layer image.
A marker identification system, the system comprising:
the first acquisition unit is used for acquiring the template image corresponding to the mark;
the processing unit is used for processing the template image to form a transparent floating layer image;
the second acquisition unit is used for acquiring the actual printing image corresponding to the mark;
the extracting unit is used for extracting the characteristics of the template image and the printing image and calculating the similarity;
the registration unit is used for registering the template image and the printing image after the similarity reaches a threshold value;
and the comparison unit is used for outputting the corrected printing image and comparing the corrected printing image with the transparent floating layer image.
The invention has the beneficial effects that: the method comprises the following steps: acquiring a template image corresponding to the shipping mark; step two: processing the template image to form a transparent floating layer image; step three: acquiring an actual printing image corresponding to the shipping mark; step four: extracting the template image and the printing image through features and calculating the similarity; step five: registering the template image and the printing image after the similarity reaches a threshold value; step six: outputting the corrected printing image to be compared with the transparent floating layer image; and the image with the highest goodness of fit is output, so that the recognition efficiency and the recognition accuracy are improved, and further the human resources are improved.
Drawings
Fig. 1 is a schematic flow chart of a shipping mark identification method.
Fig. 2 is a functional block diagram of a shipping mark identification method system.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific implementations of the present invention is provided in conjunction with specific embodiments:
the first embodiment is as follows:
fig. 1 shows an implementation process of a shipping mark identification method according to an embodiment of the present invention, and for convenience of description, only the relevant parts related to the embodiment of the present invention are shown, which are detailed as follows:
in step S101, acquiring a template image corresponding to the shipping mark;
in the embodiment of the application, a user uploads a design manuscript corresponding to a mark from an album through a mobile phone APP (android/IOS terminal) or an applet, the file type includes but is not limited to a picture format, PDF, CAD and the like, and then the design manuscript is automatically converted into a picture according to the corresponding format.
In step S102, processing the template image to form a transparent floating layer image;
preferably, the template image is processed to form a transparent float layer image, and the steps include:
and performing edge extraction on the standard image by adopting a Canny operator so as to obtain the transparent floating layer image.
Further preferably, the Canny operator is adopted to perform edge extraction on the standard image so as to obtain the transparent floating layer image, and the step includes:
using a Gaussian filter to smooth the image and filter out noise;
calculating the gradient strength and direction of each pixel point in the standard image, and eliminating stray effect caused by edge detection by applying non-maximum value inhibition;
determining real and potential edges by applying dual threshold detection, and completing edge detection by suppressing isolated weak edges;
after the standard image edges are extracted and shown on the camera to form the transparent float layer image.
In the embodiment of the application, the Canny operator is not easily interfered by noise, and a real weak edge can be detected.
In step S103, acquiring an actual printing image corresponding to the shipping mark;
preferably, before acquiring the actual printed image corresponding to the mark, the steps further include:
and transmitting each frame of image captured by the camera to an algorithm operation center for processing in real time at the frequency of 60 frames per second.
In step S104, extracting features of the template image and the print image, and calculating a similarity;
preferably, the template image and the printing image are subjected to feature extraction and similarity calculation, and the steps include:
respectively extracting edge features of the standard image and the printed image by using sobel, and eliminating interference factors by gray level stretching;
selecting an area according to a set threshold value to form two single connected domains; where the threshold is used to distinguish whether the template image is similar to the printed image, it is tested by multiple sample tests.
Respectively performing circular expansion and rectangular expansion on the two single connected domains;
and subtracting the pixel points of the two single connected domains after the circular expansion and the rectangular expansion are respectively carried out to obtain the similarity.
In this application embodiment, carry out circular inflation and rectangle inflation respectively to two single connected domains, the tiny hole in the inflation processing can the filling image connects adjacent object to refine image edge structure, make the image structure more clear, the follow-up image of being convenient for is compared, obtains more accurate numerical value.
In step S105, when the similarity reaches a threshold, registering the template image and the printing image;
preferably, after the similarity reaches a threshold, the template image and the printing image are registered, the steps including:
extracting feature points and matching the feature points of the printed image and the template image through SIFT + RANSAC;
performing affine matrix calculation on the feature point coordinates of the printing image and the template image according to the feature point coordinates of the printing image and the template image;
converting the printing image matrix and cutting to obtain a cut printing image;
and registering the cut printing image and the template image again in a GMS + ORB mode, and finely adjusting the cut printing image.
In the embodiment of the application, feature point extraction and feature point matching are performed on the printed image and the template image through SIFT + RANSAC, and the cut printed image and the template image are registered again through GMS + ORB, so that the printed image and the template image can be successfully registered.
In step S106, the corrected printed image is output for comparison with the transparent float layer image.
Preferably, the output corrected printed image is compared with the transparent relief image, the steps comprising:
and after outputting the corrected printing image through an algorithm operation center, comparing the corrected printing image with the transparent floating layer image.
In the embodiment of the application, the output corrected printing image is compared with the transparent floating layer image, so that the size proportion of the current printing image is closer to that of the template image, interference items at the edge part of the printing image are reduced, the influence of the comparison on the result is reduced, and a more accurate detection result is obtained.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by relevant hardware instructed by a program, and the program may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc.
Example two:
fig. 2 shows a structure of a shipping mark identification system according to a second embodiment of the present invention, and for convenience of description, only the parts related to the second embodiment of the present invention are shown, and detailed descriptions are as follows:
the first acquisition unit 201 is used for acquiring a template image corresponding to the mark;
the processing unit 202 is used for processing the template image to form a transparent floating layer image;
the second acquisition unit 203 is used for acquiring the actual printing image corresponding to the mark;
an extracting unit 204, configured to perform feature extraction on the template image and the print image and calculate a similarity;
a registration unit 205, configured to register the template image and the printing image after the similarity reaches a threshold;
and the comparison unit 206 is used for outputting the corrected printing image to be compared with the transparent floating layer image.
In the embodiment of the invention, the method comprises the following steps: acquiring a template image corresponding to the shipping mark; step two: processing the template image to form a transparent floating layer image; step three: acquiring an actual printing image corresponding to the shipping mark; step four: extracting the template image and the printing image through features and calculating the similarity; step five: registering the template image and the printing image after the similarity reaches a threshold value; step six: outputting the corrected printing image to be compared with the transparent floating layer image; and the image with the highest goodness of fit is output, so that the recognition efficiency and the recognition accuracy are improved, and further the human resources are improved. The detailed implementation of each unit can refer to the description of the first embodiment, and is not repeated herein.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation.
Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A mark identification method is characterized by comprising the following steps:
the method comprises the following steps: acquiring a template image corresponding to the shipping mark;
step two: processing the template image to form a transparent floating layer image;
step three: acquiring an actual printing image corresponding to the shipping mark;
step four: extracting the template image and the printing image through features and calculating the similarity;
step five: registering the template image and the printing image after the similarity reaches a threshold value;
step six: and outputting the corrected printing image to be compared with the transparent floating layer image.
2. The marker identification method according to claim 1, wherein the template image is processed to form a transparent floating layer image, and the method comprises the following steps:
and performing edge extraction on the standard image by adopting a Canny operator so as to obtain the transparent floating layer image.
3. The mark recognition method according to claim 2, wherein a Canny operator is adopted to perform edge extraction on the standard image so as to obtain the transparent floating layer image, and the steps comprise:
using a Gaussian filter to smooth the image and filter out noise;
calculating the gradient strength and direction of each pixel point in the standard image, and eliminating stray effect caused by edge detection by applying non-maximum value inhibition;
determining real and potential edges by applying dual threshold detection, and completing edge detection by suppressing isolated weak edges;
after the standard image edges are extracted and shown on the camera to form the transparent float layer image.
4. The shipping mark identification method of claim 3, wherein before acquiring the actual printed image corresponding to the shipping mark, said steps further comprise:
and transmitting each frame of image captured by the camera to an algorithm operation center for processing in real time at the frequency of 60 frames per second.
5. The marker recognition method according to claim 4, wherein the template image and the printing image are subjected to feature extraction and similarity calculation, and the method comprises the following steps:
respectively extracting edge features of the standard image and the printed image by using sobel, and eliminating interference factors by gray level stretching;
selecting an area according to a set threshold value to form two single connected domains;
respectively performing circular expansion and rectangular expansion on the two single connected domains;
and subtracting the pixel points of the two single connected domains after the circular expansion and the rectangular expansion are respectively carried out to obtain the similarity.
6. The marker identification method according to claim 5, wherein after the similarity reaches a threshold value, the template image and the printing image are registered, and the steps comprise:
extracting feature points and matching the feature points of the printed image and the template image through SIFT + RANSAC;
performing affine matrix calculation on the feature point coordinates of the printing image and the template image according to the feature point coordinates of the printing image and the template image;
converting the printing image matrix and cutting to obtain a cut printing image;
and registering the cut printing image and the template image again in a GMS + ORB mode, and finely adjusting the cut printing image.
7. A Mark identification method as claimed in claim 6, wherein the output corrected printed image is compared with the transparent float layer image, the steps comprising:
and after outputting the corrected printing image through an algorithm operation center, comparing the corrected printing image with the transparent floating layer image.
8. A marker identification system, characterized in that, the system includes:
the first acquisition unit is used for acquiring the template image corresponding to the mark;
the processing unit is used for processing the template image to form a transparent floating layer image;
the second acquisition unit is used for acquiring the actual printing image corresponding to the mark;
the extracting unit is used for extracting the characteristics of the template image and the printing image and calculating the similarity;
the registration unit is used for registering the template image and the printing image after the similarity reaches a threshold value;
and the comparison unit is used for outputting the corrected printing image and comparing the corrected printing image with the transparent floating layer image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110334594.XA CN112950623A (en) | 2021-03-29 | 2021-03-29 | Mark identification method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110334594.XA CN112950623A (en) | 2021-03-29 | 2021-03-29 | Mark identification method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112950623A true CN112950623A (en) | 2021-06-11 |
Family
ID=76227314
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110334594.XA Pending CN112950623A (en) | 2021-03-29 | 2021-03-29 | Mark identification method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112950623A (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11282960A (en) * | 1998-03-31 | 1999-10-15 | Ricoh Co Ltd | Industrial character recognition method |
US20120000592A1 (en) * | 2010-07-01 | 2012-01-05 | Sagent Pharmaceuticals, Inc. | Label, labeling system and method of labeling for containers for drug products |
CN103606220A (en) * | 2013-12-10 | 2014-02-26 | 江苏国光信息产业股份有限公司 | Check printed number recognition system and check printed number recognition method based on white light image and infrared image |
KR101409340B1 (en) * | 2013-03-13 | 2014-06-20 | 숭실대학교산학협력단 | Method for traffic sign recognition and system thereof |
CN104333696A (en) * | 2014-11-19 | 2015-02-04 | 北京奇虎科技有限公司 | View-finding processing method, view-finding processing device and client |
CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
CN106338520A (en) * | 2016-09-18 | 2017-01-18 | 南京林业大学 | Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board |
US20170017862A1 (en) * | 2014-03-14 | 2017-01-19 | Omron Corporation | Image recognition device, image sensor, and image recognition method |
CN106846317A (en) * | 2017-02-27 | 2017-06-13 | 北京连心医疗科技有限公司 | A kind of feature based extracts the method for retrieving medicine image with Similarity matching |
CN206441190U (en) * | 2017-01-18 | 2017-08-25 | 东莞市麦仕满机电有限公司 | A kind of trade mark shipping mark (shipping mark, print mark) intelligent identification detection system |
CN108805862A (en) * | 2018-05-02 | 2018-11-13 | 南京大学 | A kind of tag discrimination methods based on improved structure similarity |
CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
CN111340134A (en) * | 2020-03-11 | 2020-06-26 | 南京理工大学 | Rapid template matching method based on local dynamic warping |
CN111650220A (en) * | 2020-07-15 | 2020-09-11 | 博科视(苏州)技术有限公司 | Vision-based image-text defect detection method |
CN112184781A (en) * | 2020-09-14 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Method, device and equipment for registering ultrasonic image and CT image |
-
2021
- 2021-03-29 CN CN202110334594.XA patent/CN112950623A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11282960A (en) * | 1998-03-31 | 1999-10-15 | Ricoh Co Ltd | Industrial character recognition method |
US20120000592A1 (en) * | 2010-07-01 | 2012-01-05 | Sagent Pharmaceuticals, Inc. | Label, labeling system and method of labeling for containers for drug products |
KR101409340B1 (en) * | 2013-03-13 | 2014-06-20 | 숭실대학교산학협력단 | Method for traffic sign recognition and system thereof |
CN103606220A (en) * | 2013-12-10 | 2014-02-26 | 江苏国光信息产业股份有限公司 | Check printed number recognition system and check printed number recognition method based on white light image and infrared image |
US20170017862A1 (en) * | 2014-03-14 | 2017-01-19 | Omron Corporation | Image recognition device, image sensor, and image recognition method |
CN104333696A (en) * | 2014-11-19 | 2015-02-04 | 北京奇虎科技有限公司 | View-finding processing method, view-finding processing device and client |
CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
CN106338520A (en) * | 2016-09-18 | 2017-01-18 | 南京林业大学 | Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board |
CN206441190U (en) * | 2017-01-18 | 2017-08-25 | 东莞市麦仕满机电有限公司 | A kind of trade mark shipping mark (shipping mark, print mark) intelligent identification detection system |
CN106846317A (en) * | 2017-02-27 | 2017-06-13 | 北京连心医疗科技有限公司 | A kind of feature based extracts the method for retrieving medicine image with Similarity matching |
CN108805862A (en) * | 2018-05-02 | 2018-11-13 | 南京大学 | A kind of tag discrimination methods based on improved structure similarity |
CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
CN111340134A (en) * | 2020-03-11 | 2020-06-26 | 南京理工大学 | Rapid template matching method based on local dynamic warping |
CN111650220A (en) * | 2020-07-15 | 2020-09-11 | 博科视(苏州)技术有限公司 | Vision-based image-text defect detection method |
CN112184781A (en) * | 2020-09-14 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Method, device and equipment for registering ultrasonic image and CT image |
Non-Patent Citations (4)
Title |
---|
BBUF: "OpenCV图像处理专栏十九 | 手动实现基于Canny算子的边缘检测", pages 1 - 7, Retrieved from the Internet <URL:《https://cloud.tencent.com/developer/article/1601622》> * |
DANIEL B. RUSSAKOFF 等: "Image Similarity Using Mutual Information of Regions", 《EUROPEAN CONFERENCE ON COMPUTER VISION》, 31 December 2004 (2004-12-31), pages 596 - 607 * |
张志佳 等: "基于AT-SBTM的交通标志检测", 《计算机技术与发展》, vol. 27, no. 08, 31 August 2017 (2017-08-31), pages 195 - 199 * |
胡占奇: "基于车牌字母数字结构分析的车牌识别算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 08, 15 August 2010 (2010-08-15), pages 138 - 613 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11797886B2 (en) | Image processing device, image processing method, and image processing program | |
CN109919160B (en) | Verification code identification method, device, terminal and storage medium | |
CN109752392B (en) | PCB defect type detection system and method | |
CN115908269B (en) | Visual defect detection method, visual defect detection device, storage medium and computer equipment | |
CN112183038A (en) | Form identification and typing method, computer equipment and computer readable storage medium | |
CN115205223B (en) | Visual inspection method and device for transparent object, computer equipment and medium | |
CN114022403A (en) | Method and device for detecting defects of display panel | |
CN112614062A (en) | Bacterial colony counting method and device and computer storage medium | |
CN104615972B (en) | Intelligent identification method and device for pointer instrument | |
CN108460388B (en) | Method and device for detecting positioning mark and computer readable storage medium | |
CN112308872A (en) | Image edge detection method based on multi-scale Gabor first-order derivative | |
CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
CN114170613A (en) | Image detection method and device, electronic equipment and computer readable storage medium | |
CN113221897B (en) | Image correction method, image text recognition method, identity verification method and device | |
CN112215827A (en) | Electromigration region detection method and device, computer equipment and storage medium | |
CN111340040A (en) | Paper character recognition method and device, electronic equipment and storage medium | |
CN112950623A (en) | Mark identification method and system | |
CN113298803B (en) | Magnet piece detection method, system, equipment and computer readable storage medium | |
CN110188601B (en) | Airport remote sensing image detection method based on learning | |
CN109215068B (en) | Image magnification measuring method and device | |
CN112528741B (en) | State identification method and device for transformer substation pressure plate | |
CN113255657B (en) | Method and device for detecting scratch on bill surface, electronic equipment and machine-readable medium | |
CN115984316B (en) | Industrial image edge extraction method and device for complex environment | |
CN107392205B (en) | Code value table generation method and device of remote controller |
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 |