CN109101854A - A kind of multiple barcode localization method - Google Patents
A kind of multiple barcode localization method Download PDFInfo
- Publication number
- CN109101854A CN109101854A CN201810660166.4A CN201810660166A CN109101854A CN 109101854 A CN109101854 A CN 109101854A CN 201810660166 A CN201810660166 A CN 201810660166A CN 109101854 A CN109101854 A CN 109101854A
- Authority
- CN
- China
- Prior art keywords
- image
- point
- gradient
- barcode
- value
- 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 32
- 230000004807 localization Effects 0.000 title description 8
- 238000003708 edge detection Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract 3
- 230000008859 change Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 14
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1452—Methods for optical code recognition including a method step for retrieval of the optical code detecting bar code edges
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了一种多条形码定位方法，具体步骤包括：(1)对所检测的图像进行预处理，获得二值化图像；(2)对二值化图像中的外接矩形进行边缘检测，获得多个矩形的位置；(3)通过条形码判断，选取符合条件的矩形；(4)对选取的最小外接矩形确定角度并进行角度修正，实现条形码的正立；(5)对条形码正立后的矩形进行排序处理，在条形码码制一致的情况下，得到排序后的含有条形码的多个矩形区域，完成条形码的定位。本发明在一次测量中能够获得多个条码的定位，可以大大加快整个物流速度，从而达到了提升效率的目的。
The invention discloses a multi-barcode positioning method. The specific steps include: (1) preprocessing the detected image to obtain a binarized image; (2) performing edge detection on a circumscribed rectangle in the binarized image to obtain The position of multiple rectangles; (3) judge by the barcode, select the rectangle that meets the conditions; (4) determine the angle of the selected minimum circumscribed rectangle and correct the angle to realize the uprightness of the barcode; (5) right upright the barcode Rectangles are sorted, and in the case of consistent barcode codes, multiple sorted rectangular areas containing barcodes are obtained to complete the positioning of barcodes. The present invention can obtain the positioning of multiple barcodes in one measurement, can greatly speed up the entire logistics speed, and thus achieves the purpose of improving efficiency.
Description
Technical field
The present invention relates to the field of image processings such as the positioning of bar codes multiple in image, cutting, angle rotation, more particularly to
A kind of multiple barcode localization method.
Background technique
In today that logistic industry rapidly develops, the design of express delivery list has obtained different degrees of change according to various demands
Into but due to there is no national standard, causing the pattern of the express delivery list of every logistics company different, and specification has very big to go out
Enter, including the difference of barcode position, Aspect Ratio is different and Barcode Length is different.
Image processing techniques began to be applied from the 1950s, had been deep into daily life till now
Every aspect.Image technique content very abundant, including image acquisition, image compression, image storage and transmission, image
Transformation, image synthesis, image enhancement, image restoration and reconstruction, image segmentation, target detection, image indicate to match with description, image
Quasi-, image classification and identification, image understanding, scene analysis and understanding, the foundation of image data base, index and retrieval and synthesis
It utilizes.In field of image recognition, the orientation problem for target is always the emphasis in identification problem, and accurately positioning can
To effectively improve recognition efficiency.Framing algorithm is then the area for positioning bar code by all means in the picture at present
Domain, to cooperate subsequent algorithm to achieve the purpose that identify contained content in image.It must in almost all problem of image recognition
The problem of so encountering, the solution of the problem then need to divide identification object, and the wherein identification of text class is then
Recent big heat discusses object.It is studied according to the geometry of identified object or wave character, to obtain object
Feature, that is, the basic procedure of pattern-recognition.The completion of positioning is to have obtained the performance of target object feature, so positioning
Also it just needs to study target signature.
Detection for bar code, it is natural that positioning, which is that basis is also important step the most, to be realized to bar code, to bar shaped
The automatic detection of code is to realize the most important thing of bar code identification system.Research of the domestic many experts and scholars for bar code
It is more and more deep, many effective detection methods are proposed, for example carry out analyzing and positioning by the textural characteristics in image, again
The detection after frequency domain variation is either carried out, there are also Mathematical Morphology Method, gradient algorithm is used, is also had by dividing image
The method for being cut into boxed area to detect.Although there are many algorithms to be able to carry out a degree of detection and localization, or
Mostly or less still there are some problems.Substantially show following several aspects: algorithm first is easy under more complicated background
It is mixed with background generation, it is not easy to distinguish；Another is exactly that many algorithms can not complete multiple bar shapeds in a width picture
The detection of code.
Summary of the invention
The purpose of the present invention is to provide a kind of multiple barcode localization methods.The present invention to have the image of multiple bar codes into
Row edge detection, to obtain the region of rectangle by Edge Search, and the sequence of the edge data by judging rectangle obtains institute
The multiple the barcode size or text fields needed realize bar code positioning.The present invention is same by the carry out to multiple bar codes in an image
When identification come speed up processing.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of multiple barcode localization method, specific steps include:
(1) image detected is pre-processed, obtains binary image；
(2) edge detection is carried out to the boundary rectangle in binary image, obtains the position of multiple rectangles；
(3) judged by bar code, choose qualified rectangle；
(4) angle is determined to the minimum circumscribed rectangle of selection and carries out angle modification, realize the upright of bar code；
(5) processing is ranked up to rectangle of the bar code after upright, under bar code symbologies unanimous circumstances, is sorted
Multiple rectangular areas containing bar code afterwards, complete the positioning of bar code.
Further, the pretreatment in the step (1), specific steps include:
1) image is become into grayscale image from cromogram using the color gamut conversion of weighted mean method；
2) denoising is carried out to resulting grayscale image by Wiener filtering；
3) method of Otsu method (big law) as threshold process is chosen, grayscale image is further converted into binary picture
Picture.
Specifically, the step of edge detection in step (2) is divided into four filtering, enhancing, detection and positioning parts.And
The cardinal principle of edge detection algorithm is single order and second dervative based on image intensity.
Further, before carrying out edge detection, it is necessary to Gradient Features extraction is carried out to image, specifically:
Possess the gradient vector with size and Orientation at the image function midpoint f (x, y) (x, y) of the invention, if
There are two gradient component G with tool on the direction y in the x direction for itxAnd Gy, then the gradient vector at this can indicate are as follows:
The value of gradient are as follows:
Deflection are as follows:
Processing to digital picture should be equivalent to and seek gradient to two-dimensional discrete function, so having:
Wherein:
It is calculated to simplify, the value of gradient is simplified are as follows:
When x-axis and y-axis rotate, right angled triangle is since the length of bevel edge will not change, so two right angles
The length on side will necessarily just change, that is,Value can change.
It preferably, is Sobel operator used in the edge detection of the step (2), Sobel operator is a kind of single order
The gradient value of pixel close region is utilized to calculate the gradient of everywhere pixel, then according to certain threshold value in differential operator
Further value is carried out, to realize edge detection；For the template (z of a 3x31-z9), calculation method is as follows:
Specifically, in the step (3), after detecting the edge of target shape, the wheel by tracking object is needed
Exterior feature carries out profile orderings to shape, is generally divided into the tracking of 4 directions according to the neighbouring relations of pixel and 8 directions track, main
Step are as follows:
1) select starting point: it is that the smallest point as start bit that row coordinate in sharp point and column, which are sat target value all,
It sets.Start position is searched by way of scanning to target image, is progressively scanned according to sequence from left to right from top to bottom, when
When looking for first position of minimum row train value, if the point does not track the label symbol of end, which can be determined
For the boundary starting point of profile, it is denoted as A0, and there are in profile list structure by its coordinate value.
2) profile is searched: from starting point A0It sets out, the order priority judgement in neighborhood direction is carried out along the point, according to from small
To big principle.Then judge whether the consecutive points are boundary points by edge judgment criterion, if meeting criterion, by secondary phase
A is denoted as in the coordinate deposit profile chained list of adjoint pointn(n=1,2,3 ...), then by AnAgain it is set as current outline point, then to look into
Look for An+1, it is deposited into profile chained list, continues next direction and search.And so on, find all profile points and structure
At profile.
Specifically, in the step (4), come to carry out angle really to minimum circumscribed rectangle by using hough transformation
It is fixed.
The present invention compared to the prior art, have it is below the utility model has the advantages that
1, the present invention can realize the positioning of multiple bar codes in a figure, can only once identify one compared to existing
Infrared laser scanning means, it is clear that have higher efficiency.
2, the camera that the present invention uses is that common camera is cheap, and required configuration level is lower.
3, the algorithm comparison that uses of the present invention is simple, so that recognition speed only within 1.5s, absolutely meets industrial requirements.
Detailed description of the invention
Fig. 1 is the bar code positioning flow figure in the present invention based on Image Edge-Detection feature；
Fig. 2 is the binary image obtained after pretreatment in the present invention；
Fig. 3 is the image in the present invention after rectangular area detection and bar code content detection.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment
It is as shown in Figure 1 a kind of specific flow chart of bar code localization method based on Image Edge-Detection feature, it is described
The step of method includes:
(1) image detected is pre-processed, obtains binary image.
Pre-treatment step in the step (1), specifically includes:
1) image is become into grayscale image from cromogram using the color gamut conversion of weighted mean method；
2) denoising is carried out to resulting grayscale image by Wiener filtering；
3) method of Otsu method (big law) as threshold process is chosen, grayscale image is further converted into binary picture
Picture.
The black and white binary image that image obtains after pretreatment is as shown in Figure 2.
(2) edge detection is carried out to the boundary rectangle in binary image, obtains the position of multiple rectangles；
By carrying out edge detection to region in figure, detection identification is carried out to all edges.To obtain n rectangle region
Domain carries out the setting of length-width ratio and elongated range to n rectangular area, removes excessive and too small rectangle, filters out and meet
The rectangular area of bar code shape, number m.
Specifically, the step of edge detection in step (2) is divided into four filtering, enhancing, detection and positioning parts.And
The cardinal principle of edge detection algorithm is single order and second dervative based on image intensity.
Before carrying out edge detection, it is necessary to Gradient Features extraction is carried out to image, specifically:
Possess the gradient vector with size and Orientation at the image function midpoint f (x, y) (x, y) of the invention, if
There are two gradient component G with tool on the direction y in the x direction for itxAnd Gy, then the gradient vector at this can indicate are as follows:
The value of gradient are as follows:
Deflection are as follows:
Processing to digital picture should be equivalent to and seek gradient to two-dimensional discrete function, so having:
Wherein:
It is calculated to simplify, the value of gradient is simplified are as follows:
When x-axis and y-axis rotate, right angled triangle is since the length of bevel edge will not change, so two right angles
The length on side will necessarily just change, that is,Value can change.
It preferably, is Sobel operator used in the edge detection of the step (2), Sobel operator is a kind of single order
The gradient value of pixel close region is utilized to calculate the gradient of everywhere pixel, then according to certain threshold value in differential operator
Further value is carried out, to realize edge detection；For the template (z of a 3x31-Z9), calculation method is as follows:
After above-mentioned edge detection, acquisition is rectangular area, as shown in the region in the thick frame of grey in Fig. 3,
Wherein, 9 n, m 4.
(3) judged by bar code, choose qualified rectangle；
In the step (3), after detecting the edge of target shape, the profile by tracking object is needed, to shape
Shape carries out profile orderings, is generally divided into the tracking of 4 directions according to the neighbouring relations of pixel and 8 directions track, key step are as follows:
1) select starting point: it is that the smallest point as start bit that row coordinate in sharp point and column, which are sat target value all,
It sets.Start position is searched by way of scanning to target image, is progressively scanned according to sequence from left to right from top to bottom, when
When looking for first position of minimum row train value, if the point does not track the label symbol of end, which can be determined
For the boundary starting point of profile, it is denoted as A0, and there are in profile list structure by its coordinate value.
2) profile is searched: from starting point A0It sets out, the order priority judgement in neighborhood direction is carried out along the point, according to from small
To big principle.Then judge whether the consecutive points are boundary points by edge judgment criterion, if meeting criterion, by secondary phase
A is denoted as in the coordinate deposit profile chained list of adjoint pointn(n=1,2,3 ...), then by AnAgain it is set as current outline point, then to look into
Look for An+1, it is deposited into profile chained list, continues next direction and search.And so on, find all profile points and structure
At profile.
Contour detecting is carried out to the fringe region in figure by Freeman chain code edge in the present embodiment, what is obtained contains
There is the rectangular area of bar code as shown in the content in the thick frame of black in Fig. 3.
(4) angle is determined to the minimum circumscribed rectangle of selection and carries out angle modification, realize the upright of bar code；
There is certain angle tilts for bar code as shown in Figure 3, contain according in the image detected in step (3)
There is the rectangular area of bar code, obtains the tilt angle of image using hough angular transformation to m region, by angle change,
Obtain upright bar code rectangular image.Thus the foundation as judgement identification carries out content detection, to obtain containing upright
The rectangular area k of bar code.
(5) processing is ranked up to rectangle of the bar code after upright, under bar code symbologies unanimous circumstances, is sorted
Multiple rectangular areas containing bar code afterwards, complete the positioning of bar code.
According to the k rectangular area that step (4) obtains, to k region using the method that side length sorts can be obtained containing
The maximum area rectangular area of bar code necessarily has the maximum region of area to the detection of bar code situation in figure, by right
Area is compared, and is obtained the maximum preceding S of area, is further screened using length-width ratio, the barcode size or text field is obtained, thus complete
At the localization process of multiple barcode.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810660166.4A CN109101854A (en) | 2018-06-25 | 2018-06-25 | A kind of multiple barcode localization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810660166.4A CN109101854A (en) | 2018-06-25 | 2018-06-25 | A kind of multiple barcode localization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109101854A true CN109101854A (en) | 2018-12-28 |
Family
ID=64844950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810660166.4A Pending CN109101854A (en) | 2018-06-25 | 2018-06-25 | A kind of multiple barcode localization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101854A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918961A (en) * | 2019-02-21 | 2019-06-21 | 华南理工大学 | A Barcode Location Method Based on Image Features |
| CN110021024A (en) * | 2019-03-14 | 2019-07-16 | 华南理工大学 | A kind of image partition method based on LBP and chain code technology |
| CN111504608A (en) * | 2019-01-31 | 2020-08-07 | 中强光电股份有限公司 | Brightness uniformity detection system and brightness uniformity detection method |
| CN111582000A (en) * | 2019-02-19 | 2020-08-25 | 中科院微电子研究所昆山分所 | Bar code positioning method and device and related equipment |
| CN111783493A (en) * | 2020-06-18 | 2020-10-16 | 福州富昌维控电子科技有限公司 | Identification method and identification terminal for batch two-dimensional codes |
| CN111950315A (en) * | 2020-10-19 | 2020-11-17 | 江苏理工学院 | A method, device and storage medium for segmentation and identification of multiple barcode images |
| CN112907612A (en) * | 2021-03-31 | 2021-06-04 | 深圳市华汉伟业科技有限公司 | Bar code region positioning method and image rectangular region fitting method |
| CN113393430A (en) * | 2021-06-09 | 2021-09-14 | 东方电气集团科学技术研究院有限公司 | Thermal imaging image enhancement training method and device for fan blade defect detection |
| CN114913367A (en) * | 2022-04-25 | 2022-08-16 | 广州虎牙科技有限公司 | Image detection model training method, image detection device, electronic equipment and storage medium |
| CN115294121A (en) * | 2022-10-08 | 2022-11-04 | 南通有来信息技术有限公司 | Bar code defect detection method based on logistics label |
| WO2024164581A1 (en) * | 2023-02-07 | 2024-08-15 | 杭州晟元数据安全技术股份有限公司 | Multi-code decoding method and system based on gradient algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7286695B2 (en) * | 1996-07-10 | 2007-10-23 | R2 Technology, Inc. | Density nodule detection in 3-D digital images |
| CN106485183A (en) * | 2016-07-14 | 2017-03-08 | 深圳市华汉伟业科技有限公司 | A kind of Quick Response Code localization method and system |
-
2018
- 2018-06-25 CN CN201810660166.4A patent/CN109101854A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7286695B2 (en) * | 1996-07-10 | 2007-10-23 | R2 Technology, Inc. | Density nodule detection in 3-D digital images |
| CN106485183A (en) * | 2016-07-14 | 2017-03-08 | 深圳市华汉伟业科技有限公司 | A kind of Quick Response Code localization method and system |
Non-Patent Citations (3)
| Title |
|---|
| 王祥敏: ""复杂背景下条码识别技术研究"", 《中国优秀硕士学位论文全文数据库》 * |
| 陈俊名: ""复杂背景下一维条形码定位算法研究"", 《中国优秀硕士学位论文全文数据库》 * |
| 魏文超: ""嵌入式平台下 PDF417 条码识别的研究与实现"", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111504608A (en) * | 2019-01-31 | 2020-08-07 | 中强光电股份有限公司 | Brightness uniformity detection system and brightness uniformity detection method |
| CN111582000B (en) * | 2019-02-19 | 2023-09-12 | 中科微至科技股份有限公司 | Bar code positioning method, bar code positioning device and related equipment |
| CN111582000A (en) * | 2019-02-19 | 2020-08-25 | 中科院微电子研究所昆山分所 | Bar code positioning method and device and related equipment |
| CN109918961B (en) * | 2019-02-21 | 2021-03-30 | 华南理工大学 | Barcode positioning method based on image characteristics |
| CN109918961A (en) * | 2019-02-21 | 2019-06-21 | 华南理工大学 | A Barcode Location Method Based on Image Features |
| CN110021024A (en) * | 2019-03-14 | 2019-07-16 | 华南理工大学 | A kind of image partition method based on LBP and chain code technology |
| CN110021024B (en) * | 2019-03-14 | 2023-12-26 | 华南理工大学 | Image segmentation method based on LBP and chain code technology |
| CN111783493A (en) * | 2020-06-18 | 2020-10-16 | 福州富昌维控电子科技有限公司 | Identification method and identification terminal for batch two-dimensional codes |
| CN111950315B (en) * | 2020-10-19 | 2023-11-07 | 江苏理工学院 | Method, device and storage medium for segmenting and identifying multiple bar code images |
| CN111950315A (en) * | 2020-10-19 | 2020-11-17 | 江苏理工学院 | A method, device and storage medium for segmentation and identification of multiple barcode images |
| CN112907612A (en) * | 2021-03-31 | 2021-06-04 | 深圳市华汉伟业科技有限公司 | Bar code region positioning method and image rectangular region fitting method |
| CN112907612B (en) * | 2021-03-31 | 2025-02-28 | 深圳市华汉伟业科技有限公司 | A method for locating a barcode area and a method for fitting a rectangular area of an image |
| CN113393430A (en) * | 2021-06-09 | 2021-09-14 | 东方电气集团科学技术研究院有限公司 | Thermal imaging image enhancement training method and device for fan blade defect detection |
| CN114913367A (en) * | 2022-04-25 | 2022-08-16 | 广州虎牙科技有限公司 | Image detection model training method, image detection device, electronic equipment and storage medium |
| CN115294121A (en) * | 2022-10-08 | 2022-11-04 | 南通有来信息技术有限公司 | Bar code defect detection method based on logistics label |
| WO2024164581A1 (en) * | 2023-02-07 | 2024-08-15 | 杭州晟元数据安全技术股份有限公司 | Multi-code decoding method and system based on gradient algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109101854A (en) | A kind of multiple barcode localization method | |
| Kumar et al. | A detailed review of feature extraction in image processing systems | |
| Wang et al. | AprilTag 2: Efficient and robust fiducial detection | |
| CN106845372B (en) | A ship target detection and recognition method and system for spaceborne remote sensing optical images | |
| CN105046252B (en) | A kind of RMB prefix code recognition methods | |
| Sirmacek et al. | Urban-area and building detection using SIFT keypoints and graph theory | |
| CN104463795B (en) | A kind of dot matrix DM image in 2 D code processing method and processing device | |
| CN110598690A (en) | End-to-end optical character detection and identification method and system | |
| CN104732183A (en) | One-dimensional barcode identification method based on image sampling line grey scale information analysis | |
| Rosenfeld | Image pattern recognition | |
| Thompson et al. | Description and retrieval of geometric patterns on surface meshes using an edge-based LBP approach | |
| CN102254144A (en) | Robust method for extracting two-dimensional code area in image | |
| CN107563380A (en) | A kind of vehicle license plate detection recognition method being combined based on MSER and SWT | |
| CN110021024A (en) | A kind of image partition method based on LBP and chain code technology | |
| CN108563984A (en) | A Method for Automatic Recognition and Understanding of Process Model Diagram | |
| Bodnár et al. | Improving barcode detection with combination of simple detectors | |
| CN108009538A (en) | A kind of automobile engine cylinder-body sequence number intelligent identification Method | |
| US20230367983A1 (en) | Decoding of two-dimensional barcodes under unfavorable conditions | |
| CN115331245A (en) | A table structure recognition method based on image instance segmentation | |
| CN117392024A (en) | Certificate photo-beauty method based on image segmentation technology | |
| Bodnár et al. | A novel method for barcode localization in image domain | |
| Giri | Text information extraction and analysis from images using digital image processing techniques | |
| CN119048837A (en) | Method, system, equipment and medium for detecting defects of PCB (printed circuit board) components | |
| CN113538404A (en) | Cover plate glass defect detection method and system based on anchor point selection | |
| CN118071831A (en) | Image coarse positioning method, device and computer readable storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181228 |
|
| WD01 | Invention patent application deemed withdrawn after publication |