CN107423653B - Two-dimensional code preprocessing method, system and decoding method - Google Patents
Two-dimensional code preprocessing method, system and decoding method Download PDFInfo
- Publication number
- CN107423653B CN107423653B CN201710548082.7A CN201710548082A CN107423653B CN 107423653 B CN107423653 B CN 107423653B CN 201710548082 A CN201710548082 A CN 201710548082A CN 107423653 B CN107423653 B CN 107423653B
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- image
- threshold value
- target image
- blocks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- 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
-
- 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
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
- G06K7/1491—Methods for optical code recognition the method including quality enhancement steps the method including a reconstruction step, e.g. stitching two pieces of bar code together to derive the full bar code
Abstract
The invention discloses a two-dimensional code preprocessing method, a system and a decoding method, wherein the two-dimensional code preprocessing method comprises the steps of carrying out image binarization; dividing the image into rectangular blocks; judging whether the two-dimensional code is contained and marked by blocks; iteratively expanding the two-dimensional code area according to the marks and calculating the reliability; judging whether the image contains the two-dimensional code according to the reliability, and outputting an effective area of the two-dimensional code, so as to identify whether the target image contains the two-dimensional code in advance; on the basis, the two-dimension code area in the target image can be cut, and then the cut two-dimension code area is analyzed, so that the decoding speed of the two-dimension code can be greatly improved.
Description
Technical Field
The invention relates to a coding processing technology, in particular to a two-dimensional code identification technology.
Background
Two-dimensional codes are also called QR codes, and QR is called Quick Response, which is an ultra-popular coding mode on mobile equipment in recent years, and can store more information and represent more data types than traditional Bar Code Bar codes.
The two-dimensional bar code/two-dimensional code (2-dimensional bar code) records data symbol information by using black and white alternate graphs which are distributed on a plane (two-dimensional direction) according to a certain rule by using a certain specific geometric figure; the concept of '0' and '1' bit stream which forms the internal logic base of computer is skillfully utilized in coding, a plurality of geometric shapes corresponding to binary system are used for representing literal numerical information, and the information is automatically read by an image input device or an optoelectronic scanning device so as to realize the automatic processing of the information: it has some commonality of barcode technology: each code system has its specific character set; each character occupies a certain width; has certain checking function and the like. Meanwhile, the method also has the function of automatically identifying information of different rows and processing the graph rotation change points.
For the identification of two-dimensional codes, the prior art determines the existence of two-dimensional codes by searching a position detection pattern and a positioning pattern in the whole image. Because the proportion of the position detection graph and the positioning graph in the whole image is very small, and operations such as rotation correction, inclination correction, distortion correction and the like of the image can be involved, the method occupies a long time in the two-dimensional code identification stage and consumes system resources.
Therefore, the existing two-dimensional code identification technology has the problems of high hardware consumption and low decoding speed in the actual use process, and the phenomenon of low decoding speed on a middle and low-end processor platform is more obvious.
Therefore, the two-dimensional code identification technology with low hardware consumption and high decoding speed is an urgent problem to be solved in the field.
Disclosure of Invention
Aiming at the problem of slow decoding speed of the existing two-dimensional code identification technology, a quick two-dimensional code decoding technology is needed.
Therefore, the technical problem to be solved by the present invention is to provide a two-dimensional code preprocessing method, system and decoding method.
In order to solve the technical problem, the two-dimensional code preprocessing method provided by the invention comprises the following steps:
carrying out image binarization;
dividing the image into rectangular blocks;
judging whether the two-dimensional code is contained and marked by blocks;
iteratively expanding the two-dimensional code area according to the marks and calculating the reliability;
and judging whether the image contains the two-dimensional code according to the reliability, and outputting an effective area of the two-dimensional code.
Further, in the image binarization processing, a threshold value for the binarization of the gray level image is calculated by an iterative algorithm, and the image is binarized according to the threshold value.
Further, the iterative calculation process of the threshold value for binarization includes:
calculating histogram data of the image;
calculating a minimum non-zero value and a maximum non-zero value in the histogram data, taking the minimum non-zero value as an initial threshold value, taking an average value of the minimum non-zero value and the initial threshold value as an initial new threshold value, and judging whether the minimum non-zero value and the maximum non-zero value are equal;
when the two gray values are not equal, the histogram is divided into two parts according to the initial new threshold value, the average gray value is respectively calculated, and the average value of the two average gray values is used as the new threshold value.
Further, the block judgment includes:
polling each rectangular block, and calculating whether the black-white pixel ratio of each rectangular block meets the condition;
quartering the rectangular blocks meeting the conditions, and judging whether the four sub-blocks meet preset conditions or not; if yes, marking the two-dimension code as a two-dimension code effective area;
and accumulating the credibility of each continuous 2 x 2 blocks of rectangular blocks marked as the valid areas of the two-dimensional codes.
Further, 3 x 3 blocks of rectangular blocks in the credibility region are expanded to form a two-dimensional code effective region until the current credibility is equal to the previous credibility.
In order to solve the above technical problem, the two-dimensional code decoding preprocessing system provided by the present invention includes:
the image binarization module is used for carrying out binarization processing on the target image;
the image segmentation rectangular blocks are used for segmenting a plurality of rectangular blocks of the binarized target image;
the block judgment and marking module is used for judging whether each rectangular block contains the two-dimensional code and marking;
the effective area expansion module is used for iteratively expanding the two-dimensional code area according to the mark and calculating the reliability;
and the output module is used for judging whether the image contains the two-dimensional code or not according to the credibility and outputting the effective area of the two-dimensional code.
In order to solve the technical problem, the two-dimensional code decoding method provided by the invention identifies whether the target image contains the two-dimensional code in advance through the two-dimensional code preprocessing method, cuts the two-dimensional code area in the target image, and then analyzes the cut two-dimensional code area.
When the preprocessing and decoding scheme of the two-dimensional code is specifically implemented, the hardware consumption is low, the decoding speed is greatly improved, and the effect on a middle and low-end processor platform is remarkable.
Drawings
The invention is further described below in conjunction with the appended drawings and the detailed description.
FIG. 1 is a flow chart of the two-dimensional code preprocessing performed in the present embodiment;
FIG. 2 is a flow chart of image binarization in the two-dimensional code preprocessing process according to the scheme;
FIG. 3 is a flow chart of block judgment in the two-dimensional code preprocessing process according to the present embodiment;
FIG. 4 is a flowchart of expanding an effective area in the two-dimensional code preprocessing process according to the present embodiment;
FIG. 5 is a schematic diagram of the two-dimensional code decoding preprocessing system according to the present embodiment;
FIG. 6 is an exemplary diagram of an original image in an embodiment of the present invention;
FIG. 7 is an exemplary diagram of an image after binarization in an embodiment of the present invention;
FIG. 8 is a diagram illustrating segmentation of a binarized image according to an embodiment of the present invention;
FIG. 9 is an exemplary diagram of an image detected by a first step in an embodiment of the present invention;
FIG. 10 is an exemplary diagram of an image detected by the second step in the embodiment of the present invention;
fig. 11 is an exemplary diagram of an extended two-dimensional code effective area in an embodiment of the present invention;
fig. 12 is a diagram illustrating an example of outputting two-dimensional code valid areas in the embodiment of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the specific drawings.
When the two-dimensional code is decoded, the two-dimensional code is preprocessed before being analyzed, so that the decoding speed of the two-dimensional code is improved.
Whether the two-dimensional code is contained in the target image is recognized in advance in the two-dimensional code scanning and decoding process, the two-dimensional code area in the target image is cut, the cut two-dimensional code area is input into the two-dimensional code analysis library to be analyzed, and therefore the decoding speed of the two-dimensional code can be increased.
According to the scheme, the target image is preprocessed to identify whether the target image contains the two-dimensional code, and the corresponding preprocessing process is as follows (see fig. 1):
and (1) carrying out binarization on the target image.
For the target image binarization processing in the scheme, a threshold value for gray level image binarization is calculated through an iterative algorithm, and the image binarization is carried out according to the threshold value. And the iterative computation process of the threshold for binarization is as follows (as shown in fig. 2):
step (11) acquiring image data to be processed;
step (12) calculating histogram data of the image;
step (13), calculating minimum and maximum non-zero values, minValue and maxValue, in the histogram data; taking a minimum non-zero value minValue as an initial threshold value TH, and taking the average value of the minimum non-zero value minValue and the initial threshold value TH as an initial new threshold value THNew;
step (14) judges whether the threshold TH and the new threshold THNew are equal: if not, turning to the step (15); if yes, turning to the step (16);
step (15) dividing the histogram into two parts according to a threshold TH, respectively solving an average gray value, taking the mean value of the two average gray values as a new threshold THNew, and then comparing the new threshold THNew with the threshold TH until the two are equal;
and (16) taking the new threshold value THNew as a threshold value for binarization, and using the new threshold value THNew as the threshold value for binarization of the image.
And (2) segmenting the binarized target image into rectangular blocks.
And (3) respectively judging whether the two-dimensional code is contained and marked aiming at each block.
The block judgment process in the scheme specifically includes the following steps (see fig. 3):
polling each rectangular block, and calculating whether the black-white pixel ratio of each rectangular block meets the condition;
the rectangular block meeting the condition is quartered, and whether the four sub-blocks meet the preset condition (the preset condition can be that the black-white pixel ratio of the four sub-blocks meets the condition or whether the number of the sub-blocks in the four sub-blocks, the black-white pixel ratio of which meets the condition, is more than half) is judged; if yes, marking the rectangular block as a two-dimensional code effective area;
and (33) accumulating the credibility of each continuous 2 x 2 blocks of the rectangular blocks marked as the two-dimensional code effective areas.
And (4) iteratively expanding the two-dimensional code area according to the mark and calculating the reliability.
For the implementation process of expanding the two-dimensional code area in the present scheme, the implementation process specifically includes the following steps (see fig. 4):
step (41) calculating the reliability of the current two-dimensional code effective area;
step (42) judging whether the current reliability is equal to the previous reliability, if so, ending, and if not, turning to step (43);
and (43) expanding the two-dimensional code effective area by every 3 x 3 blocks of the rectangular blocks in the credibility area, calculating the credibility, and turning to the step (42).
Judging whether the image contains the two-dimensional code or not according to the reliability, and if the reliability meets a corresponding threshold value, judging that the target image contains the two-dimensional code and outputting a two-dimensional code effective area; and if the reliability does not meet the corresponding threshold value, judging that the target image does not contain the two-dimensional code.
The two-dimensional code preprocessing scheme formed in the way can quickly and accurately judge whether the target image contains the two-dimensional code, and is convenient for quick decoding of the subsequent two-dimensional code.
Referring to fig. 5, a two-dimensional code decoding preprocessing system provided by the present solution is shown. The two-dimensional code decoding preprocessing system can achieve the two-dimensional code decoding preprocessing function, can effectively judge whether a target image contains a two-dimensional code, and transmits a two-dimensional code effective area through an output parameter.
As can be seen from the figure, the two-dimensional code decoding preprocessing system 10 mainly includes an image binarization module 11, an image segmentation module 12, a block determination and labeling module 13, an effective area expansion module 14, and an output module 15.
The image binarization module 11 receives a target image and performs binarization processing on the target image.
The image binarization module 11 calculates a threshold value for the binarization of the grayscale image by an iterative algorithm according to the flow shown in fig. 2, and binarizes the image according to the threshold value.
And the image segmentation rectangular block 12 is in data connection with the binarization module 11 and is used for segmenting the binarized target image into a plurality of rectangular blocks.
And the block judging and marking module 13 is in data connection with the image segmentation rectangular blocks 12 and is used for judging and marking the module, judging whether each rectangular block contains the two-dimensional code and marking.
The block determination and marking module 13 determines whether each block contains a two-dimensional code according to the flow shown in fig. 3, and marks the flow shown.
And the effective area expanding module 14 is in data connection with the block judging and marking module 13 and is used for iteratively expanding the two-dimensional code area according to the marks and calculating the reliability.
The valid region extension module 14 iteratively extends the two-dimensional code region for the marker according to the flow shown in fig. 4 and calculates the reliability.
And the output module 15 is in data connection with the effective area expanding module 14 and is used for preprocessing the target image.
The output module 15 outputs true under the condition that the credibility meets the condition, and outputs the two-dimensional code effective area through the parameters; and outputting false if the reliability does not meet the condition.
The two-dimensional code preprocessing system formed by the method can be realized by a corresponding software architecture when being specifically realized. The operation of the method is described below by a specific application example.
In this example, when the two-dimensional code decoding preprocessing system processes, it receives a piece of gray image data, returns a bool variable to indicate whether the two-dimensional code is contained, and the two-dimensional code effective area is transmitted out through the output parameter.
Referring to fig. 6, an exemplary diagram of an original image that needs to be preprocessed in this example is shown.
First, the present system calculates a threshold value for binarizing a grayscale image by an iterative algorithm with respect to an original image shown in fig. 6, and binarizes the original image shown in fig. 6 based on the threshold value to obtain a binarized image (as shown in fig. 7).
Next, the binarized image shown in fig. 7 is divided into a predetermined number of small blocks (as shown in fig. 8) which are close to squares.
Next, for the image shown in fig. 8 divided into several small blocks approaching to a square, each small block is polled to calculate whether its black-white pixel ratio satisfies the condition, see fig. 9, which is an exemplary diagram of the image detected by the first step.
Then, aiming at the image detected in the first step, quartering each small block meeting the regulation, and judging whether the black-white pixel ratios of the four sub-blocks meet the conditions; referring to fig. 10, an exemplary diagram of an image detected by the second step is shown.
Next, for the image detected by the second step, a succession of 2 x 2 blocks of accumulated confidence is performed.
Then, 3 × 3 expansion is carried out on the blocks in the credibility region until the current credibility is equal to the previous credibility; referring to fig. 11, a diagram of an example of an image of an effective area of a two-dimensional code to be expanded is shown.
Finally, outputting true aiming at the condition that the reliability meets the condition, and outputting a two-dimensional code effective area through parameters (as shown in figure 12); and outputting false aiming at the condition that the reliability does not meet the condition.
The two-dimensional code effective area output according to the method is used for cutting the two-dimensional code area in the output target image when the follow-up two-dimensional code is decoded, and then the cut two-dimensional code area is input into the two-dimensional code analysis library for analysis, so that the decoding speed of the two-dimensional code can be accelerated.
Finally, the above-mentioned solution is a pure software architecture, and can be distributed on a physical medium such as a hard disk, a floppy disk, an optical disk, or any machine-readable storage medium (such as a smart phone or a computer-readable storage medium) through a program code.
The described aspects may also be embodied in the form of program code that is transmitted over some transmission medium, such as electrical cable, fiber optics, or via any other form of transmission, wherein, when the program code is received and loaded into and executed by a machine, such as a smart phone, the machine becomes an apparatus for practicing the described aspects.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A two-dimensional code preprocessing method is characterized by comprising the following steps:
directly carrying out binarization on the whole target image;
directly segmenting the binarized target image in the step (1) into rectangular blocks;
step (3), judging whether each block formed in the step (2) contains a two-dimensional code and marking the two-dimensional code;
step (4), iteratively expanding the two-dimensional code area according to the mark formed in the step (3) and calculating the reliability;
step (5), judging whether the image contains the two-dimensional code according to the reliability calculated and determined in the step (4), and if the reliability meets a corresponding threshold value, judging that the target image contains the two-dimensional code and outputting a two-dimensional code effective area; and if the reliability does not meet the corresponding threshold value, judging that the target image does not contain the two-dimensional code.
2. The two-dimensional code preprocessing method according to claim 1, wherein, in the image binarization processing, a threshold value for the binarization of the grayscale image is calculated by an iterative algorithm, and the image binarization is performed according to the threshold value.
3. The two-dimensional code preprocessing method according to claim 2, wherein the iterative computation process of the threshold value for binarization includes:
calculating histogram data of the image;
calculating a minimum non-zero value and a maximum non-zero value in the histogram data, taking the minimum non-zero value as an initial threshold value, taking an average value of the minimum non-zero value and the initial threshold value as an initial new threshold value, and judging whether the minimum non-zero value and the maximum non-zero value are equal;
when the two gray values are not equal, the histogram is divided into two parts according to the initial new threshold value, the average gray value is respectively calculated, and the average value of the two average gray values is used as the new threshold value.
4. The two-dimensional code preprocessing method according to claim 1, wherein the block judgment comprises:
polling each rectangular block, and calculating whether the black-white pixel ratio of each rectangular block meets the condition;
quartering the rectangular blocks meeting the conditions, and judging whether the four sub-blocks meet preset conditions or not; if yes, marking the two-dimension code as a two-dimension code effective area;
and accumulating the credibility of each continuous 2 x 2 blocks of rectangular blocks marked as the valid areas of the two-dimensional codes.
5. The two-dimensional code preprocessing method according to claim 1, wherein 3 x 3 blocks of expansion of the two-dimensional code effective area are performed on the rectangular blocks in the confidence level area until the current confidence level is equal to the previous confidence level.
6. A two-dimensional code decoding preprocessing system is characterized by comprising:
the image binarization module is used for carrying out binarization processing on the target image;
the image segmentation rectangular blocks are used for segmenting a plurality of rectangular blocks of the binarized target image;
the block judgment and marking module is used for judging whether each rectangular block contains the two-dimensional code and marking;
the effective area expansion module is used for iteratively expanding the two-dimensional code area according to the mark and calculating the reliability;
and the output module is used for judging whether the image contains the two-dimensional code or not according to the credibility and outputting the effective area of the two-dimensional code.
7. A two-dimensional code decoding method is characterized in that whether a two-dimensional code is contained in a target image or not is identified in advance through the two-dimensional code preprocessing method of any one of claims 1 to 5, a two-dimensional code area in the target image is cut, and then the cut two-dimensional code area is analyzed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710548082.7A CN107423653B (en) | 2017-07-06 | 2017-07-06 | Two-dimensional code preprocessing method, system and decoding method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710548082.7A CN107423653B (en) | 2017-07-06 | 2017-07-06 | Two-dimensional code preprocessing method, system and decoding method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107423653A CN107423653A (en) | 2017-12-01 |
CN107423653B true CN107423653B (en) | 2021-06-08 |
Family
ID=60427465
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710548082.7A Active CN107423653B (en) | 2017-07-06 | 2017-07-06 | Two-dimensional code preprocessing method, system and decoding method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107423653B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109801389A (en) * | 2019-03-18 | 2019-05-24 | 重庆睿驰智能科技有限公司 | Payment auxiliary system based on viewing system |
CN110276226A (en) * | 2019-06-26 | 2019-09-24 | 北京慧眼智行科技有限公司 | A kind of dot matrix code detection method and system |
CN114139564A (en) * | 2021-12-07 | 2022-03-04 | Oppo广东移动通信有限公司 | Two-dimensional code detection method and device, terminal equipment and training method for detection network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254144A (en) * | 2011-07-12 | 2011-11-23 | 四川大学 | Robust method for extracting two-dimensional code area in image |
CN102708552A (en) * | 2012-05-24 | 2012-10-03 | 中山大学 | Rapid two-dimensional barcode image motion deblurring method |
CN104517090A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Method and system for detecting QR code detection figures |
CN104933387A (en) * | 2015-06-24 | 2015-09-23 | 上海快仓智能科技有限公司 | Rapid positioning and identifying method based on two-dimensional code decoding |
CN105654019A (en) * | 2016-02-23 | 2016-06-08 | 海信集团有限公司 | Fast decoding method and device for two-dimension code |
CN105868724A (en) * | 2016-04-07 | 2016-08-17 | 广州智慧城市发展研究院 | Two-dimensional bar code identification method and system based on connected domain |
-
2017
- 2017-07-06 CN CN201710548082.7A patent/CN107423653B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254144A (en) * | 2011-07-12 | 2011-11-23 | 四川大学 | Robust method for extracting two-dimensional code area in image |
CN102708552A (en) * | 2012-05-24 | 2012-10-03 | 中山大学 | Rapid two-dimensional barcode image motion deblurring method |
CN104517090A (en) * | 2013-09-29 | 2015-04-15 | 北大方正集团有限公司 | Method and system for detecting QR code detection figures |
CN104933387A (en) * | 2015-06-24 | 2015-09-23 | 上海快仓智能科技有限公司 | Rapid positioning and identifying method based on two-dimensional code decoding |
CN105654019A (en) * | 2016-02-23 | 2016-06-08 | 海信集团有限公司 | Fast decoding method and device for two-dimension code |
CN105868724A (en) * | 2016-04-07 | 2016-08-17 | 广州智慧城市发展研究院 | Two-dimensional bar code identification method and system based on connected domain |
Also Published As
Publication number | Publication date |
---|---|
CN107423653A (en) | 2017-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108920580B (en) | Image matching method, device, storage medium and terminal | |
CN107423653B (en) | Two-dimensional code preprocessing method, system and decoding method | |
CN109658402B (en) | Automatic detection method for geometric dimension of industrial profile based on computer vision imaging | |
CN108805128B (en) | Character segmentation method and device | |
CN111651636B (en) | Video similar segment searching method and device | |
CN111860348A (en) | Deep learning-based weak supervision power drawing OCR recognition method | |
CN104298982A (en) | Text recognition method and device | |
CN111709420A (en) | Text detection method, electronic device and computer readable medium | |
CN110610166A (en) | Text region detection model training method and device, electronic equipment and storage medium | |
CN113723330B (en) | Method and system for understanding chart document information | |
CN108229232B (en) | Method and device for scanning two-dimensional codes in batch | |
CN101930532A (en) | Mobile phone-based camera quick response matrix code recognizing and reading method | |
US9922263B2 (en) | System and method for detection and segmentation of touching characters for OCR | |
CN113297870A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN102521559B (en) | 417 bar code identification method based on sub-pixel edge detection | |
EP0996079B1 (en) | Method for locating codes in bidimensional images | |
CN111967449B (en) | Text detection method, electronic device and computer readable medium | |
CN109977715B (en) | Two-dimensional code identification method based on contour identification and two-dimensional code | |
CN112214737A (en) | Method, system, device and medium for identifying picture-based fraudulent webpage | |
Salunkhe et al. | Recognition of multilingual text from signage boards | |
CN111753842B (en) | Method and device for detecting text region of bill | |
CN110826488B (en) | Image identification method and device for electronic document and storage equipment | |
CN112434700A (en) | License plate recognition method, device, equipment and storage medium | |
CN112183540A (en) | Label parameter extraction method and device, storage medium and electronic device | |
KR101828873B1 (en) | Method and apparatus for identifying code targets |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |