CN103177235A - Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background - Google Patents
Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background Download PDFInfo
- Publication number
- CN103177235A CN103177235A CN2013101358160A CN201310135816A CN103177235A CN 103177235 A CN103177235 A CN 103177235A CN 2013101358160 A CN2013101358160 A CN 2013101358160A CN 201310135816 A CN201310135816 A CN 201310135816A CN 103177235 A CN103177235 A CN 103177235A
- Authority
- CN
- China
- Prior art keywords
- chinese letter
- chinese
- image
- letter
- carried out
- 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
Images
Landscapes
- Character Discrimination (AREA)
- Character Input (AREA)
Abstract
The invention belongs to the field of two-dimensional code recognition, relates to applications of image processing and character recognition technology and discloses a Chinese-sensible code recognition device and a Chinese-sensible code recognition method under a complicated background. The method comprises the following steps of: collecting a Chinese-sensible code image with a complicated background; preprocessing the collected image; carrying out secondary positioning on a Chinese-sensible code in the image to obtain the accurate position of the Chinese-sensible code; carrying out slant correction on the Chinese-sensible code obtained by positioning, thus obtaining the corrected Chinese-sensible code; partitioning the Chinese-sensible code by using an edge detection and projection algorithm to obtain a single-line Chinese-sensible code, and then carrying out single-character recognition; decoding to obtain Chinese-sensible code information; and displaying the Chinese-sensible code information on a display screen. According to the method disclosed by the invention, the location accuracy is improved, the efficiency of algorithm is high, the rate is fast, the anti-interference property is strong, the robustness is good, single-character bar codes can be recognized rapidly and effectively, the bar codes can be recognized accurately, and the efficiency of Chinese-sensible code recognition is greatly improved.
Description
Technical field
The invention belongs to two-dimension code and identify the field, is the application of image processing and character recognition technologies, particularly relates to recognition device and the method for Chinese letter co under a kind of complex background.
Background technology
In the two-dimension code application facet, the domestic main external technology such as PDF417, QR code that rely at present.These technology exist strict patent protection, thereby relevant device is expensive and have certain hidden danger on information security.First has the two-dimension code national standard issue of complete independent intellectual property right along with China, and Chinese letter co is more and more used in various aspects such as books, vehicle managements gradually.But due to applied environment characteristics and external interference factor, the accuracy of Chinese letter co identification and robustness are difficult to guarantee.Therefore, under complex background, the recognition methods of Chinese letter co is very practical at recognition Chinese letter co message context.Use the secondary location and tilt to correct, effectively accurately alignment code figure, adopt and correctly identify single character based on the dual threshold recognition methods of projection result analysis, and by the decoding decoding step, obtain rapidly and accurately Chinese letter co information.
Summary of the invention
Purpose: in order to overcome the deficiencies in the prior art, the invention provides identification equipment and the method for Chinese letter co under a kind of complex background, can improve efficient and the accuracy of Chinese letter co identification, reduce noise to the interference of identification, and obtain fast Chinese letter co information.
Technical scheme: for solving the problems of the technologies described above, the technical solution used in the present invention is:
The identification equipment of Chinese letter co under a kind of complex background, it is characterized in that: comprise Chinese letter co image, camera, PC and display with complex background, described camera carries out shooting, collecting to the Chinese letter co image, and the image that gathers is sent to PC, described PC comprises that to image the algorithm identified of location, rectification, monocase identification, decoding decoding obtains Chinese letter co information, and described display shows Chinese letter co information.
A kind of intelligent traffic dispatching method based on the multiple agent interaction technique is characterized in that: comprise the steps:
Step (1) gathers the Chinese letter co image with complex background;
Step (2) is carried out pre-service to the image that gathers;
Step (3) is carried out secondary location to the Chinese letter co in image, obtains the exact position of Chinese letter co;
Step (4) tilts to correct to the Chinese letter co that the location obtains, the Chinese letter co that obtains correcting;
Step (5) is utilized rim detection and projection algorithm, Chinese letter co is cut apart obtain the single file Chinese letter co, then carries out single character recognition;
Step (6) is carried out the decoding decoding, obtains Chinese letter co information;
Step (7) is presented at the Chinese letter co information that obtains on display screen.
In described step (2), the image that gathers being carried out pretreated step is:
(2a) adopt the component method, coloured image is carried out gray processing process, obtain gray level image;
(2b) medium filtering is removed the noise of image;
(2c) strengthen processing to increase picture contrast.
In described step (3), the Chinese letter co in image being carried out secondary location is to the image coarse positioning according to the subregion feature, go out the image region that may comprise Chinese letter co according to two Feature Selections of contrast, linear-scale of subregion, at last subregion is merged, detect the Position Approximate at bar code place, complete coarse positioning; According to view finding graph scanning feature, image is accurately located again, the steps include:
(3a) at first the Chinese letter co gray level image is divided into m * n sub regions, every sub regions is labeled as A
i,j(i=0,1 ..., m-1; J=0,1 ..., n-1);
(3b) Calculation Comparison degree feature: at subregion A
i,jIn, obtaining the gray-scale value i of each pixel, selected threshold T makes image be divided into light and shade two parts that pixel quantity equates, and namely in subregion, gray-scale value equates with sum of all pixels greater than T less than the sum of all pixels of T.N wherein
iBe the pixel number of i for gray-scale value in subregion, be respectively than the dark pixel gray average with than the gray average of bright pixel in the zone so:
Subregion A in the definition image
i,jContrast C on (A
i,j) be the difference Con (A of light and shade two parts gray average in the zone
i,j)=G
Bright-G
Dark
(3c) calculate the linear-scale feature: at first image is carried out the canny operator edge detection, with the edge image binaryzation that obtains.Then surpass all straight-line segments of certain threshold value with length in hough change detection bianry image, then add up straight line number corresponding to each angle of inclination, choose the maximum angle θ of line correspondence number
maxAs target direction.Add up at last every sub regions at θ
maxStraight line number Line (A on direction
i,j), and with Line (A
i,j) be defined as the linear-scale of subregion;
(3d) the subregion screening merges: at first adopt OTSU algorithm picks threshold value T
cAnd T
lIf, certain sub regions A
i,jBe the part of Chinese letter co, the contrast of this sub regions, linear-scale need to satisfy certain condition so:
To carry out connected region through the subregion of screening again and divide, obtain the set of regions S of several connections
1, S
2..., S
N, then calculate the included subregion number ‖ S of each connected set
i‖ is called set of regions S
iBase, for the too small connected set ‖ S of base
i‖<T
AreaGet rid of the T here
AreaBeing the Chinese letter co area rounds value after processing divided by the value of subregion area;
(3e) complete coarse positioning after, accurately locate according to view finding graph scanning feature.When straight line passed the center of view finding figure of Chinese letter co, the scanning feature was 1:1:1:1:3 or the 3:1:1:1:1 that the depth replaces.This feature does not change because of code figure size, rotation, and in code figure the possibility of this ratio to occur minimum in other places, accurately determines the particular location of code figure by identifying four view finding figures.
The step that the Chinese letter co that in described step (4), the location is obtained tilts to correct is:
(4a) connect the center of four view finding figures, can form equilateral right-angle triangle with two minor faces and diagonal line, what the summit was corresponding is the center of Chinese letter co upper right corner view finding figure, and the center of hypotenuse is a yard center of graph.
(4b) be connected the straight-line equation xcos θ that the center connects+ysin θ=ρ with upper left corner view finding figure according to the right-angle triangle summit, obtain tilt angle theta, the x in equation, y is the horizontal and vertical direction of corresponding whole image respectively, and ρ is constant;
(4c) centered by code figure center, code figure is carried out central rotation, the anglec of rotation is tilt angle theta, rotation formula is: x '=xcos θ+ysin θ y '=-xsin θ+ycos θ (x wherein, y) be former figure coordinate, (x ', y ') be postrotational coordinate;
If (4d) postrotational image pixel can not find corresponding pixel in former figure, adopt bilinear interpolation to carry out approximate processing.Postrotational image pixel may can not find corresponding pixel in former figure, because in digital picture, coordinate is integer.
Described step is utilized rim detection and projection algorithm in (5), Chinese letter co is cut apart obtain the single file Chinese letter co, then carries out single character recognition, specifically comprises the following steps:
(5a) at first adopt the horizontal operator of Sobel to do rim detection to image, then carry out the horizontal direction projection, obtain row bound and the character duration H of unit of Chinese letter co, according to width, bar code is divided into the single file bar code;
(5b) single file Chinese letter co image is carried out vertical projection, then according to character duration H, projection result is cut apart;
(5c) establish in the capable j row of i character picture that in the k row, light pixel number is that in single Chinese letter co character, light standoff height is
Setting threshold h
th, detect in each character picture
Greater than threshold value h
thNumber lines (i, j), in single character module, standoff height accounts for the ratio of the total columns of single-bit module greater than the columns of threshold value:
(5d) choose at last suitable threshold value l
th(0<l
th<1), with l
i,jWith l
thCompare, according to
Obtain the value S of single Chinese letter co character
i,j(S
i,j=0 represents this character for dark, otherwise is light color).Can setting threshold h in real process
th=1/2H, threshold value l
th=1/2.
In described step (6), the step of decoding decoding is:
(6a) function information of Chinese letter co carried out decoding, determine version, error-correction level and the mask scheme of Chinese letter co;
(6b) according to symbol version and other decoding information, set up the sampling grid, Chinese letter co is taken a sample;
(6c) according to the mask scheme that obtains in function information, determine mask images, with mask images, the module of code area is carried out XOR and process, remove mask;
(6d) according to the arranging rule of data, recover the code word data sequence;
(6e) the data codeword sequence is carried out error-detecting, if find mistake, carry out error-correcting decoding and process;
(6f) the information codeword sequence is carried out decoding of information, obtain Chinese letter co information.
Beneficial effect: the present invention has following advantage:
(1) the present invention adopts secondary positioning instant coarse positioning and accurately locates two steps and realize Bar code positioning, has avoided the poor efficiency of traditional localization method, improved the accuracy of location, and efficiency of algorithm is high, and speed is fast, strong interference immunity;
(2) the present invention proposes the concrete grammar that Chinese letter co tilts to correct, not only innovate and enriched the method that bar code tilts to correct, adopt simultaneously bilinear interpolation method to carry out approximate processing, can greatly improve the accuracy rate of bar-code identification;
(3) the present invention proposes a kind of method of new bar-code identification, the dual threshold identification of namely analyzing based on projection result, to single character recognition, and decoding is as a result decoded, obtain Chinese letter co information, this method is the identification form character barcode fast and effeciently, has good anti-interference, robustness, can identify exactly bar code, and greatly improve the efficient of Chinese letter co identification.
Description of drawings
Fig. 1 is the block diagram of system of the present invention;
Fig. 2 is the process flow diagram of Chinese letter co recognition methods under complex background in the present invention;
Fig. 3 is the pretreated process flow diagram of image in the present invention;
Fig. 4 is the process flow diagram of secondary location in the present invention;
Fig. 5 is the process flow diagram that in the present invention, Chinese letter co tilts to correct;
Fig. 6 is that in the present invention, Chinese letter co is cut apart the process flow diagram of identifying with monocase;
Fig. 7 is the process flow diagram of decoding decoding in the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention is further described.
As shown in Figure 1, the identification equipment of Chinese letter co under a kind of complex background, comprise: with Chinese letter co image, camera, PC and the display of complex background, described camera carries out shooting, collecting to the Chinese letter co image, and image is sent to PC, described PC comprises that to image the algorithm identified of location, rectification, monocase identification, decoding decoding obtains Chinese letter co information, and described display shows Chinese letter co information.
The said equipment obtains the code figure of standard to the location inclination rectification of the Chinese letter co secondary under complex background, identifies with decoding by monocase and decodes, obtain fast Chinese letter co information, its idiographic flow as shown in Figure 2, under a kind of complex background, the recognition methods of Chinese letter co, comprise the steps:
Step (1), gather the Chinese letter co image with complex background;
Step (2), image is carried out pre-service;
Step (3), the Chinese letter co in image is carried out secondary location, obtain the exact position of Chinese letter co;
Step (4), the Chinese letter co that the location is obtained tilt to correct, the Chinese letter co that obtains correcting;
Step (5), utilize rim detection and projection algorithm, Chinese letter co is cut apart obtained the single file Chinese letter co, then carry out single character recognition;
Step (6), carry out decoding decoding, obtain Chinese letter co information;
Step (7), the Chinese letter co information that obtains is presented on display screen.
As shown in Figure 3, in step (2), the step of " image is carried out pre-service " is:
(2a), adopt the component method, coloured image is carried out gray processing processes, obtain gray level image;
(2b), medium filtering is removed the noise of image;
(2c), strengthen processing to increase picture contrast.
The step of as shown in Figure 4, " Chinese letter co in image being carried out secondary locate, obtaining the exact position of Chinese letter co " in step (3) is:
(3a), secondary location refers to according to the subregion feature the image coarse positioning, then according to view finding graph scanning feature, image is accurately located;
(3b), at first the Chinese letter co gray level image is divided into m * n sub regions, every sub regions is labeled as S
i,j(i=0,1 ..., m-1; J=0,1 ..., n-1).And then go out the image region that may comprise Chinese letter co according to two Feature Selections of contrast, linear-scale of subregion, and at last subregion is merged, detect the Position Approximate at bar code place, complete coarse positioning;
(3c), Calculation Comparison degree feature.At subregion A
i,jIn, obtaining the gray-scale value i of each pixel, selected threshold T makes image be divided into light and shade two parts that pixel quantity equates, and namely in subregion, gray-scale value equates with sum of all pixels greater than T less than the sum of all pixels of T.N wherein
iBe the pixel number of i for gray-scale value in subregion, be respectively than the dark pixel gray average with than the gray average of bright pixel in the zone so:
Subregion A in the definition image
i,jContrast C on (A
i,j) be the difference Con (A of light and shade two parts gray average in the zone
i,j)=G
Bright-G
Dark
(3d), calculate the linear-scale feature.At first we first carry out the canny operator edge detection to image, with the edge image binaryzation that obtains.Then surpass all straight-line segments of certain threshold value with length in hough change detection bianry image, then add up straight line number corresponding to each angle of inclination, choose the maximum angle θ of line correspondence number
maxAs target direction.Add up at last every sub regions at θ
maxStraight line number Line (A on direction
i,j), and with Line (A
i,j) be defined as the linear-scale of subregion;
(3e), the subregion screening merges.At first adopt OTSU algorithm picks threshold value T
cAnd T
lIf, certain sub regions A
i,jBe the part of Chinese letter co, the contrast of this sub regions, linear-scale need to satisfy certain condition so:
To carry out connected region through the subregion of screening again and divide, obtain the set of regions S of several connections
1, S
2..., S
N, then calculate the included subregion number ‖ S of each connected set
i‖ is called set of regions S
iBase, for the too small connected set ‖ S of base
i‖<T
AreaGet rid of;
(3f), complete coarse positioning after, accurately locate according to view finding graph scanning feature.When straight line passed the center of view finding figure of Chinese letter co, the scanning feature was 1:1:1:1:3 or the 3:1:1:1:1 that the depth replaces.This feature does not change because of code figure size, rotation, and in code figure the possibility of this ratio to occur minimum in other places, accurately determines the particular location of code figure by identifying four view finding figures.
As shown in Figure 5, in step (4), the step of " Chinese letter co that the location is obtained tilts to correct, the Chinese letter co that obtains correcting " is:
(4a), connect the center of four view finding figures, can form equilateral right-angle triangle with two minor faces and diagonal line, what the summit was corresponding is the center of Chinese letter co upper right corner view finding figure, the center of hypotenuse is a yard center of graph.
(4b), be connected the straight-line equation xcos θ that the center connects+ysin θ=ρ with upper left corner view finding figure according to the right-angle triangle summit, obtain tilt angle theta;
(4c), centered by code figure center, code figure is carried out central rotation, anglec of rotation θ, rotation formula is: x '=xcos θ+ysin θ y '=-xsin θ+ycos θ (x wherein, y) be former figure coordinate, (x ', y ') be postrotational coordinate;
(4d), adopt bilinear interpolation to carry out approximate processing.Postrotational image pixel may can not find corresponding pixel in former figure, because in digital picture, coordinate is integer.
As shown in Figure 6, " utilize rim detection and projection algorithm, Chinese letter co is cut apart obtained the single file Chinese letter co, then carry out single character recognition " in step (5) and comprise the following steps:
(5a), at first adopt the horizontal operator of Sobel to do rim detection to image, then carry out the horizontal direction projection, obtain row bound and the character duration H of unit of Chinese letter co, according to width, bar code is divided into the single file bar code;
(5b), single file Chinese letter co image is carried out vertical projection, then according to character duration H, projection result is cut apart;
(5c), establish in the capable j row of i character picture that in the k row, light pixel number is that in single Chinese letter co character, light standoff height is
Setting threshold h
th, detect in each character picture
Greater than threshold value h
thNumber lines (i, j), in single character module, standoff height accounts for the ratio of the total columns of single-bit module greater than the columns of threshold value:
(5d), choose at last suitable threshold value l
th(0<l
th<1), with l
i,jWith l
thCompare, according to
Obtain the value S of single Chinese letter co character
i,j(S
i,j=0 represents this character for dark, otherwise is light color).Can setting threshold h in real process
th=1/2H, threshold value l
th=1/2.
As shown in Figure 7, " carry out the decoding decoding, obtain Chinese letter co information " in step (6) comprising the following steps:
(6a), the function information of Chinese letter co is carried out decoding, determine version, error-correction level and the mask scheme of Chinese letter co;
(6b), according to symbol version and other information, set up the sampling grid, Chinese letter co is taken a sample;
(6c), according to the mask scheme that obtains in function information, determine mask graph, with mask images, the module of code area is carried out XOR and processes, remove mask;
(6d), according to the arranging rule of data, recover the code word data sequence;
(6e), the data codeword sequence is carried out error-detecting, if the discovery mistake is carried out error-correcting decoding and processed;
(6f), the information codeword sequence is carried out decoding of information, obtain Chinese letter co information.
The present invention adopts secondary positioning instant coarse positioning and accurately locates two steps and realize Bar code positioning, has avoided the poor efficiency of traditional localization method, improved the accuracy of location, and efficiency of algorithm is high, and speed is fast, strong interference immunity.The present invention proposes the concrete grammar that Chinese letter co tilts to correct, not only innovate and enriched the method that bar code tilts to correct, adopt simultaneously bilinear interpolation method to carry out approximate processing, can greatly improve the accuracy rate of bar-code identification.The present invention proposes a kind of method of new bar-code identification, the dual threshold identification of namely analyzing based on projection result, to single character recognition, and decoding is as a result decoded, obtain Chinese letter co information, this method is the identification form character barcode fast and effeciently, has good anti-interference, robustness, can identify exactly bar code, and greatly improve the efficient of Chinese letter co identification.The present invention has great realistic meaning and using value at present and in the identification of Chinese letter co in the future.
The above is only the preferred embodiment of the present invention; be noted that for those skilled in the art; under the prerequisite that does not break away from the principle of the invention, can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (7)
1. the recognition device of Chinese letter co under a complex background, it is characterized in that: comprise Chinese letter co image, camera, PC and display with complex background, described camera carries out shooting, collecting to the Chinese letter co image, and the image that gathers is sent to PC, described PC comprises that to image the algorithm identified of location, rectification, monocase identification, decoding decoding obtains Chinese letter co information, and described display shows Chinese letter co information.
2. the recognition methods of Chinese letter co under a complex background is characterized in that: comprise the steps:
Step (1) gathers the Chinese letter co image with complex background;
Step (2) is carried out pre-service to the image that gathers;
Step (3) is carried out secondary location to the Chinese letter co in image, obtains the exact position of Chinese letter co;
Step (4) tilts to correct to the Chinese letter co that the location obtains, the Chinese letter co that obtains correcting;
Step (5) is utilized rim detection and projection algorithm, Chinese letter co is cut apart obtain the single file Chinese letter co, then carries out single character recognition;
Step (6) is carried out the decoding decoding, obtains Chinese letter co information;
Step (7) is presented at the Chinese letter co information that obtains on display screen.
3. the recognition methods of Chinese letter co under a kind of complex background according to claim 2 is characterized in that: in described step (2), the image that gathers being carried out pretreated step is:
(2a) adopt the component method, coloured image is carried out gray processing process, obtain gray level image;
(2b) medium filtering is removed the noise of image;
(2c) strengthen processing to increase picture contrast.
4. the recognition methods of Chinese letter co under a kind of complex background according to claim 3, it is characterized in that: in described step (3), the Chinese letter co in image being carried out secondary location is to the image coarse positioning according to the subregion feature, according to view finding graph scanning feature, image is accurately located again, the steps include:
(3a) at first the Chinese letter co gray level image is divided into m * n sub regions, every sub regions is labeled as A
i,j(i=0,1 ..., m-1; J=0,1 ..., n-1);
(3b) Calculation Comparison degree feature: at subregion A
i,jIn, obtaining the gray-scale value i of each pixel, selected threshold T makes image be divided into light and shade two parts that pixel quantity equates, and namely in subregion, gray-scale value equates with sum of all pixels greater than T less than the sum of all pixels of T; N wherein
iBe the pixel number of i for gray-scale value in subregion, so in the zone than dark pixel gray average G
DarkWith the gray average G than bright pixel
BrightBe respectively:
Subregion A in the definition image
i,jContrast C on (A
i,j) be the difference Con (A of light and shade two parts gray average in the zone
i,j)=G
Bright-G
Dark
(3c) calculate the linear-scale feature: at first image is carried out the canny operator edge detection, with the edge image binaryzation that obtains; Then surpass all straight-line segments of certain threshold value with length in hough change detection bianry image, then add up straight line number corresponding to each angle of inclination, choose the maximum angle θ of line correspondence number
maxAs target direction; Add up at last every sub regions at θ
maxStraight line number Line (A on direction
i,j), and with Line (A
i,j) be defined as the linear-scale of subregion;
(3d) the subregion screening merges: at first adopt OTSU algorithm picks threshold value T
cAnd T
lIf, certain sub regions A
i,jBe the part of Chinese letter co, the contrast of this sub regions, linear-scale need to satisfy condition simultaneously so:
To carry out connected region through the subregion of screening again and divide, obtain the set of regions S of several connections
1, S
2..., S
N, then calculate the included subregion number ‖ S of each connected set
i‖ is called set of regions S
iBase, for basic ‖ S
i‖<T
AreaConnected set get rid of, the T here
AreaBeing the Chinese letter co area rounds value after processing divided by the value of subregion area;
(3e) complete coarse positioning after, accurately locate according to view finding graph scanning feature; When straight line passed the center of view finding figure of Chinese letter co, the scanning feature was 1:1:1:1:3 or the 3:1:1:1:1 that the depth replaces; Accurately determine the particular location of code figure by identifying four view finding figures.
5. the recognition methods of Chinese letter co under a kind of complex background according to claim 4 is characterized in that: the step that the Chinese letter co that in described step (4), the location is obtained tilts to correct is:
(4a) connect the center of four view finding figures, can form equilateral right-angle triangle with two minor faces and diagonal line, what the summit was corresponding is the center of Chinese letter co upper right corner view finding figure, and the center of hypotenuse is a yard center of graph;
(4b) be connected the straight-line equation xcos θ that the center connects+ysin θ=ρ with upper left corner view finding figure according to the right-angle triangle summit, obtain tilt angle theta, the x in equation, y is the horizontal and vertical direction of corresponding whole image respectively, and ρ is constant;
(4c) centered by code figure center, code figure is carried out central rotation, the anglec of rotation is tilt angle theta, rotation formula is: x '=xcos θ+ysin θ y '=-xsin θ+ycos θ, wherein (x, y) is former figure coordinate, (x ', y ') be postrotational coordinate;
If (4d) postrotational image pixel can not find corresponding pixel in former figure, adopt bilinear interpolation to carry out approximate processing.
6. the recognition methods of Chinese letter co under a kind of complex background according to claim 2, it is characterized in that: described step is utilized rim detection and projection algorithm in (5), Chinese letter co cut apart obtained the single file Chinese letter co, then carry out single character recognition, specifically comprise the following steps:
(5a) at first adopt the horizontal operator of Sobel to do rim detection to image, then carry out the horizontal direction projection, obtain row bound and the character duration H of unit of Chinese letter co, according to width, bar code is divided into the single file bar code;
(5b) single file Chinese letter co image is carried out vertical projection, then according to character duration H, projection result is cut apart;
(5c) establish in the capable j row of i character picture that in the k row, light pixel number is that in single Chinese letter co character, light standoff height is
Setting threshold h
th, detect in each character picture
Greater than threshold value h
thNumber lines (i, j), in single character module, standoff height accounts for the ratio of the total columns of single-bit module greater than the columns of threshold value:
(5d) choose at last suitable threshold value l
th(0<l
th<1), with l
i,jWith l
thCompare, according to
Obtain the value S of single Chinese letter co character
i,j, S
i,j=0 represents this character for dark, otherwise is light color.
7. the recognition methods of Chinese letter co under a kind of complex background according to claim 2 is characterized in that: in described step (6), the step of decoding decoding is:
(6a) function information of Chinese letter co carried out decoding, determine version, error-correction level and the mask scheme of Chinese letter co;
(6b) according to decoding information, set up the sampling grid, Chinese letter co is taken a sample;
(6c) according to the mask scheme that obtains in function information, determine mask images, with mask images, the module of code area is carried out XOR and process, remove mask;
(6d) according to the arranging rule of data, recover the code word data sequence;
(6e) the data codeword sequence is carried out error-detecting, if find mistake, carry out error-correcting decoding and process;
(6f) the information codeword sequence is carried out decoding of information, obtain Chinese letter co information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101358160A CN103177235A (en) | 2013-04-18 | 2013-04-18 | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101358160A CN103177235A (en) | 2013-04-18 | 2013-04-18 | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103177235A true CN103177235A (en) | 2013-06-26 |
Family
ID=48637079
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013101358160A Pending CN103177235A (en) | 2013-04-18 | 2013-04-18 | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103177235A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699869A (en) * | 2013-12-30 | 2014-04-02 | 优视科技有限公司 | Method and device for recognizing two-dimension codes |
CN103699867A (en) * | 2013-11-22 | 2014-04-02 | 唐玉红 | Wedge-shaped bar code recognition method |
CN103761500A (en) * | 2014-01-22 | 2014-04-30 | 东华大学 | Intelligent book locating device based on two-dimension code technology |
CN103839031A (en) * | 2014-02-27 | 2014-06-04 | 杭州晟元芯片技术有限公司 | Special embedded type two-dimensional code recognition method |
CN104166829A (en) * | 2014-07-25 | 2014-11-26 | 北京农业智能装备技术研究中心 | Portable Chinese-sensible code reading machine and reading method thereof |
CN105550623A (en) * | 2016-01-25 | 2016-05-04 | 苏州佳世达电通有限公司 | Barcode image analysis method and barcode apparatus |
CN105989344A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Barcode recognition method and device |
CN106017313A (en) * | 2015-03-31 | 2016-10-12 | 株式会社三丰 | Edge detection bias correction value calculation method, edge detection bias correction method, and equipment |
WO2017041600A1 (en) * | 2015-09-07 | 2017-03-16 | 福建联迪商用设备有限公司 | Chinese-sensitive code feature pattern detection method and system |
CN106951810A (en) * | 2017-03-09 | 2017-07-14 | 江苏智联天地科技有限公司 | A kind of Chinese letter co localization method based on EWMA model |
CN107145810A (en) * | 2017-04-26 | 2017-09-08 | 南京理工大学 | A kind of comprehensive bar code identifying device and method |
CN108009459A (en) * | 2017-11-24 | 2018-05-08 | 浙江工业大学 | Character two-dimensional bar code method for rapidly positioning based on triangle polyester fibre symbol |
CN109840522A (en) * | 2019-01-08 | 2019-06-04 | 河北科技大学 | A kind of big plane rod end tagging scheme and character picture antidote |
CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
CN111259888A (en) * | 2020-01-15 | 2020-06-09 | 平安国际智慧城市科技股份有限公司 | Image-based information comparison method and device and computer-readable storage medium |
CN113312937A (en) * | 2021-06-25 | 2021-08-27 | 展讯通信(上海)有限公司 | Bar code identification method and device, storage medium and computer equipment |
CN114283145A (en) * | 2022-03-07 | 2022-04-05 | 中煤科工开采研究院有限公司 | Method and device for detecting equipment information code in underground coal mine |
CN114299409A (en) * | 2022-03-07 | 2022-04-08 | 中煤科工开采研究院有限公司 | Method and device for positioning underground personnel based on image recognition and depth information |
CN117085969A (en) * | 2023-10-11 | 2023-11-21 | 中国移动紫金(江苏)创新研究院有限公司 | Artificial intelligence industrial vision detection method, device, equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040238636A1 (en) * | 2001-10-08 | 2004-12-02 | Eckhard Marx | Semiconductor device identification apparatus |
CN101777119A (en) * | 2009-01-13 | 2010-07-14 | 芯发威达电子(上海)有限公司 | Quick pattern positioning method |
-
2013
- 2013-04-18 CN CN2013101358160A patent/CN103177235A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040238636A1 (en) * | 2001-10-08 | 2004-12-02 | Eckhard Marx | Semiconductor device identification apparatus |
CN101777119A (en) * | 2009-01-13 | 2010-07-14 | 芯发威达电子(上海)有限公司 | Quick pattern positioning method |
Non-Patent Citations (5)
Title |
---|
刘宁钟: "复杂背景中条码检测定位技术的研究", 《南京航空航天大学学报》, vol. 37, no. 1, 10 February 2005 (2005-02-10), pages 65 - 69 * |
周乐: "二维条码图像定位及识别算法的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 2, 15 February 2013 (2013-02-15), pages 1 - 55 * |
张旭: "汉信码识读技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 2, 15 August 2007 (2007-08-15), pages 1 - 31 * |
杜志俊: "PDF417二维条形码的读取和识别技术", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 4, 15 April 2010 (2010-04-15), pages 1 - 17 * |
甘岚等: "基于亚像素边缘检测的二维条码识别", 《计算机工程》, vol. 29, no. 22, 15 December 2003 (2003-12-15), pages 155 - 157 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699867A (en) * | 2013-11-22 | 2014-04-02 | 唐玉红 | Wedge-shaped bar code recognition method |
CN103699867B (en) * | 2013-11-22 | 2017-01-25 | 唐玉红 | Wedge-shaped bar code recognition method |
CN103699869A (en) * | 2013-12-30 | 2014-04-02 | 优视科技有限公司 | Method and device for recognizing two-dimension codes |
CN103761500A (en) * | 2014-01-22 | 2014-04-30 | 东华大学 | Intelligent book locating device based on two-dimension code technology |
CN103839031A (en) * | 2014-02-27 | 2014-06-04 | 杭州晟元芯片技术有限公司 | Special embedded type two-dimensional code recognition method |
CN104166829A (en) * | 2014-07-25 | 2014-11-26 | 北京农业智能装备技术研究中心 | Portable Chinese-sensible code reading machine and reading method thereof |
CN105989344A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Barcode recognition method and device |
CN106017313A (en) * | 2015-03-31 | 2016-10-12 | 株式会社三丰 | Edge detection bias correction value calculation method, edge detection bias correction method, and equipment |
US10528781B2 (en) | 2015-09-07 | 2020-01-07 | Fujian Landi Commercial Equipment Co., Ltd. | Detection method and system for characteristic patterns of Han Xin codes |
WO2017041600A1 (en) * | 2015-09-07 | 2017-03-16 | 福建联迪商用设备有限公司 | Chinese-sensitive code feature pattern detection method and system |
CN105550623B (en) * | 2016-01-25 | 2017-12-29 | 苏州佳世达电通有限公司 | The analysis method and barcode device of a kind of barcode image |
CN105550623A (en) * | 2016-01-25 | 2016-05-04 | 苏州佳世达电通有限公司 | Barcode image analysis method and barcode apparatus |
CN106951810A (en) * | 2017-03-09 | 2017-07-14 | 江苏智联天地科技有限公司 | A kind of Chinese letter co localization method based on EWMA model |
CN106951810B (en) * | 2017-03-09 | 2019-12-24 | 江苏智联天地科技有限公司 | Chinese-sensible code positioning method based on EWMA model |
CN107145810A (en) * | 2017-04-26 | 2017-09-08 | 南京理工大学 | A kind of comprehensive bar code identifying device and method |
CN108009459B (en) * | 2017-11-24 | 2020-08-18 | 浙江工业大学 | Character two-dimensional bar code rapid positioning method based on triangular locator |
CN108009459A (en) * | 2017-11-24 | 2018-05-08 | 浙江工业大学 | Character two-dimensional bar code method for rapidly positioning based on triangle polyester fibre symbol |
CN109840522A (en) * | 2019-01-08 | 2019-06-04 | 河北科技大学 | A kind of big plane rod end tagging scheme and character picture antidote |
CN109840522B (en) * | 2019-01-08 | 2023-06-20 | 河北科技大学 | Large-rod end face marking scheme and character image correction method |
CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
CN111259888A (en) * | 2020-01-15 | 2020-06-09 | 平安国际智慧城市科技股份有限公司 | Image-based information comparison method and device and computer-readable storage medium |
CN113312937A (en) * | 2021-06-25 | 2021-08-27 | 展讯通信(上海)有限公司 | Bar code identification method and device, storage medium and computer equipment |
CN114283145A (en) * | 2022-03-07 | 2022-04-05 | 中煤科工开采研究院有限公司 | Method and device for detecting equipment information code in underground coal mine |
CN114299409A (en) * | 2022-03-07 | 2022-04-08 | 中煤科工开采研究院有限公司 | Method and device for positioning underground personnel based on image recognition and depth information |
CN114283145B (en) * | 2022-03-07 | 2022-06-07 | 中煤科工开采研究院有限公司 | Method and device for detecting equipment information code in underground coal mine |
CN117085969A (en) * | 2023-10-11 | 2023-11-21 | 中国移动紫金(江苏)创新研究院有限公司 | Artificial intelligence industrial vision detection method, device, equipment and storage medium |
CN117085969B (en) * | 2023-10-11 | 2024-02-13 | 中国移动紫金(江苏)创新研究院有限公司 | Artificial intelligence industrial vision detection method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103177235A (en) | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background | |
CN102136058B (en) | Bar code image identification method | |
KR101612700B1 (en) | Method for decoding matrix-type two-dimensional code | |
Liu et al. | Recognition of QR Code with mobile phones | |
US9607199B2 (en) | Decoding machine-readable optical codes with aesthetic component | |
CN102799850B (en) | A kind of barcode recognition method and device | |
CN104732183A (en) | One-dimensional barcode identification method based on image sampling line grey scale information analysis | |
CN105989317B (en) | Two-dimensional code identification method and device | |
TWI606406B (en) | Methods, apparatus, and tangible computer readable storage media to extract text from imaged documents | |
CN110598686B (en) | Invoice identification method, system, electronic equipment and medium | |
CN103400131B (en) | Correcting unit in a kind of image recognition and method thereof | |
Clark et al. | Rectifying perspective views of text in 3D scenes using vanishing points | |
CN104361353A (en) | Application of area-of-interest positioning method to instrument monitoring identification | |
CN104424457A (en) | Method for identifying two-dimensional code under the condition of nonlinear distortion | |
WO2014092979A1 (en) | Method of perspective correction for devanagari text | |
CN1862560A (en) | 2-D barcode system capable of fast positioning based on positioning graph | |
WO2017041600A1 (en) | Chinese-sensitive code feature pattern detection method and system | |
CN105260694A (en) | Two-dimension code area locating method based on multistage backbone extraction and analysis | |
CN103839031A (en) | Special embedded type two-dimensional code recognition method | |
CN105335744A (en) | One-dimensional code region location based on image backbone extraction strip distribution features | |
CN103177251A (en) | Automatic QR (quick response) code positioning and orientating method | |
CN109978110A (en) | A kind of two dimensional code and coding/decoding method positioned for AGV with navigation | |
CN102073862B (en) | Method for quickly calculating layout structure of document image | |
Boukerma et al. | A novel Arabic baseline estimation algorithm based on sub-words treatment | |
CN102521559B (en) | 417 bar code identification method based on sub-pixel edge detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130626 |