CN104952143A - Color change detection method and color change detection system for red waterlines of bill images - Google Patents
Color change detection method and color change detection system for red waterlines of bill images Download PDFInfo
- Publication number
- CN104952143A CN104952143A CN201510340977.2A CN201510340977A CN104952143A CN 104952143 A CN104952143 A CN 104952143A CN 201510340977 A CN201510340977 A CN 201510340977A CN 104952143 A CN104952143 A CN 104952143A
- Authority
- CN
- China
- Prior art keywords
- bill
- red waterline
- red
- color change
- variable color
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a color change detection method and a color change detection system for red waterlines of bill images. According to the method, acquisition, graying, extraction and binarization processing are performed on the bill images in sequence; according to the system, the bill images are processed through an image acquisition module, a color space conversion module, a water redline area extraction module, a binarization processing module and a color change detection module, and whether the red waterlines of the bill images are changed in color or not is detected further according to black picture elements in the images; manual operation is not needed; the phenomenon that the bill invalidity is caused by the fact that the amount in words of face value information are stained in the automatic processing procedure of batch bills is effectively solved; the time of manually collating the bills is greatly shortened, and the processing efficiency of the batch bills is promoted. The color change detection method and the color change detection system disclosed by the invention can be widely applied to bill detection.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of bill images red waterline variable color detection method and system.
Background technology
The bill automated programming system of bank or unit, when processing bill, requires that specification filled in by pending bill, and nominal value is clean without altering.If pending face of instrument is stained or have sign of erasure, then bill automated programming system cannot carry out follow-up process or operation.Therefore, how bill images nominal value is carried out to the important research object be parsed into fast and effectively in the industry, and red waterline variable color to detect be one of them emphasis.
At present, it is generally come by the mode of range estimation by business personnel that the red waterline variable color of bank money image detects, and this detection mode detection efficiency is lower, is unfavorable for the batch processing of bill, and inevitable human eye estimates the accidental error brought.
In order to reduce time of manually collecting bill and error once in a while, promoting the efficiency of batch bill process, being badly in need of overcoming the above problems.
Summary of the invention
In order to solve the problems of the technologies described above, the object of this invention is to provide one can improve discrimination, and reliable and stable bill images red waterline variable color detection method.
Another object of the present invention is to provide one can improve discrimination, and reliable and stable bill images red waterline variable color detection system.
The technical solution adopted in the present invention is:
A kind of bill images red waterline variable color detection method, comprises the following steps:
A, bill images to be gathered, obtain bill coloured image;
B, bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtain bill Y channel image;
The red waterline regional location coordinate that C, basis are preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
D, Threshold segmentation process is carried out to the red waterline area image of bill, obtain bill red waterline region bianry image;
E, according to bill red waterline region bianry image, judge whether red waterline region variable color occurs.
As the further improvement of described a kind of bill images red waterline variable color detection method, described step e comprises:
E1, from the bianry image of bill red waterline region, extract all color change intervals;
E2, judge that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judge that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur.
As the further improvement of described a kind of bill images red waterline variable color detection method, described step e 1 comprises:
E11, to add up by column from the first row of bill red waterline region bianry image;
E12, statistics when the black picture element number in prostatitis, and calculate the ratio with bill red waterline region bianry image height, obtain the variable color ratio when prostatitis;
Whether E13, the variable color ratio of judgement when prostatitis are greater than default first threshold, if so, then record the sequence number when prostatitis, obtain the start sequence number of current color change interval, and perform step e 14; Otherwise, then next column is added up and returns performing step e 12;
E14, statistics next column calculate its variable color ratio, judge whether its variable color ratio is greater than default first threshold, if so, then return and re-execute step e 14; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number of current color change interval, and then extracts color change interval;
E15, judge whether that all row have added up complete, if so, then terminate to add up and perform step e 2; Otherwise, then next column is added up and returns performing step e 12.
As the further improvement of described a kind of bill images red waterline variable color detection method, in described step e 14 and then also comprise after extracting color change interval:
According to start sequence number and the end sequence number of current color change interval, calculate the width of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform step e 15; Otherwise, then directly step e 15 is performed.
As the further improvement of described a kind of bill images red waterline variable color detection method, carry out Threshold segmentation process to the red waterline area image of bill in described step D, it is specially:
According to the segmentation threshold preset and following formula, the pixel in the red waterline area image of bill is processed;
;
Wherein, i represents the horizontal ordinate in bill red waterline area image and bill red waterline region bianry image, j represents the ordinate in bill red waterline area image and bill red waterline region bianry image, D [i, j] represent horizontal ordinate in the bianry image of bill red waterline region to be i and ordinate be the value at the pixel place of j, RE [i, j] represents horizontal ordinate in the red waterline area image of bill to be i and ordinate is the value at the pixel place of j, and th represents segmentation threshold.
Another technical scheme of the present invention is:
A kind of bill images red waterline variable color detection system, comprising:
Image capture module, for gathering bill images, obtains bill coloured image;
Color space conversion module, for bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtains bill Y channel image;
Red waterline region extraction module, for according to the red waterline regional location coordinate preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
Binary conversion treatment module, for carrying out Threshold segmentation process to the red waterline area image of bill, obtains bill red waterline region bianry image;
Variable color detection module, for according to bill red waterline region bianry image, judges whether red waterline region variable color occurs.
As the further improvement of described a kind of bill images red waterline variable color detection system, described variable color detection module comprises:
Color change interval extraction module, for extracting all color change intervals from the bianry image of bill red waterline region;
Variable color determination module, for judging that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judges that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur.
As the further improvement of described a kind of bill images red waterline variable color detection system, described color change interval extraction module comprises:
Image statistics module, for adding up by column the first row from bill red waterline region bianry image;
Ratio computing module, for adding up the black picture element number when prostatitis, and calculating the ratio with bill red waterline region bianry image height, obtaining the variable color ratio when prostatitis;
First judge module, for judging whether the variable color ratio when prostatitis is greater than default first threshold, if so, then records the sequence number when prostatitis, obtains the start sequence number of current color change interval, and perform the second judge module; Otherwise, then add up next column and return execution ratio computing module;
Second judge module, for adding up next column and calculating its variable color ratio, judges whether its variable color ratio is greater than default first threshold, if so, then returns and re-execute the second judge module; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number of current color change interval, and then extracts color change interval;
Add up complete judge module, for judging whether that all row have added up complete, if so, then terminating to add up and performing variable color determination module; Otherwise, then add up next column and return execution ratio computing module.
As the further improvement of described a kind of bill images red waterline variable color detection system, described second judge module also comprises:
Width judge module, for according to the start sequence number of current color change interval with terminate sequence number, calculates the width of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform the complete judge module of statistics; Otherwise, then the complete judge module of statistics is directly performed.
The invention has the beneficial effects as follows:
A kind of bill images of the present invention red waterline variable color detection method by gathering successively bill images, gray processing, extraction and binary conversion treatment, and then detect the whether variable color of the red waterline of bill images according to the black picture element in image, without the need to manual operation, efficiently solve the invalid note phenomenon caused because ticket information amount in Chinese character is stained in batch bill automatic business processing process, greatly reduce the time of manual sorting bill, improve the efficiency of batch bill process.
Another beneficial effect of the present invention is:
A kind of bill images red waterline variable color detection system of the present invention is processed bill images by image capture module, color space conversion module, red waterline region extraction module, binary conversion treatment module and variable color detection module, and then detect the whether variable color of the red waterline of bill images, without the need to manual operation, efficiently solve the invalid note phenomenon caused because ticket information amount in Chinese character is stained in batch bill automatic business processing process, greatly reduce the time of manual sorting bill, improve the efficiency of batch bill process.
Accompanying drawing explanation
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described further:
Fig. 1 is the flow chart of steps of a kind of bill images of the present invention red waterline variable color detection method;
Fig. 2 is the flow chart of steps of a kind of bill images of the present invention red waterline variable color detection method step e;
Fig. 3 is the flow chart of steps of a kind of bill images of the present invention red waterline variable color detection method step e 1;
Fig. 4 is the block diagram of a kind of bill images of the present invention red waterline variable color detection system.
Embodiment
With reference to figure 1, a kind of bill images of the present invention red waterline variable color detection method, comprises the following steps:
A, bill images to be gathered, obtain bill coloured image;
B, bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtain bill Y channel image;
The red waterline regional location coordinate that C, basis are preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
D, Threshold segmentation process is carried out to the red waterline area image of bill, obtain bill red waterline region bianry image;
E, according to bill red waterline region bianry image, judge whether red waterline region variable color occurs.
Further, the circular extracting Y channel value is:
;
Wherein, i=1, 2 ... W, j=1, 2 ... H, i represents the horizontal ordinate in bill images, j represents the ordinate in bill images, W is the width of bill images, H is the height of bill images, R [i, j] represent horizontal ordinate to be i and ordinate be redness (R) component value of the RGB color space at the pixel place of j, G [i, j] represent horizontal ordinate to be i and ordinate be green (G) component value of the RGB color space at the pixel place of j, B [i, j] represent horizontal ordinate to be i and ordinate be blueness (B) component value of the RGB color space at the pixel place of j, Y [i, j] represent XYZ color space Y passage horizontal ordinate to be i and ordinate be the value at the pixel place of j, Y [i, j] ∈ [0, 255].
With reference to figure 2, as the further improvement of described a kind of bill images red waterline variable color detection method, described step e comprises:
E1, from the bianry image of bill red waterline region, extract all color change intervals;
E2, judge that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judge that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur, and fills in and meets specification.
With reference to figure 3, as the further improvement of described a kind of bill images red waterline variable color detection method, described step e 1 comprises:
E11, to add up by column from the first row of bill red waterline region bianry image;
E12, statistics when the black picture element number in prostatitis, and calculate the ratio with bill red waterline region bianry image height, obtain the variable color ratio when prostatitis;
Whether E13, the variable color ratio of judgement when prostatitis are greater than default first threshold, if so, then record the sequence number C1 when prostatitis, obtain the start sequence number of current color change interval, and perform step e 14; Otherwise, then next column is added up and returns performing step e 12;
E14, statistics next column calculate its variable color ratio, judge whether its variable color ratio is greater than default first threshold, if so, then return and re-execute step e 14; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number C2 of current color change interval, and then extracts color change interval;
E15, judge whether that all row have added up complete, if so, then terminate to add up and perform step e 2; Otherwise, then next column is added up and returns performing step e 12.
As the further improvement of described a kind of bill images red waterline variable color detection method, in described step e 14 and then also comprise after extracting color change interval:
According to start sequence number C1 and the end sequence number C2 of current color change interval, calculate the width C=C2-C1 of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform step e 15; Otherwise, then directly step e 15 is performed.
As the further improvement of described a kind of bill images red waterline variable color detection method, carry out Threshold segmentation process to the red waterline area image of bill in described step D, it is specially:
According to the segmentation threshold preset and following formula, the pixel in the red waterline area image of bill is processed;
;
Wherein, i represents the horizontal ordinate in bill red waterline area image and bill red waterline region bianry image, j represents the ordinate in bill red waterline area image and bill red waterline region bianry image, D [i, j] represent horizontal ordinate in the bianry image of bill red waterline region to be i and ordinate be the value at the pixel place of j, RE [i, j] represents horizontal ordinate in the red waterline area image of bill to be i and ordinate is the value at the pixel place of j, and th represents segmentation threshold.As D [i, j]=0, it is expressed as black pixel point.
Further, described segmentation threshold can for the fixed threshold preset, and global threshold dividing method also can be adopted to obtain, and in embodiments of the present invention, th is preset as 165.
With reference to figure 4, a kind of bill images of the present invention red waterline variable color detection system, comprising:
Image capture module, for gathering bill images, obtains bill coloured image;
Color space conversion module, for bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtains bill Y channel image;
Red waterline region extraction module, for according to the red waterline regional location coordinate preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
Binary conversion treatment module, for carrying out Threshold segmentation process to the red waterline area image of bill, obtains bill red waterline region bianry image;
Variable color detection module, for according to bill red waterline region bianry image, judges whether red waterline region variable color occurs.
As the further improvement of described a kind of bill images red waterline variable color detection system, described variable color detection module comprises:
Color change interval extraction module, for extracting all color change intervals from the bianry image of bill red waterline region;
Variable color determination module, for judging that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judges that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur.
As the further improvement of described a kind of bill images red waterline variable color detection system, described color change interval extraction module comprises:
Image statistics module, for adding up by column the first row from bill red waterline region bianry image;
Ratio computing module, for adding up the black picture element number when prostatitis, and calculating the ratio with bill red waterline region bianry image height, obtaining the variable color ratio when prostatitis;
First judge module, for judging whether the variable color ratio when prostatitis is greater than default first threshold, if so, then records the sequence number when prostatitis, obtains the start sequence number of current color change interval, and perform the second judge module; Otherwise, then add up next column and return execution ratio computing module;
Second judge module, for adding up next column and calculating its variable color ratio, judges whether its variable color ratio is greater than default first threshold, if so, then returns and re-execute the second judge module; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number of current color change interval, and then extracts color change interval;
Add up complete judge module, for judging whether that all row have added up complete, if so, then terminating to add up and performing variable color determination module; Otherwise, then add up next column and return execution ratio computing module.
As the further improvement of described a kind of bill images red waterline variable color detection system, described second judge module also comprises:
Width judge module, for according to the start sequence number of current color change interval with terminate sequence number, calculates the width of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform the complete judge module of statistics; Otherwise, then the complete judge module of statistics is directly performed.
From foregoing, the present invention takes full advantage of the feature of bill images itself, principle is simple, calculated amount is little, utilize scanning bill images correctly to detect the whether variable color of the red waterline of bill images, without the need to manual operation, efficiently solve the invalid note phenomenon caused because ticket information amount in Chinese character is stained in batch bill automatic business processing process, reduce the time of manual sorting bill, improve the efficiency of batch bill process.
More than that better enforcement of the present invention is illustrated, but the invention is not limited to described embodiment, those of ordinary skill in the art also can make all equivalent variations or replacement under the prerequisite without prejudice to spirit of the present invention, and these equivalent distortion or replacement are all included in the application's claim limited range.
Claims (9)
1. a bill images red waterline variable color detection method, is characterized in that, comprise the following steps:
A, bill images to be gathered, obtain bill coloured image;
B, bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtain bill Y channel image;
The red waterline regional location coordinate that C, basis are preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
D, Threshold segmentation process is carried out to the red waterline area image of bill, obtain bill red waterline region bianry image;
E, according to bill red waterline region bianry image, judge whether red waterline region variable color occurs.
2. a kind of bill images according to claim 1 red waterline variable color detection method, is characterized in that: described step e comprises:
E1, from the bianry image of bill red waterline region, extract all color change intervals;
E2, judge that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judge that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur.
3. a kind of bill images according to claim 2 red waterline variable color detection method, is characterized in that: described step e 1 comprises:
E11, to add up by column from the first row of bill red waterline region bianry image;
E12, statistics when the black picture element number in prostatitis, and calculate the ratio with bill red waterline region bianry image height, obtain the variable color ratio when prostatitis;
Whether E13, the variable color ratio of judgement when prostatitis are greater than default first threshold, if so, then record the sequence number when prostatitis, obtain the start sequence number of current color change interval, and perform step e 14; Otherwise, then next column is added up and returns performing step e 12;
E14, statistics next column calculate its variable color ratio, judge whether its variable color ratio is greater than default first threshold, if so, then return and re-execute step e 14; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number of current color change interval, and then extracts color change interval;
E15, judge whether that all row have added up complete, if so, then terminate to add up and perform step e 2; Otherwise, then next column is added up and returns performing step e 12.
4. a kind of bill images according to claim 3 red waterline variable color detection method, is characterized in that: in described step e 14 and then also comprise after extracting color change interval:
According to start sequence number and the end sequence number of current color change interval, calculate the width of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform step e 15; Otherwise, then directly step e 15 is performed.
5. a kind of bill images according to claim 1 red waterline variable color detection method, is characterized in that: carry out Threshold segmentation process to the red waterline area image of bill in described step D, it is specially:
According to the segmentation threshold preset and following formula, the pixel in the red waterline area image of bill is processed;
;
Wherein, i represents the horizontal ordinate in bill red waterline area image and bill red waterline region bianry image, j represents the ordinate in bill red waterline area image and bill red waterline region bianry image, D [i, j] represent horizontal ordinate in the bianry image of bill red waterline region to be i and ordinate be the value at the pixel place of j, RE [i, j] represents horizontal ordinate in the red waterline area image of bill to be i and ordinate is the value at the pixel place of j, and th represents segmentation threshold.
6. a bill images red waterline variable color detection system, is characterized in that, comprising:
Image capture module, for gathering bill images, obtains bill coloured image;
Color space conversion module, for bill coloured image is converted to XYZ color space by rgb space, and extracts Y channel value, and then obtains bill Y channel image;
Red waterline region extraction module, for according to the red waterline regional location coordinate preset, extracts and obtains the red waterline area image of bill from bill Y channel image;
Binary conversion treatment module, for carrying out Threshold segmentation process to the red waterline area image of bill, obtains bill red waterline region bianry image;
Variable color detection module, for according to bill red waterline region bianry image, judges whether red waterline region variable color occurs.
7. a kind of bill images according to claim 6 red waterline variable color detection system, is characterized in that: described variable color detection module comprises:
Color change interval extraction module, for extracting all color change intervals from the bianry image of bill red waterline region;
Variable color determination module, for judging that the width whether having color change interval in all color change intervals is greater than default decision threshold, if so, then judges that variable color occurs in bill images red waterline region; Otherwise, then judge that the red waterline region of bill images variable color does not occur.
8. a kind of bill images according to claim 7 red waterline variable color detection system, is characterized in that: described color change interval extraction module comprises:
Image statistics module, for adding up by column the first row from bill red waterline region bianry image;
Ratio computing module, for adding up the black picture element number when prostatitis, and calculating the ratio with bill red waterline region bianry image height, obtaining the variable color ratio when prostatitis;
First judge module, for judging whether the variable color ratio when prostatitis is greater than default first threshold, if so, then records the sequence number when prostatitis, obtains the start sequence number of current color change interval, and perform the second judge module; Otherwise, then add up next column and return execution ratio computing module;
Second judge module, for adding up next column and calculating its variable color ratio, judges whether its variable color ratio is greater than default first threshold, if so, then returns and re-execute the second judge module; Otherwise then record is when the sequence number in prostatitis, draws the end sequence number of current color change interval, and then extracts color change interval;
Add up complete judge module, for judging whether that all row have added up complete, if so, then terminating to add up and performing variable color determination module; Otherwise, then add up next column and return execution ratio computing module.
9. a kind of bill images according to claim 8 red waterline variable color detection system, is characterized in that: described second judge module also comprises:
Width judge module, for according to the start sequence number of current color change interval with terminate sequence number, calculates the width of current color change interval, and judge whether it is greater than default Second Threshold, if so, then record is carried out to the width of this color change interval, and perform the complete judge module of statistics; Otherwise, then the complete judge module of statistics is directly performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510340977.2A CN104952143A (en) | 2015-06-18 | 2015-06-18 | Color change detection method and color change detection system for red waterlines of bill images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510340977.2A CN104952143A (en) | 2015-06-18 | 2015-06-18 | Color change detection method and color change detection system for red waterlines of bill images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104952143A true CN104952143A (en) | 2015-09-30 |
Family
ID=54166767
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510340977.2A Pending CN104952143A (en) | 2015-06-18 | 2015-06-18 | Color change detection method and color change detection system for red waterlines of bill images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104952143A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105225335A (en) * | 2015-10-28 | 2016-01-06 | 深圳怡化电脑股份有限公司 | A kind of stained recognition methods of paper money number and system |
CN106096601A (en) * | 2016-06-06 | 2016-11-09 | 深圳辰通智能股份有限公司 | The method and system of character types in a kind of automatic detection bill |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030068077A1 (en) * | 2001-10-10 | 2003-04-10 | Naohiko Koakutsu | Negotiable instrument processing apparatus and negotiable instrument processing method |
CN102542660A (en) * | 2011-12-05 | 2012-07-04 | 中钞实业有限公司 | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics |
CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
CN104063859A (en) * | 2014-01-27 | 2014-09-24 | 辰通智能设备(深圳)有限公司 | Method and system for detecting number of figures of account in figures in note image |
CN104574642A (en) * | 2015-01-30 | 2015-04-29 | 广州广电运通金融电子股份有限公司 | Method and device for detecting color-variable printing ink of renminbi on basis of Lab color spaces |
-
2015
- 2015-06-18 CN CN201510340977.2A patent/CN104952143A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030068077A1 (en) * | 2001-10-10 | 2003-04-10 | Naohiko Koakutsu | Negotiable instrument processing apparatus and negotiable instrument processing method |
CN102542660A (en) * | 2011-12-05 | 2012-07-04 | 中钞实业有限公司 | Bill anti-counterfeiting identification method based on bill watermark distribution characteristics |
CN103208004A (en) * | 2013-03-15 | 2013-07-17 | 北京英迈杰科技有限公司 | Automatic recognition and extraction method and device for bill information area |
CN104063859A (en) * | 2014-01-27 | 2014-09-24 | 辰通智能设备(深圳)有限公司 | Method and system for detecting number of figures of account in figures in note image |
CN104574642A (en) * | 2015-01-30 | 2015-04-29 | 广州广电运通金融电子股份有限公司 | Method and device for detecting color-variable printing ink of renminbi on basis of Lab color spaces |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105225335A (en) * | 2015-10-28 | 2016-01-06 | 深圳怡化电脑股份有限公司 | A kind of stained recognition methods of paper money number and system |
CN106096601A (en) * | 2016-06-06 | 2016-11-09 | 深圳辰通智能股份有限公司 | The method and system of character types in a kind of automatic detection bill |
CN106096601B (en) * | 2016-06-06 | 2019-06-18 | 深圳辰通智能股份有限公司 | The method and system of character types in a kind of automatic detection bill |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107578035B (en) | Human body contour extraction method based on super-pixel-multi-color space | |
CN103258198B (en) | Character extracting method in a kind of form document image | |
CN102043950B (en) | Vehicle outline recognition method based on canny operator and marginal point statistic | |
CN103235938B (en) | The method and system of car plate detection and indentification | |
CN109284758B (en) | Invoice seal eliminating method and device and computer storage medium | |
CN110399875A (en) | A kind of form of general use information extracting method based on deep learning and pixel projection | |
CN108133216B (en) | Nixie tube reading identification method capable of realizing decimal point reading based on machine vision | |
CN103824373B (en) | A kind of bill images amount of money sorting technique and system | |
CN105005969B (en) | A kind of bill images alter detection method and system | |
CN110309806B (en) | Gesture recognition system and method based on video image processing | |
CN104298982A (en) | Text recognition method and device | |
CN104361336A (en) | Character recognition method for underwater video images | |
CN109146878A (en) | A kind of method for detecting impurities based on image procossing | |
CN103914833B (en) | The method and system that a kind of automatic detection bill is the most incomplete | |
CN102436575A (en) | Method for automatically detecting and classifying station captions | |
CN102332157B (en) | Method for eliminating shadow | |
CN104966348A (en) | Ticket image element integrity detection method and system | |
CN104899839A (en) | Ghost quick-inhibition method based on ViBe algorithm | |
CN104952077B (en) | A kind of bill images greasy dirt detection method and system | |
CN106097368A (en) | A kind of recognition methods in veneer crack | |
CN104732220A (en) | Specific color human body detection method oriented to surveillance videos | |
CN106096667A (en) | Bill images sorting technique based on SVM | |
CN103679146A (en) | Safety belt intelligent detection method based on high-pass filter and Hough conversion | |
CN108010040A (en) | A kind of method for separating medical bill red seal | |
CN108288275A (en) | A kind of mechanically harvested seed cotton method for detecting impurities based on mobile intelligent terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: Shenzhen Nanshan District City, Guangdong province 518000 white pine Luxili Nangang first industrial park, building seven floor 1-3 Applicant after: TOUCHSTONE INTELLIGENCE SYSTEM (SHENZHEN) CO., LTD. Address before: Shenzhen Nanshan District City, Guangdong province 518000 white pine Luxili Nangang first Industrial Park 7 Applicant before: Automated Touchstone Machines Limited |
|
COR | Change of bibliographic data | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150930 |
|
RJ01 | Rejection of invention patent application after publication |