CN104318238A - Method for extracting crown word numbers from scanned banknote images in banknote detection module - Google Patents
Method for extracting crown word numbers from scanned banknote images in banknote detection module Download PDFInfo
- Publication number
- CN104318238A CN104318238A CN201410627642.4A CN201410627642A CN104318238A CN 104318238 A CN104318238 A CN 104318238A CN 201410627642 A CN201410627642 A CN 201410627642A CN 104318238 A CN104318238 A CN 104318238A
- Authority
- CN
- China
- Prior art keywords
- crown word
- word number
- banknote
- point
- character
- 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
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention discloses a method for extracting crown word numbers from scanned banknote images in a banknote detection module. The method comprises the following steps that the green ray of an image sensor is used for banknote collecting to form source images, the boundaries, in the source images, of the banknote images are found by adopting the mode of scanning boundary points, and then the banknote images are turned over and corrected to the horizontal state; feature points are extracted, and face value and orientation of banknotes are identified according to the obtained feature points; crown word number areas are determined, binarization processing is adopted for the crown word number areas, the obtained binarization images of the crown word number areas are searched for the boundaries containing all crown word numbers, then each single crowd word number is segmented, and a support vector machine identifies and processes the segmented and normalized single word images. The method for extracting the crown word numbers from the scanned banknote images provides a powerful support for identifying the authenticity of banknotes, crown word numbers can be identified accurately, the ability to identify the authenticity of banknotes is greatly improved, and the property safety of the financial department is effectively protected.
Description
Technical field
The present invention relates to a kind of method banknote figure of scanning being extracted to crown word number in currency checking module.
Background technology
In the China of rapid economic development, the circulation of bank note is also in multiplication, other bank note various types of in large-scale circulation, make the pressure of interested regulatory authorities also increasing, work just can not be exhaustive, more effectively can help the work of supervision department and financial institution after adopting crown word number identification, also improve the property safety coefficient of the people.Traditional crown word number identification method not for different denominations towards bank note do different process, to thus bank note all adopt identical algorithm process, cause the discrimination of bank note not high; In addition, the recognition methods of traditional crown word number needs the gray-scale value of each pixel to banknote image to calculate, and causes calculated amount large, and equipment carries out identifying that the time needed for crown word number on bank note is longer.Further, on usual market, the bank note of low-denomination is larger than the large-denomination amount of paper money in circulation, and spot can be more serious, and when adopting the crown word number on same algorithm identification bank note, the precision identified is not high.
Summary of the invention
The invention provides a kind of method banknote figure of scanning being extracted to crown word number in currency checking module, discrimination is high and accurate.
In currency checking module of the present invention, the banknote figure of scanning is extracted to the method for crown word number, comprises the following steps:
Step 1, forms source images by the green glow of imageing sensor to banknote collection, is adopting the mode of scanning boundary point to find the border of banknote image in source images, is then overturning banknote image and be corrected to horizontality;
Step 2, carries out feature point extraction, according to the unique point obtained carry out face amount towards identification;
Step 3, determine crown word number region, crown word number region adopts binary conversion treatment, and the crown word number region binary image obtained finds the border comprising all crown word number, then carry out single crown word number segmentation, for segmentation and normalized single character picture carries out support vector machine identifying processing.
In currency checking module of the present invention, the banknote figure of scanning is extracted to the method for crown word number, adopting the mode of scanning boundary point to find the border of the image of bank note in source images, then flipped image is corrected to horizontality, this completes the pre-service of image.After the pre-treatment carry out feature point extraction, according to these unique points obtained carry out face amount towards identification, when determine face amount towards after just can find crown word number region accurately, next like this, just overall Binarization methods or local binarization algorithm are adopted to crown word number region, again crown word number region obtained in the previous step binary image is found to the border comprising all crown word number, then carry out single crown word number segmentation, for segmentation and normalized single character picture carries out support vector machine identifying processing.Banknote figure of the present invention extracts the method for crown word number, first level correction process is carried out to banknote image, banknote image position in source images can be reduced to occur at random and the error caused, then eigenwert is extracted, determine face amount towards, can identify crown word number more effectively and accurately, the gray-scale value that only need calculate eigenwert in addition carries out mating, lower calculated amount, improve the speed of crown word number identification.Banknote figure to scanning of the present invention extracts the method for crown word number, financial associated mechanisms is allowed to obtain fine Data support, the true and false identification strong support of bank note can be given, and can accurately crown word number be identified, so just improve the true and false recognition capability of bank note greatly, effectively maintain the property safety of financial department.
Accompanying drawing explanation
Fig. 1 is the method flow diagram in currency checking module, the banknote figure of scanning being extracted to crown word number.
Embodiment
The present embodiment adopts based on a kind of currency checking module of DM642 and FPGA, is divided into two steps to carry out, and the first step uses FPGA controls CIS(optical sensor) green glow collection image, image is kept in SDRAM.Second step uses the algorithm process in DM642 to be processed by the image in SDRAM, finally obtains paper money number and crown word number area image.Adopt CIS(optical sensor) use green single light source to carry out image scanning collection, therefore obtaining is exactly gray level image.Then Image semantic classification is carried out to this gray level image, calculate rotation matrix, then histogram equalization process is carried out, face amount is carried out towards identification according to the algorithm of Feature Points Matching, then find crown word number region carry out intercepting and carry out binary conversion treatment to this region, subsequently Character segmentation is carried out to the image after binaryzation.
Concrete grammar and step: in face amount towards when identification, adopt Feature Points Matching algorithm to identify.Concrete steps and gordian technique as follows,
Ask for rotation matrix, find the frontier point of bank note in source images, then according to least square method, the point that every bar border is looked for is fitted to straight line.So just can go out four summits of bank note according to the intersection point calculation of four straight lines, try to achieve the coordinate of bank note central point further.Again can calculate the anglec of rotation of bank note according to any boundary straight line, obtain rotation matrix
, can be so just that reference point carries out rotation correction banknote image with centre coordinate.
Training matching template, for bank note special denomination, the gray-scale value of a certain location point is a fixing scope, and this scope is found out by the object of training exactly.Then judge whether new certain location point of banknote image mates, in the intensity value ranges of the gray-scale value seeing this point exactly whether in a template this position, if this Point matching just can be thought in this scope.In source images, choose certain position to have the larger point of otherness, in other words, bank note a certain towards in certain location point and other gray scale naked eyes towards same position point just can be easy to differentiate.If the boundary setting not match point in identifying schemes is that the most very much not match point 12, if exceed this number just think that this image does not mate.
Face amount is towards identification, follow the result of the calculating according to above-mentioned steps, according to unique point coordinate setting in template to the gray-scale value of source images same coordinate point, judge this gray-scale value whether in the scope of template training fast, then subsidiary according to this template bank note information just can carry out face amount fast towards identification (thus determine the face amount of bank note towards).
In traditional face amount towards in identification, need to calculate the gray-scale value of each point in former figure, and then carry out whole Image Reversal correction, and then carry out Similarity measures with template, in the value of optimum, finally carry out judgement identify, such algorithm arrangement calculates quite large, and for the equipment of true-time operation, can not meet far away, therefore this face amount has a significant effect towards recognition methods.
Determining that face amount is towards rear, according to the feature that the version of bank note has, such as certain zone marker of image is different, so just this region can be intercepted and calculate its gray scale total value, compare with same area gray scale total value in template, as long as meet corresponding error range just can judge bank note version fast.
After completing above-mentioned steps, intercept crown word number place towards image-region because certainly spot to some extent on paper in fiduciary circulation process, in such scheme, just binary conversion treatment is carried out to the crown word number area image of intercepting.Experience is determined, low-denomination is certainly large than large-denomination circulation, like this will spot more serious, institute's this programme adopts the method for classification process, but each denomination also has spot in various degree, so just require will there be adaptive ability when binary conversion treatment, therefore adopt the global threshold binary conversion treatment of Ostu algorithm and maximum between-cluster variance algorithm in this programme, the feature of this algorithm can the ability automatically chosen of the fast segmentation threshold of processing speed.Image is divided into background and target two class by it, calculates inter-class variance maximal value, obtain optimal threshold by search.Another one adopts local threshold algorithm (niblack algorithm), and niblack method comparison is simple, and in computed image, its adjacent statistical property of each pixel carrys out judgment threshold.By a large amount of test data, this programme setting is for the employing niblack algorithm of 100 yuan of denominations, and the employing Ostu algorithm of other denominations, traditional binaryzation scheme only adopts the not specific impact considering spot factor of a kind of algorithm.
Projection algorithm after binaryzation: calculate each projection width of crown word number character in the vertical direction and in horizontal direction according to projection algorithm, choose that width numerical value maximum as the height and width of crown word number square boundary, partitioning algorithm behind crown word number border, for the partitioning algorithm of crown word number character, carry out based on projection algorithm equally, can have in the horizontal and vertical directions each connected component character and independently project.So just can calculate the area coordinate of each character, finally have the character of clear and definite coordinate to carry out dividing processing to these.Cause because crown word number character size is not of uniform size, so the process that will be normalized.
Crown word number Character mother plate is trained: obtain character picture after normalization according to above step, these a large amount of single characters carry out 36 kinds of images (arabic numeral of 1 to 9 and 26 letters) classification, be further divided into training set and test set in character type for each, carry out template training.Based on the character recognition of SVM algorithm.For the image of each input, calculate this eigenvectors matrix, utilize the SVM model of crown word number to carry out decision-making judgement, identify crown word number.
Claims (7)
1. in currency checking module, the banknote figure of scanning is extracted to a method for crown word number, it is characterized in that, comprise the following steps:
Step 1, forms source images by the green glow of imageing sensor to banknote collection, is adopting the mode of scanning boundary point to find the border of banknote image in source images, is then overturning banknote image and be corrected to horizontality;
Step 2, carries out feature point extraction, according to the unique point obtained carry out face amount towards identification;
Step 3, determine crown word number region, crown word number region adopts binary conversion treatment, and the crown word number region binary image obtained finds the border comprising all crown word number, then carry out single crown word number segmentation, for segmentation and normalized single character picture carries out support vector machine identifying processing.
2. in currency checking module according to claim 1, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: comprise following sub-step in step 1,
Step 1.1, according to the difference of banknote image edge gray-scale value, finds the frontier point of banknote image;
Step 1.2, at least looks for two points to fit to straight line on every bar border according to least square method, and the intersection point of four straight lines is four summits of banknote image, calculates the coordinate of banknote image central point further;
Step 1.3, calculates the anglec of rotation of bank note, obtains rotation matrix according to any boundary straight line
, be that reference point carries out rotation correction banknote image with centre coordinate.
3. in currency checking module according to claim 1, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: comprise following sub-step in step 2,
Step 2.1, training coupling set: a large amount of different denominations towards source images in choose certain position to have the larger point of otherness, namely bank note a certain towards in certain location point to differ larger point with other gray scales towards same position point as unique point, the same face is averaged as trained values to the gray-scale value of the unique point of this position of face amount;
Step 2,2, determine a certain banknote image face amount towards: according to the gray-scale value of unique point coordinate setting to source images same coordinate point, judge this gray-scale value with which trained values in step 2.1 mates, thus judge the face amount of this bank note towards.
4. in currency checking module according to claim 1, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: comprise following sub-step in step 3,
Step 3.1, adopts Binarization methods to carry out computing to banknote image;
Step 3.2, calculates each projection width of crown word number character in the vertical direction and in horizontal direction according to projection algorithm, chooses that width numerical value maximum as the height and width of crown word number square boundary;
Step 3.3, segmentation crown word number character: the area coordinate calculating each crown word number character based on projection algorithm, carries out segmentation and normalized to there being the crown word number character of clear and definite coordinate;
Step 3.4, classifies to the normalization character picture obtained, and repeats above-mentioned steps and obtains a large amount of character pictures, is divided into training set test set, carries out masterplate training, obtain the training pattern of each class character each class character;
Step 3.5, based on the character recognition of SVM algorithm, to the character picture of each input, calculates this eigenvectors matrix, utilizes the training pattern of each class crown word number character to carry out decision-making judgement, identify crown word number.
5. in currency checking module according to claim 4, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: adopt different Binarization methods to carry out computing to the bank note of different denominations.
6. in currency checking module according to claim 5, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: maximum between-cluster variance algorithm is adopted to the banknote image below 100 yuan of denominations.
7. in currency checking module according to claim 5, the banknote figure of scanning is extracted to the method for crown word number, it is characterized in that: local threshold algorithm is adopted to the banknote image of 100 yuan of denominations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410627642.4A CN104318238A (en) | 2014-11-10 | 2014-11-10 | Method for extracting crown word numbers from scanned banknote images in banknote detection module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410627642.4A CN104318238A (en) | 2014-11-10 | 2014-11-10 | Method for extracting crown word numbers from scanned banknote images in banknote detection module |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104318238A true CN104318238A (en) | 2015-01-28 |
Family
ID=52373467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410627642.4A Pending CN104318238A (en) | 2014-11-10 | 2014-11-10 | Method for extracting crown word numbers from scanned banknote images in banknote detection module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104318238A (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160756A (en) * | 2015-08-18 | 2015-12-16 | 深圳怡化电脑股份有限公司 | Paper money facing direction recognition method and device |
| CN105243730A (en) * | 2015-10-28 | 2016-01-13 | 深圳怡化电脑股份有限公司 | Banknote identification method and system |
| CN105261109A (en) * | 2015-07-24 | 2016-01-20 | 广州广电运通金融电子股份有限公司 | Identification method of prefix letter of banknote |
| CN105336035A (en) * | 2015-10-28 | 2016-02-17 | 深圳怡化电脑股份有限公司 | Smudged serial number image classification method and system |
| CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
| CN105761351A (en) * | 2016-01-08 | 2016-07-13 | 东方通信股份有限公司 | Structure characteristic-based character recognition method |
| CN105913547A (en) * | 2016-04-07 | 2016-08-31 | 四川大学 | Bill optical identification method and device |
| CN106355743A (en) * | 2015-07-14 | 2017-01-25 | 深圳怡化电脑股份有限公司 | Banknote version identification method and device |
| CN106683257A (en) * | 2016-12-30 | 2017-05-17 | 深圳怡化电脑股份有限公司 | Serial number location method and device |
| CN106780960A (en) * | 2015-11-18 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note currency type and system |
| CN106780961A (en) * | 2015-11-23 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note face amount and system |
| CN106846610A (en) * | 2017-01-20 | 2017-06-13 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note version and device |
| CN106875553A (en) * | 2017-01-20 | 2017-06-20 | 浙江维融办公用品有限公司 | A kind of point currency examination all-in-one and its banknote detection method with POS payment functions |
| CN106874909A (en) * | 2017-01-18 | 2017-06-20 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
| CN107358718A (en) * | 2017-07-10 | 2017-11-17 | 深圳怡化电脑股份有限公司 | A kind of crown word number identification method, device, equipment and storage medium |
| CN107464335A (en) * | 2017-08-03 | 2017-12-12 | 恒银金融科技股份有限公司 | Paper currency crown word number positioning method |
| CN107481389A (en) * | 2017-08-03 | 2017-12-15 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| CN107590900A (en) * | 2017-09-15 | 2018-01-16 | 深圳怡化电脑股份有限公司 | A kind of crown word number image acquiring method, device, equipment and storage medium |
| CN107610320A (en) * | 2017-09-06 | 2018-01-19 | 深圳怡化电脑股份有限公司 | A kind of bank slip recognition method and apparatus |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN108073921A (en) * | 2016-11-10 | 2018-05-25 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of banknote information and device |
| CN108154596A (en) * | 2016-12-04 | 2018-06-12 | 湖南丰汇银佳科技股份有限公司 | A kind of double comb paper money discrimination method based on images match |
| CN108320374A (en) * | 2018-02-08 | 2018-07-24 | 中南大学 | A kind of multinational paper money number character identifying method based on finger image |
| CN108537237A (en) * | 2018-04-04 | 2018-09-14 | 深圳怡化电脑股份有限公司 | Characteristic area extracting method, device, equipment and the storage medium of bill |
| CN108734845A (en) * | 2017-04-20 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Detect the method and device of paper money number |
| CN108765690A (en) * | 2018-04-28 | 2018-11-06 | 深圳怡化电脑股份有限公司 | Vision sensor data processing method, device, system and financial self-service equipment |
| CN108806058A (en) * | 2017-05-05 | 2018-11-13 | 深圳怡化电脑股份有限公司 | A kind of paper currency detecting method and device |
| CN111104946A (en) * | 2019-12-24 | 2020-05-05 | 江苏国光信息产业股份有限公司 | Paper currency crown word number character segmentation method based on SVM classifier |
| CN111382696A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111833511A (en) * | 2020-06-09 | 2020-10-27 | 武汉卓目科技有限公司 | Method and device for improving identification rate of prefix number based on multi-channel synthesis technology |
| CN112307867A (en) * | 2020-03-03 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for outputting information |
| CN117671849A (en) * | 2023-12-14 | 2024-03-08 | 浙江南星科技有限公司 | Vertical image scanning banknote counter adopting banknote sliding structure |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521911A (en) * | 2011-12-16 | 2012-06-27 | 尤新革 | Identification method of crown word number (serial number) of bank note |
| KR101270173B1 (en) * | 2007-08-23 | 2013-05-31 | 삼성전자주식회사 | Method and apparatus for extracting feature points from digital image |
| CN203588363U (en) * | 2013-10-23 | 2014-05-07 | 东方通信股份有限公司 | Banknote offering machine core with function of identifying serial number on banknote |
-
2014
- 2014-11-10 CN CN201410627642.4A patent/CN104318238A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101270173B1 (en) * | 2007-08-23 | 2013-05-31 | 삼성전자주식회사 | Method and apparatus for extracting feature points from digital image |
| CN102521911A (en) * | 2011-12-16 | 2012-06-27 | 尤新革 | Identification method of crown word number (serial number) of bank note |
| CN203588363U (en) * | 2013-10-23 | 2014-05-07 | 东方通信股份有限公司 | Banknote offering machine core with function of identifying serial number on banknote |
Non-Patent Citations (2)
| Title |
|---|
| 沈瑛: "身份证识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈杰: "基于多国纸币版面和号码识别的研究与应用", 《中国优秀硕士论文全文数据库》 * |
Cited By (49)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355743A (en) * | 2015-07-14 | 2017-01-25 | 深圳怡化电脑股份有限公司 | Banknote version identification method and device |
| CN105261109A (en) * | 2015-07-24 | 2016-01-20 | 广州广电运通金融电子股份有限公司 | Identification method of prefix letter of banknote |
| CN105261109B (en) * | 2015-07-24 | 2017-10-31 | 广州广电运通金融电子股份有限公司 | A kind of bill crown word number recognition methods |
| WO2017016240A1 (en) * | 2015-07-24 | 2017-02-02 | 广州广电运通金融电子股份有限公司 | Banknote serial number identification method |
| CN105160756A (en) * | 2015-08-18 | 2015-12-16 | 深圳怡化电脑股份有限公司 | Paper money facing direction recognition method and device |
| CN105243730A (en) * | 2015-10-28 | 2016-01-13 | 深圳怡化电脑股份有限公司 | Banknote identification method and system |
| CN105336035A (en) * | 2015-10-28 | 2016-02-17 | 深圳怡化电脑股份有限公司 | Smudged serial number image classification method and system |
| CN105243730B (en) * | 2015-10-28 | 2018-02-09 | 深圳怡化电脑股份有限公司 | Paper Currency Identification and system |
| CN105336035B (en) * | 2015-10-28 | 2019-02-01 | 深圳怡化电脑股份有限公司 | A kind of method and system of dirty crown word number image classification |
| CN106780960A (en) * | 2015-11-18 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note currency type and system |
| CN106780961A (en) * | 2015-11-23 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note face amount and system |
| CN105654609A (en) * | 2015-12-29 | 2016-06-08 | 深圳怡化电脑股份有限公司 | Paper money processing method and paper money processing system |
| CN105761351A (en) * | 2016-01-08 | 2016-07-13 | 东方通信股份有限公司 | Structure characteristic-based character recognition method |
| CN105913547A (en) * | 2016-04-07 | 2016-08-31 | 四川大学 | Bill optical identification method and device |
| CN105913547B (en) * | 2016-04-07 | 2018-11-20 | 四川大学 | A kind of account ticket optical identification method and device |
| CN108073921B (en) * | 2016-11-10 | 2021-10-08 | 深圳怡化电脑股份有限公司 | Method and device for identifying banknote information |
| CN108073921A (en) * | 2016-11-10 | 2018-05-25 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of banknote information and device |
| CN108154596A (en) * | 2016-12-04 | 2018-06-12 | 湖南丰汇银佳科技股份有限公司 | A kind of double comb paper money discrimination method based on images match |
| CN106683257A (en) * | 2016-12-30 | 2017-05-17 | 深圳怡化电脑股份有限公司 | Serial number location method and device |
| CN106874909A (en) * | 2017-01-18 | 2017-06-20 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN106874909B (en) * | 2017-01-18 | 2019-10-11 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN106846610A (en) * | 2017-01-20 | 2017-06-13 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note version and device |
| CN106846610B (en) * | 2017-01-20 | 2019-04-26 | 深圳怡化电脑股份有限公司 | A kind of bank note version recognition methods and device |
| CN106875553A (en) * | 2017-01-20 | 2017-06-20 | 浙江维融办公用品有限公司 | A kind of point currency examination all-in-one and its banknote detection method with POS payment functions |
| CN106875553B (en) * | 2017-01-20 | 2022-10-14 | 浙江维融办公用品有限公司 | Currency counting and detecting all-in-one machine with POS payment function and currency detecting method thereof |
| CN108734845A (en) * | 2017-04-20 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Detect the method and device of paper money number |
| CN108734845B (en) * | 2017-04-20 | 2021-01-01 | 深圳怡化电脑股份有限公司 | Method and device for detecting paper money crown word number |
| CN108806058A (en) * | 2017-05-05 | 2018-11-13 | 深圳怡化电脑股份有限公司 | A kind of paper currency detecting method and device |
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
| CN107025716B (en) * | 2017-06-05 | 2019-12-10 | 深圳怡化电脑股份有限公司 | Method and device for detecting contamination of paper money crown word number |
| CN107358718A (en) * | 2017-07-10 | 2017-11-17 | 深圳怡化电脑股份有限公司 | A kind of crown word number identification method, device, equipment and storage medium |
| CN107358718B (en) * | 2017-07-10 | 2019-09-20 | 深圳怡化电脑股份有限公司 | A kind of crown word number identification method, device, equipment and storage medium |
| CN107481389A (en) * | 2017-08-03 | 2017-12-15 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| CN107464335A (en) * | 2017-08-03 | 2017-12-12 | 恒银金融科技股份有限公司 | Paper currency crown word number positioning method |
| CN107481389B (en) * | 2017-08-03 | 2019-06-07 | 恒银金融科技股份有限公司 | Banknote serial number area image binarization processing method |
| CN107464335B (en) * | 2017-08-03 | 2020-01-17 | 恒银金融科技股份有限公司 | Paper currency crown word number positioning method |
| CN107610320A (en) * | 2017-09-06 | 2018-01-19 | 深圳怡化电脑股份有限公司 | A kind of bank slip recognition method and apparatus |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN107590900A (en) * | 2017-09-15 | 2018-01-16 | 深圳怡化电脑股份有限公司 | A kind of crown word number image acquiring method, device, equipment and storage medium |
| CN108320374A (en) * | 2018-02-08 | 2018-07-24 | 中南大学 | A kind of multinational paper money number character identifying method based on finger image |
| CN108537237A (en) * | 2018-04-04 | 2018-09-14 | 深圳怡化电脑股份有限公司 | Characteristic area extracting method, device, equipment and the storage medium of bill |
| CN108765690A (en) * | 2018-04-28 | 2018-11-06 | 深圳怡化电脑股份有限公司 | Vision sensor data processing method, device, system and financial self-service equipment |
| CN111104946A (en) * | 2019-12-24 | 2020-05-05 | 江苏国光信息产业股份有限公司 | Paper currency crown word number character segmentation method based on SVM classifier |
| CN112307867A (en) * | 2020-03-03 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for outputting information |
| CN111382696A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111833511A (en) * | 2020-06-09 | 2020-10-27 | 武汉卓目科技有限公司 | Method and device for improving identification rate of prefix number based on multi-channel synthesis technology |
| CN117671849A (en) * | 2023-12-14 | 2024-03-08 | 浙江南星科技有限公司 | Vertical image scanning banknote counter adopting banknote sliding structure |
| CN117671849B (en) * | 2023-12-14 | 2024-05-14 | 浙江南星科技有限公司 | Vertical image scanning banknote counter adopting banknote sliding structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104318238A (en) | Method for extracting crown word numbers from scanned banknote images in banknote detection module | |
| US10930105B2 (en) | Banknote management method and system | |
| CN104464079B (en) | Multiple Currencies face amount recognition methods based on template characteristic point and topological structure thereof | |
| CN101923640B (en) | Method for distinguishing false iris images based on robust texture features and machine learning | |
| CN104298989B (en) | False distinguishing method and its system based on zebra stripes Infrared Image Features | |
| CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN104899965B (en) | A kind of multinational paper money sequence number recognition methods based on cleaning-sorting machine | |
| CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN104700092A (en) | Small-character number identification method based on template and feature matching | |
| CN103886309A (en) | Method for identifying dollar denominations through facial recognition | |
| CN105404868A (en) | Interaction platform based method for rapidly detecting text in complex background | |
| CN106355744A (en) | Image identification method and device | |
| CN106898078B (en) | Port currency version identification method and device | |
| Jang et al. | Low-quality banknote serial number recognition based on deep neural network | |
| CN107393115A (en) | Banknote serial number identification and counterfeit identification method | |
| CN107464335A (en) | Paper currency crown word number positioning method | |
| CN106447910B (en) | A kind of method and device of paper money recognition | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| CN105631816B (en) | A kind of iris image noise classification detection method | |
| Lee et al. | Vehicle model recognition in video | |
| CN106447905A (en) | Banknote type identification method and device | |
| Kennard et al. | Offline signature verification and forgery detection using a 2-D geometric warping approach | |
| CN106780953A (en) | A kind of paper money discrimination method and system based on double comb font size | |
| CN106934914B (en) | Method and device for anti-counterfeiting detection of paper money | |
| CN107481389B (en) | Banknote serial number area image binarization processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150128 |
|
| RJ01 | Rejection of invention patent application after publication |