CN106373256A - Method and system for RMB version recognition - Google Patents

Method and system for RMB version recognition Download PDF

Info

Publication number
CN106373256A
CN106373256A CN201610704638.2A CN201610704638A CN106373256A CN 106373256 A CN106373256 A CN 106373256A CN 201610704638 A CN201610704638 A CN 201610704638A CN 106373256 A CN106373256 A CN 106373256A
Authority
CN
China
Prior art keywords
data channel
metal wire
rmb
crest
data
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.)
Granted
Application number
CN201610704638.2A
Other languages
Chinese (zh)
Other versions
CN106373256B (en
Inventor
旺静然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Yihua Computer Co Ltd
Shenzhen Yihua Time Technology Co Ltd
Shenzhen Yihua Financial Intelligent Research Institute
Original Assignee
Shenzhen Yihua Computer Co Ltd
Shenzhen Yihua Time Technology Co Ltd
Shenzhen Yihua Financial Intelligent Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Yihua Computer Co Ltd, Shenzhen Yihua Time Technology Co Ltd, Shenzhen Yihua Financial Intelligent Research Institute filed Critical Shenzhen Yihua Computer Co Ltd
Priority to CN201610704638.2A priority Critical patent/CN106373256B/en
Publication of CN106373256A publication Critical patent/CN106373256A/en
Application granted granted Critical
Publication of CN106373256B publication Critical patent/CN106373256B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07DHANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/16Testing the dimensions
    • G07D7/164Thickness

Abstract

The present invention provides a method and system for RMB version recognition, which relate to the field of monetary recognition method. The method comprises the following steps: extracting the effective thickness data of the RMB in the row direction; detecting the metal line peaks of each data channel in the column direction of the effective thickness data; determining the presence of the metal line in the data channel based on the number of metal line peaks present in each data channel; and determining the version of RMB according to the position of the metal line. The recognition method of the present invention can determine the position and the version of the metal line by detecting the metal line peak data of the area where the RMB security line is located, and is not affected by the characteristics of the RMB itself, such as the paper sample wear and tear. The operation is simple enough to realize rapid and convenient RMB version recognition.

Description

The method and system of RMB version identification
Technical field
The invention belongs to currency recognition technical field, more particularly, to a kind of method and system of RMB version identification.
Background technology
People's Bank of China has issued two editions RMB respectively at 2005 and 2015, and on existing market, two editions RMB are same When circulation.Because being related to the identification of RMB version during currency examination, version identification is correct to be just beneficial to subsequently carry out other knowledges Do not judge, thus be necessary version is identified.The algorithm that existing neural network algorithm is identified to RMB version, first First pretreatment is carried out to RMB image, eliminates some unfavorable information and noise, then RMB sequence number is carried out segmentation and Normalization, and extract the characteristic vector of character, finally using neutral net, character is emulated.Existing neural network algorithm pair The dependency of RMB sample is stronger, such as the sample of different temperatures, and RMB sequence number is carried out with segmentation and normalized convergence Speed is slow, and needs quantity of parameters to participate in calculating, and the such as initial value of network topology structure, weights and threshold value increased identification Complexity.
The problems referred to above are urgently to be resolved hurrily.
Content of the invention
Slow compared with strong, convergence rate to the identification sample dependency of RMB version and identification process is multiple for prior art Miscellaneous defect, the embodiment of the present invention provides a kind of method and system of RMB version identification.
The present invention provides a kind of RMB version to know method for distinguishing, comprising:
Extract RMB effective thickness data in the row direction;
Along the column direction of described effective thickness data, detect the metal wire crest in each data channel respectively;
There is metal wire in this data channel of quantitative determination according to there is metal wire crest in each described passage;
The version of the location determination RMB according to described metal wire.
Preferably, described extract inclusion before RMB institute effective thickness data in the row direction:
Remove the background data on the line direction that RMB is located.
Preferably, the described column direction along described effective thickness data, detects the metal wire in each data channel respectively Crest specifically includes:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
Preferably, described have gold according to this data channel of quantitative determination that there is metal wire crest in each described passage Belong to line to specifically include:
There is the data channel sequence number of described metal wire crest in record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
Preferably, the version of the described location determination RMB according to described metal wire specifically includes:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs in No. 1-3 Some data channel or No. 8-10 in some data channel, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to certain in No. 4-7 One data channel, then for 2005 editions RMB.
Also a kind of system of RMB version identification of the present invention, comprising:
Extraction module, for extract RMB effective thickness data in the row direction;
Detection module, for the column direction along described effective thickness data, detects the metal in each data channel respectively Line crest;
First determination module, for according to this data channel of quantitative determination that there is metal wire crest in each described passage There is metal wire;
Second determination module, for the version of the location determination RMB according to described metal wire.
Preferably, described system also includes:
Remove module, for removing the background data on the line direction at RMB place.
Preferably, described detection module specifically for:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
Preferably, described first determination module specifically for:
There is the data channel sequence number of described metal wire crest in record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
Preferably, described second determination module specifically for:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs in No. 1-3 Some data channel or No. 8-10 in some data channel, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to certain in No. 4-7 One data channel, then for 2005 editions RMB.
Beneficial effect: the recognition methodss that the present invention provides are passed through to detect the metal wire crest of RMB safety line region Data, to judge metal wire position and version, is substantially not subject to the impact of the RMB self characters such as bank note sample abrasion, Simple to operate, identification RMB version is faster.
Brief description
Fig. 1 is the method and step figure of RMB version identification provided in an embodiment of the present invention;
The method and step figure of the RMB version identification that Fig. 2 provides for another embodiment of the present invention;
The method and step figure of the RMB version identification that Fig. 3 provides for yet another embodiment of the invention;
Fig. 4 is the system construction drawing of RMB version identification provided in an embodiment of the present invention;
The system construction drawing of the RMB version identification that Fig. 5 provides for further embodiment of this invention.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and It is not used in the restriction present invention.
The present invention provides a kind of RMB version to know method for distinguishing, as shown in Figure 1, comprising:
S100, extract RMB effective thickness data in the row direction;
S200, the column direction along described effective thickness data, detect the metal wire crest in each data channel respectively;
S300, metal wire is had according to this data channel of quantitative determination that there is metal wire crest in each described passage;
S400, the version according to the location determination RMB of described metal wire.
Specifically, according to national regulation, using white, width is not less than 60mm to the metal wire of RMB, and people About 0.1 millimeter of coin thickness, about 20 microns of a wires thickness, the position of the two superposition will than the thickness of RMB slightly Thick.There is metal wire crest in metal wire, can determine that the people of different editions according to metal wire crest and effective thickness data People's coin.
Preferably, as shown in Fig. 2 described extract inclusion before RMB institute effective thickness data in the row direction:
S500, the background data removing on the line direction that RMB is located.
Specifically, background data numerical value is less than normal substantially zeroed, and effective thickness data is real banknote thickness data, numerical value Bigger than normal, background and effective thickness data separation can be come by arranging threshold value.As 25 can be set a threshold to, wherein background The value in region is essentially less than 10, and the width regions value of effective thickness data is more than 40, the width of general effective thickness data Regional value is 50-60.
Preferably, the described column direction along described effective thickness data, detects the metal wire in each data channel respectively Crest specifically includes:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
Specifically, set effective thickness data herein and there are ten passages along column direction, be by the hardware controls detecting Set by frame for movement, adjust the quantity of passage also dependent on different detection hardware adaptive mechanisms, in order to measure belonging to metal wire Channel range.
Preferably, as shown in figure 3, described according to this data of quantitative determination that there is metal wire crest in each described passage There is metal wire and specifically include in passage:
There is the data channel sequence number of described metal wire crest in s301, record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
Specifically, the bank note of different editions can be identified according to the position of metal wire difference, by passage crest Number can determine that whether passage is the position that metal wire is located.
Preferably, the version of the described location determination RMB according to described metal wire specifically includes:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs in No. 1-3 Some data channel or No. 8-10 in some data channel, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to certain in No. 4-7 One data channel, then for 2005 editions RMB.
Specifically, it is set in diverse location in the horizontal direction according to two editions RMB characteristic metal lines itself and determine people The version of people's coin.
The recognition methodss that the present invention provides are passed through to detect the metal wire crest data of RMB safety line region, to sentence Determine metal wire position and version, be substantially not subject to the impact of the RMB self characters such as bank note sample abrasion, simple to operate, Identification RMB version is faster.
The present invention also provides a kind of system of RMB version identification, as shown in Figure 4, comprising:
Extraction module 100, for extract RMB effective thickness data in the row direction;
Detection module 200, for the column direction along described effective thickness data, detects the gold in each data channel respectively Belong to line crest;
First determination module 300, for according to this data of quantitative determination that there is metal wire crest in each described passage There is metal wire in passage;
Second determination module 400, for the version of the location determination RMB according to described metal wire.
Preferably, described system also includes:
Remove module 500, for removing the background data on the line direction at RMB place.
Preferably, described detection module specifically for:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
Preferably, described first determination module specifically for:
There is the data channel sequence number of described metal wire crest in record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
Preferably, described second determination module specifically for:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs in No. 1-3 Some data channel or No. 8-10 in some data channel, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to certain in No. 4-7 One data channel, then for 2005 editions RMB.
It should be noted that modules in said system provided in an embodiment of the present invention, due to real with the inventive method Apply example and be based on same design, the technique effect that it brings is identical with the inventive method embodiment, and particular content can be found in the present invention Narration in embodiment of the method, here is omitted.
The identifying system that the present invention provides is passed through to detect the metal wire crest data of RMB safety line region, to sentence Determine metal wire position and version, be substantially not subject to the impact of the RMB self characters such as bank note sample abrasion, simple to operate, Identification RMB version is faster.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.

Claims (10)

1. a kind of RMB version knows method for distinguishing it is characterised in that including:
Extract RMB effective thickness data in the row direction;
Along the column direction of described effective thickness data, detect the metal wire crest in each data channel respectively;
There is metal wire in this data channel of quantitative determination according to there is metal wire crest in each described passage;
The version of RMB described in location determination according to described metal wire.
2. the method for claim 1 it is characterised in that described extraction RMB effective thickness number in the row direction According to including before:
Remove the background data on the line direction that RMB is located.
3. method as claimed in claim 2, it is characterised in that the described column direction along described effective thickness data, is examined respectively The metal wire crest surveyed in each data channel specifically includes:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
4. method as claimed in claim 3 is it is characterised in that described have metal wire crest according in each described passage There is metal wire and specifically include in this data channel of quantitative determination:
There is the data channel sequence number of described metal wire crest in record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
5. method as claimed in claim 4 is it is characterised in that the version of the described location determination RMB according to described metal wire Originally specifically include:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs to certain in No. 1-3 Some data channel in one passage or No. 8-10, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to some in No. 4-7 Data channel, then for 2005 editions RMB.
6. a kind of system of RMB version identification is it is characterised in that include:
Extraction module, for extract RMB effective thickness data in the row direction;
Detection module, for the column direction along described effective thickness data, detects the metal wire ripple in each data channel respectively Peak;
First determination module, for existing according to this data channel of quantitative determination that there is metal wire crest in each described passage Metal wire;
Second determination module, for the version of the location determination RMB according to described metal wire.
7. system as claimed in claim 6 is it is characterised in that described system also includes:
Remove module, for removing the background data on the line direction at RMB place.
8. system as claimed in claim 7 it is characterised in that described detection module specifically for:
Obtain the quantity of the metal wire crest in each described data channel by the thickness collection of illustrative plates of RMB.
9. system as claimed in claim 8 it is characterised in that described first determination module specifically for:
There is the data channel sequence number of described metal wire crest in record, and
There is the quantity of metal wire crest in the data channel that there is metal wire crest.
10. system as claimed in claim 9 it is characterised in that described second determination module specifically for:
Described data channel is ten, carries out channel number successively along length of paper currency direction;
If the metal wire crest number existing in certain data channel is more than or equal to 3, and this data channel belongs to certain in No. 1-3 Some data channel in one data channel or No. 8-10, then for 2015 editions RMB;
If the metal wire crest number existing in certain data channel is more than 3, and this data channel belongs to some in No. 4-7 Data channel, then for 2005 editions RMB.
CN201610704638.2A 2016-08-23 2016-08-23 The method and system of RMB version identification Active CN106373256B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610704638.2A CN106373256B (en) 2016-08-23 2016-08-23 The method and system of RMB version identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610704638.2A CN106373256B (en) 2016-08-23 2016-08-23 The method and system of RMB version identification

Publications (2)

Publication Number Publication Date
CN106373256A true CN106373256A (en) 2017-02-01
CN106373256B CN106373256B (en) 2019-04-26

Family

ID=57878847

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610704638.2A Active CN106373256B (en) 2016-08-23 2016-08-23 The method and system of RMB version identification

Country Status (1)

Country Link
CN (1) CN106373256B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63247895A (en) * 1987-04-03 1988-10-14 オムロン株式会社 Paper money discriminator
CN1538353A (en) * 2003-04-17 2004-10-20 株式会社日立制作所 Paper kind discriminating device
CN101504781A (en) * 2009-03-10 2009-08-12 广州广电运通金融电子股份有限公司 Valuable document recognition method and apparatus
CN101536047A (en) * 2006-11-06 2009-09-16 光荣株式会社 Papers discriminating device, and papers discriminating method
CN102176262A (en) * 2011-01-17 2011-09-07 广州广电运通金融电子股份有限公司 Thickness detecting method and device for slice medium
CN105184955A (en) * 2015-08-18 2015-12-23 深圳怡化电脑股份有限公司 Method and device for identifying paper money
CN105719385A (en) * 2014-12-18 2016-06-29 起山电子株式会社 Paper currency processing device and control method thereof

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63247895A (en) * 1987-04-03 1988-10-14 オムロン株式会社 Paper money discriminator
CN1538353A (en) * 2003-04-17 2004-10-20 株式会社日立制作所 Paper kind discriminating device
CN101536047A (en) * 2006-11-06 2009-09-16 光荣株式会社 Papers discriminating device, and papers discriminating method
CN101504781A (en) * 2009-03-10 2009-08-12 广州广电运通金融电子股份有限公司 Valuable document recognition method and apparatus
CN102176262A (en) * 2011-01-17 2011-09-07 广州广电运通金融电子股份有限公司 Thickness detecting method and device for slice medium
CN105719385A (en) * 2014-12-18 2016-06-29 起山电子株式会社 Paper currency processing device and control method thereof
CN105184955A (en) * 2015-08-18 2015-12-23 深圳怡化电脑股份有限公司 Method and device for identifying paper money

Also Published As

Publication number Publication date
CN106373256B (en) 2019-04-26

Similar Documents

Publication Publication Date Title
CN102324132B (en) Bank-note detecting method by identifying ultraviolet-light image and system
WO2015085815A1 (en) Method and system for recognizing bill with abnormal thickness
Hassanpour et al. Feature extraction for paper currency recognition
US8385612B2 (en) Fingerprint image background detection apparatus and detection method
WO2015085811A1 (en) Method and device for banknote identification based on thickness signal identification
EP1964076A1 (en) Detecting improved quality counterfeit media items
KR20070119105A (en) Apparatus and method for face recognition using machine learning
CN106157135A (en) Antifraud system and method based on Application on Voiceprint Recognition Sex, Age
Odeh et al. Off-line signature verification and recognition: Neural Network Approach
CN105574981B (en) A kind of rmb paper currency denomination identifying method based on safety line magnetic information
EP2360619A1 (en) Fast fingerprint searching method and fast fingerprint searching system
CN107093259A (en) A kind of recognition methods of forge or true or paper money and its device
CN104574638A (en) Method for identifying RMB
Odeh et al. Apply multi-layer perceptrons neural network for off-line signature verification and recognition
CN106447897A (en) Method and apparatus for detecting magnetic characteristics of paper note
US20060088194A1 (en) Apparatus for online signature verification using pattern transform technique and method therefor
CN106683261B (en) A kind of false distinguishing method and apparatus of bank note
Dhar et al. Paper currency detection system based on combined SURF and LBP features
CN106373256A (en) Method and system for RMB version recognition
Zarin et al. A hybrid fake banknote detection model using OCR, face recognition and hough features
Foroozandeh et al. Persian signature verification based on fractal dimension using testing hypothesis
CN106780953A (en) A kind of paper money discrimination method and system based on double comb font size
EP3410409B1 (en) Media security validation
Verma et al. Static Signature Recognition System for User Authentication Based Two Level Cog, Hough Tranform and Neural Network
Ghosh et al. A study on diverse recognition techniques for Indian currency note

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant