CN106846603A - A kind of recognition methods of forge or true or paper money and its device - Google Patents
A kind of recognition methods of forge or true or paper money and its device Download PDFInfo
- Publication number
- CN106846603A CN106846603A CN201611112140.3A CN201611112140A CN106846603A CN 106846603 A CN106846603 A CN 106846603A CN 201611112140 A CN201611112140 A CN 201611112140A CN 106846603 A CN106846603 A CN 106846603A
- Authority
- CN
- China
- Prior art keywords
- character
- word number
- crown word
- true
- forge
- 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
Links
Landscapes
- Character Discrimination (AREA)
Abstract
Recognition methods and its device the present invention relates to a kind of forge or true or paper money, the method include:Obtain multiple crown word number area images of bank note;Recognize the crown word number information in the multiple crown word number area image;Judge whether the crown word number information in the multiple crown word number area image is consistent;The true and false of bank note is recognized according to judged result.The embodiment of the present invention passes through to judge whether the information of multiple crown word numbers is consistent, to recognize the true and false of bank note, and need not manually carry out the differentiation of the true and false, also the purple light image that manifests of projection post analysis is not relying on to judge forge or true or paper money, the recognition efficiency of forge or true or paper money discriminating is improve, the cost of forge or true or paper money identification is also reduced.
Description
Technical field
The invention belongs to paper money recognition field, more particularly to a kind of forge or true or paper money recognition methods and its device.
Background technology
With expanding economy, the amount of paper money in circulation is also corresponding increasing, and lawless person prints counterfeit money privately, is handing over
Easily during how rapid identification bank note the true and false it is particularly important.Existing forge or true or paper money authentication technique, it is main to be thrown using purple light
Penetrate in after bank note, then by manually differentiate the bank note whether presentation attributes image, its recognition efficiency is relatively low, and needs to utilize purple light
Grenade instrumentation, causes identification relatively costly.
The content of the invention
The purpose of the embodiment of the present invention is recognition methods and its device for providing a kind of forge or true or paper money, it is intended to solved existing
Forge or true or paper money RM recognition efficiency it is low, and need using purple light grenade instrumentation, cause identification relatively costly.
The embodiment of the present invention is achieved in that a kind of recognition methods of forge or true or paper money, and methods described includes:
Obtain multiple crown word number area images of bank note;
Recognize the crown word number information in the multiple crown word number area image;
Judge whether the crown word number information in the multiple crown word number area image is consistent;
The true and false of the bank note is recognized according to judged result.
On the other hand, the embodiment of the present invention provides a kind of identifying device of forge or true or paper money, and described device includes:
Crown word number acquiring unit, the multiple crown word number area images for obtaining bank note;
Character information recognition unit, for recognizing the crown word number information in the multiple crown word number area image;
Character information identifying unit, for judge the crown word number information in the multiple crown word number area image whether one
Cause;
Identification unit, the true and false for recognizing the bank note according to judged result.
Implement a kind of bank note provided in an embodiment of the present invention towards recognition methods and its device have the advantages that:
Whether the embodiment of the present invention passes through to judge the consistent true and false to recognize bank note of information of multiple crown word numbers, because illegal
Molecule, due to the imperfection and the relation of a large amount of photocopy of urgent need of technology, is printing crown word number mistake during counterfeit money is manufactured
Cheng Zhong, the situation for wrongly typed often occurs, biting.And country distribution legal bank note is due to technology maturation and has Special Survey
Department, is not in such case.Therefore, the forge or true or paper money identification that the embodiment of the present invention is realized, and need not manually carry out
The differentiation of the true and false, is also not relying on the purple light image that manifests of projection post analysis to judge forge or true or paper money, improves forge or true or paper money mirror
Other recognition efficiency, also reduces the cost of forge or true or paper money identification.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the recognition methods of forge or true or paper money provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart of the recognition methods of forge or true or paper money that another embodiment of the present invention is provided;
Fig. 3 be another embodiment of the present invention provide a kind of forge or true or paper money recognition methods in segmentation strategy idiographic flow
Figure;
Fig. 4 be another embodiment of the present invention provide a kind of forge or true or paper money recognition methods in, S206's implements stream
Cheng Tu;
Fig. 5 is a kind of structured flowchart of the identifying device of forge or true or paper money provided in an embodiment of the present invention;
Fig. 6 is a kind of structured flowchart of the identifying device of forge or true or paper money that another embodiment of the present invention is provided;
Fig. 7 be another embodiment of the present invention provide a kind of forge or true or paper money identifying device in character recognition unit it is specific
Structured flowchart.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Whether the embodiment of the present invention is mainly consistent by judging the character information of bank note multiple characteristic image, reaches identification paper
The purpose of the coin true and false, so that the recognition efficiency for solving existing forge or true or paper money RM is low, and needs to utilize purple light
Grenade instrumentation, causes identification relatively costly.
In embodiments of the present invention, the executive agent of flow is forge or true or paper money identifying device.The forge or true or paper money identification dress
Put and can be used alone, can also coordinate other devices to be used as part in using or being assembled in other devices.Fig. 1 shows this hair
Flow chart is realized in the recognition methods of the forge or true or paper money that bright embodiment is provided, and details are as follows:
In S101, multiple crown word number area images of bank note are obtained.
In the present embodiment, the mode for obtaining image can shoot acquisition by external devices, can also be by true in bank note
Sensor devices are set in pseudo- identifying device and directly generate corresponding image.
In the present embodiment, because prefix code is the sequence number and relevant information comprising the bank note of the identification note true and false,
Therefore all types of bank note will certainly exist prefix code.Prefix code thus be may be used on into existing all paper as characteristic image
In the middle of coin, the wide usage of the present embodiment is improved.
In S102, the crown word number information in the multiple crown word number area image is recognized.
In the present embodiment, the mode of identification crown word number information has various, and the character information of crown word number can be recognized one by one;
Can also be identified crown word number as an entirety, extract the frame of crown word number.
In S103, judge whether the crown word number information in the multiple crown word number area image is consistent.
In the present embodiment, the mode of judgement is corresponding, according to the different and different of identification crown word number information mode.If
The character information of crown word number is recognized one by one, then the character of crown word number information in multiple crown word number area images is contrasted one by one and sentenced
It is disconnected;If being identified crown word number information as an entirety, then by the multiple crown word numbers in multiple crown word number area images
Information is integrally compared judgement.
In S104, the true and false of the bank note is recognized according to judged result.
In the present embodiment, if the character information included in multiple crown word number area images in S103 is all identical,
Then judge that the bank note is genuine notes;If have in multiple crown word number area images one or more crown word number area image and other
The character information that crown word number image is included is differed, then judge that the bank note is counterfeit money.
Preferably, if judging, the bank note is counterfeit money, and the bank note is positioned over into region to be confirmed.Due to passing through this reality
After applying judgement, the bank note has been determined as counterfeit money, it is therefore desirable to carry out difference placement with genuine notes, in case a large amount of bank note are identified
After operation, counterfeit money is still mixed into the middle of genuine notes.
Whether the embodiment of the present invention passes through to judge the consistent true and false to recognize bank note of information of multiple crown word numbers, because illegal
Molecule, due to the imperfection and the relation of a large amount of photocopy of urgent need of technology, is printing crown word number mistake during counterfeit money is manufactured
Cheng Zhong, the situation for wrongly typed often occurs, biting.And country distribution legal bank note is due to technology maturation and has Special Survey
Department, is not in such case.Therefore, the forge or true or paper money identification that the embodiment of the present invention is realized, and need not manually carry out
The differentiation of the true and false, is also not relying on the purple light image that manifests of projection post analysis to judge forge or true or paper money, improves forge or true or paper money mirror
Other recognition efficiency, also reduces the cost of forge or true or paper money identification.
Fig. 2 shows a kind of flow chart of the recognition methods of forge or true or paper money that another embodiment of the present invention is provided.Referring to Fig. 2
Shown, a kind of recognition methods of the forge or true or paper money provided relative to a upper embodiment, the present embodiment is relative in a upper embodiment
Crown word number information in the multiple crown word number area image of identification has made further restriction, and details are as follows:
In S205, the multiple crown word number area image is divided into multiple character respectively according to default segmentation strategy
Image, each character subgraph includes a character information.
In the present embodiment, for the ease of the character recognition in later stage, the character picture that will be included in crown word number area image,
It is unit according to character, is divided into character subgraph independent one by one.The storage order of character subgraph after segmentation, according to word
Order in symbol frame region, from left to right, is from top to bottom stored in register successively.Character subgraph after segmentation
Represent a corresponding character.
In the present embodiment, segmentation strategy refers specifically to the method by picture segmentation according to matching algorithm.Illustratively,
In the present embodiment, by detecting that each pixel point value of continuous two row is identical or difference of pixel point value is less than predetermined threshold value, then
Judge to need segmentation at this.
In S206, the multiple characters included in multiple character subgraphs of each crown word number area image are recognized respectively
Information, and the crown word number information according to corresponding to the multiple character information generates the crown word number area image.
Preferably, in the present embodiment, the method for identification character information is the template by character subgraph and specification character
Compare, the minimum template of selection differences as character subgraph matching template, the corresponding character of matching template is this
Character represented by character subgraph.
In the present embodiment, the corresponding crown word number information of the crown word number area image is generated to come specifically, will identify that
Character information, carry out rearrangement combination in the order of crown word number area image according to the character subgraph before segmentation, obtain
Unique crown word number information sequence.
In embodiments of the present invention, single character recognition is carried out by segmentation, so as to reduce the operand of identification character, is carried
The efficiency of truth identification high.In the case of for a multiple character mixing in one image, identification is needed by a large amount of
Permutation and combination scheme compare identification, this will increase the recognition time of computer, and know because multiple characters mix
The interference between image character can not be produced, so as to lower the accuracy rate of identification.And single character separately recognize will solve it is above-mentioned
Problem.
Further, as an alternative embodiment of the invention, the recognition methods of the forge or true or paper money also includes:
In S201, the character sample image that multiple includes identical characters, the multiple character sample image point are obtained
Wei Yu not be in multiple currency types, face amount identical bank note in the crown word number area image of same position.
In the present embodiment, it is used as the template of character subgraph matching, it is necessary at such to obtain enough samples
In type bank note, substantial amounts of sample image is gathered, and the sample image for being gathered should belong to positioned at same crown word number area image
It is interior.For different characteristic images, even if representing same character, because font and the relation of stretcher strain, can influence the hat
The pixel distribution of character subgraph in font size area image.Therefore, in collecting sample, corresponding to the pixel of same character
The sample of characteristic value template, should also be located in the crown word number area image of same position.
In the present embodiment, sample image quantity should be greater than 100.Substantial amounts of sample image quantity is gathered, can be caused
Template is more representative, overcomes the error produced because of the influence of noise or shooting machine.
In S202, the mean pixel point value that the multiple character sample image is often gone is used as the preset configuration list
Corresponding row pixel point value in the pixel characteristic value template of the middle correspondence character;By the multiple character sample image each column
Mean pixel point value is arranged accordingly as the pixel characteristic value template of the correspondence character in the preset configuration list
Pixel point value.
In the present embodiment, each column in pixel characteristic value template often row pixel point value by sample mean pixel point value structure
Into.Multiple sample images are acquired in S201 steps, the pixel point value of corresponding row are added again divided by sample size, you can
Obtain mean pixel point value.Especially, for binary image, because should only there are 0 or 255 two values in sample image, because
This, when pixel point value is averaging, should choose 127 and be not more than 127 as benchmark value, i.e. the mean pixel point value, then sentence
The pixel point value of breaking is 0;Conversely, then judging that the pixel point value is 255.
In S203, the pixel characteristic value template of the correspondence character is stored in preset configuration list.
In embodiments of the present invention, sample form is used as by the image in actual banknote, relative to being stored in computer
In standard letter Character mother plate for, it is more close with character subgraph to be judged.Therefore, it is possible to improve identification character
Accuracy rate, and then improve the accuracy rate of forge or true or paper money identification.
It should be noted that in the present embodiment S204 and S207 due to embodiment illustrated in fig. 1 in S101 and
It is identical that S104 implements process, therefore repeats no more in this embodiment.
Further, as an alternative embodiment of the invention, relative to a upper embodiment, Fig. 3 shows segmentation strategy
Specific steps, the segmentation strategy is specially:
In S301, the default screens matched with the crown word number area image is chosen by template matching algorithm and is cut
Template.
In the present embodiment, the different default screens cutting board of different crown word number area image correspondences, due to font
And the reason for image stretch, the elemental area shared by each character is also different, therefore, for different crown word number administrative division maps
Picture, distributes different default screens cutting boards.
In the present embodiment, because crown word number is that a line is sequentially arranged, therefore row line of cut can be first chosen, by crown word number area
Area image is by character for unit cuts apart successively.If character information described in the crown word number area image is not horizontally arranged,
The crown word number area image then carries out rotation process is horizontally arranged to character, then carries out above-mentioned cutting operation.
In S302, the crown word number area image is cut into multiple words using the default screens cutting board for matching
Symbol subgraph.
In the present embodiment, by recognizing the border of character, cutting operation is being carried out using default screens cutting board.Lift
Example property ground, the crown word number area image is binary image, pixel point value detection is carried out to the subgraph from left to right, when first
The secondary subgraph pixel point value that includes of row that detects is 0 pixel, then judge that this is classified as the left margin of a character subgraph;
When being consecutively detected, the subgraph is a few to arrange the pixel that the pixel point value that does not include is 0, then judge that this is classified as a character subgraph
The right margin of picture.Up-and-down boundary is determined by this detection method, so that it is determined that going out all characters in the crown word number area image
The character boundary of subgraph, cutting board is then applied mechanically again carries out cutting operation.
In implementation is invented, by using identical form and size, character subgraph is intercepted, character subgraph can be easy to
Storage and identification, so as to improve the accuracy rate of forge or true or paper money identification.
Further, referring to Fig. 4, as an alternative embodiment of the invention, relative to the embodiment shown in Fig. 2, this reality
Example is applied to do the multiple character informations included in the multiple character subgraphs for recognizing each crown word number area image respectively
Further refinement, details are as follows:
Multiple character informations included in the multiple character subgraphs for recognizing each crown word number area image respectively
Specially:
In S401, by often row pixel point value and each column pixel point value in the multiple character subgraph, respectively with advance
If the corresponding row pixel point value of pixel characteristic value template and row pixel point value in configured list carry out differing from square operation, obtain
Multiple difference square value, the pixel characteristic value template one specific character of correspondence in the preset configuration list.
In the present embodiment, because character subgraph is stored in a digital format, therefore character subgraph is considered as one
The individual image being made up of multiple pixel grid points, the character subgraph each column or row has several pixels, the pixel
Point has pixel point value, for colored image, the pixel point value is constituted by tri- pixel values of RGB;For gray level image, then by
The gray value of the point as the point pixel point value;For binary image, then the pixel point value of the point is 0 or 255.
In the present embodiment, the pixel characteristic value template at least two in preset configuration list, it is preferable that preset configuration
At least 36 pixel characteristic value templates in list, comprising corresponding to 26 templates and 10 numeric words of upper case alphabetic character
The template of symbol.
Preferably, in the present embodiment, each one described preset configuration list of the crown word number area image correspondence, institute
The character subgraph stated in characteristic image is compared with the template in corresponding preset configuration list.Due to for different spies
Levy image, identical character may be printed with different fonts or stretcher strain is caused and had any different in display through typesetting,
Therefore be conducive to improving the accuracy of matching using different lists.
In S402, the multiple poor square value summation is stated the matching numerical value of template as institute's pixel characteristic value.
Illustratively, character subgraph is binary image, and picture traverse and height are 3 pixels, specific pixel
Point value is distributed as:The pixel point value of a wherein pixel characteristic value template is distributed as:Then the first row pixel point value of the character subgraph is 255+255+0=510, the pixel characteristic value
The pixel point value of template the first row is 255+0+0=255, then both differences square are (510-255)2=65025.Remaining each row
Each leu time is calculated, the matching numerical value of the poor square value sum for the drawing as pixel characteristic value template.
In S403, in the multiple pixel characteristic value template, a minimum picture of the matching numerical value is obtained
Plain characteristic value template, using the specific character corresponding to the minimum pixel characteristic value template of the matching numerical value as the word
The corresponding character of symbol subgraph.
In the present embodiment, because by image, after differing from square operation, the matching value for obtaining can effectively represent multiple
Matching degree between image, therefore, the minimum corresponding pixel characteristic value template of selection matching numerical value, it is believed that the template be with
The most close pixel characteristic value template in preset configuration list of the character subgraph.
Preferably, if the character pixel template corresponding to matching numerical value minimum has multiple, using identification strategy selection
Optimum Matching template, the identification strategy is specially:Judge whether the matching value identical multiple pixel characteristic value template belongs to
In same big class template, if so, then using character feature diagnostic method;If it is not, then using center convergence diagnostic method.
In the present embodiment, same big class template is referred to corresponding to the pixel characteristic value template in preset configuration list
Character shape it is close, illustratively, character " 6 " and character " 9 ";Character " 0 ", character " O " and character " D " etc..This
In the case of, we can further be screened using feature decision method to pixel characteristic value template.Illustratively, for word
Symbol " 6 " and character " 9 ", can detect the area pixel point Distribution value in the character subgraph upper right corner, if only a small amount of in the region
Point value is 0 pixel, then judge that the corresponding character of character subgraph is " 6 ";Conversely, then corresponding character is " 9 ", remaining
Each major class character also can carry out further refinement and differentiate by the method for same feature decision.
In the present embodiment, center convergence diagnostic method refer to reduce borderline region differentiation, that is, leave out first trip first with
And footline terminal column, then carry out differing from square matches method.Due to the multiple pixel characteristic value templates for being not belonging to same major class
Matching numerical value is identical, it may be possible to caused because the noise on border is more;On the other hand, when two characters be not belonging to it is same big
Class, closer to picture centre, its difference will be bigger, therefore, can be judged using the method for gradually decreasing border to compare.
In embodiments of the present invention, the minimum matching template of difference is selected by difference square matches method and is used as the character subgraph
The corresponding templates of picture, so as to recognize the character that character subgraph is represented.The method is realized simply, by simple poor square of fortune
Calculate, you can identification image character, the time of forge or true or paper money identification is improve, so as to improve recognition efficiency.
It should be understood that the size of the sequence number of each step is not meant to the priority of execution sequence, each process in above-described embodiment
Execution sequence should determine that the implementation process without tackling the embodiment of the present invention constitutes any limit with its function and internal logic
It is fixed.
Fig. 5 shows the structured flowchart of the identifying device of forge or true or paper money provided in an embodiment of the present invention, the forge or true or paper money
Identifying device is used for the method for performing embodiment illustrated in fig. 1 offer.For convenience of description, illustrate only related to the present embodiment
Part.
Referring to Fig. 5, the identifying device of the forge or true or paper money includes:
Crown word number acquiring unit 51, the multiple crown word number area images for obtaining bank note;
Character information recognition unit 52, for recognizing the crown word number information in the multiple crown word number area image;
Character information identifying unit 53, for judge the crown word number information in the multiple crown word number area image whether one
Cause;
Identification unit 54, the true and false for recognizing the bank note according to judged result.
Alternatively, shown in Figure 6, in another embodiment, the identifying device of the forge or true or paper money in the embodiment is used for
The method that operation embodiment illustrated in fig. 2 is provided, the identifying device of the forge or true or paper money also includes:
Specifically, character information recognition unit includes:
Character segmentation unit 65, for being divided into the multiple crown word number area image respectively according to default segmentation strategy
Multiple character subgraphs, each character subgraph includes a character information;
Character recognition unit 66, for included in the multiple character subgraphs for recognizing each crown word number area image respectively
Multiple character informations, and the crown word number letter according to corresponding to the multiple character information generates the crown word number area image
Breath.
Alternatively, the identifying device of the forge or true or paper money also includes:
Character sample acquiring unit 61, for obtaining multiple character sample images comprising identical characters, multiple words
Symbol sample image is located in the crown word number area image of same position in multiple currency types, the identical bank note of face amount respectively;
Template generation unit 62, for mean pixel point value that multiple character sample images are often gone as described pre-
If corresponding row pixel point value in the pixel characteristic value template of the correspondence character in configured list;By multiple character samples
The mean pixel point value of image each column as the correspondence character in the preset configuration list pixel characteristic value mould
The corresponding row pixel point value of plate;
Template storage unit 63, the pixel characteristic value template for the correspondence character is stored in preset configuration list
In.
It should be noted that in the present embodiment 64 and 67 due to embodiment illustrated in fig. 5 in 51 and 54 specific structures
The function of making and realize is identical, therefore repeats no more in this embodiment.
Specifically, the segmentation strategy is specially:
The default screens cutting board matched with the crown word number area image is chosen by template matching algorithm;
The crown word number area image is cut into multiple character subgraphs using the default screens cutting board for matching.
Specifically, referring to Fig. 7, the character recognition unit is specifically included:
Pixel point value computing unit 71, for by often row pixel point value and each column pixel in the multiple character subgraph
Point value, row pixel point value corresponding with the multiple pixel characteristic value templates in preset configuration list and row pixel point value are entered respectively
Row difference square operation, obtains multiple difference square values, and the pixel characteristic value template correspondence one in the preset configuration list is specific
Character;
Matching value computing unit 72, for using the multiple poor square value summation as the pixel characteristic value template
With numerical value;
Template identifying unit 73, in the multiple pixel characteristic value template, obtaining the matching numerical value minimum
One pixel characteristic value template, by the specific character corresponding to the minimum pixel characteristic value template of the matching numerical value
As the corresponding character of the character subgraph.
Therefore, the identifying device of forge or true or paper money provided in an embodiment of the present invention again may be by judging multiple crown word number areas
Whether the character information included in area image is consistent to recognize the true and false of bank note, and need not manually carry out the differentiation of the true and false,
It is not relying on the purple light image that manifests of projection post analysis to judge forge or true or paper money, thus improves the efficiency of forge or true or paper money discriminating,
Also reduce the cost of forge or true or paper money identifying device.
It is apparent to those skilled in the art that, for convenience of description and succinctly, only with above-mentioned each work(
Energy unit, the division of module are carried out for example, in practical application, as needed can distribute by different above-mentioned functions
Functional unit, module are completed, will the internal structure of described device be divided into different functional unit or modules, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
Being that unit is individually physically present, it is also possible to which two or more units are integrated in a unit, above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.In addition, each function list
Unit, the specific name of module are also only to facilitate mutually differentiation, is not limited to the protection domain of the application.Said system
The specific work process of middle unit, module, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Unit and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function, but this realization can be realized it is not considered that exceeding using distinct methods to each specific application
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed apparatus and method, can be by other
Mode is realized.For example, system embodiment described above is only schematical, for example, the division of the module or unit,
It is only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be with
With reference to or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed
Coupling each other or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of device or unit or
Communication connection, can be electrical, mechanical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional module in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that modules are individually physically present, it is also possible to which two or more modules are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or use
When, can store in a computer read/write memory medium.Based on such understanding, the technical scheme of the embodiment of the present invention
The part for substantially being contributed to prior art in other words or all or part of the technical scheme can be with software products
Form embody, the computer software product is stored in a storage medium, including some instructions are used to so that one
Computer equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform this hair
The all or part of step of bright embodiment each embodiment methods described.And foregoing storage medium includes:USB flash disk, mobile hard disk,
Read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic
Dish or CD etc. are various can be with the medium of store program codes.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although with reference to foregoing reality
Example is applied to be described in detail the present invention, it will be understood by those within the art that:It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent to which part technical characteristic;And these are changed
Or replace, do not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution, all should
It is included within protection scope of the present invention.
Claims (10)
1. a kind of recognition methods of forge or true or paper money, it is characterised in that the recognition methods of the forge or true or paper money includes:
Obtain multiple crown word number area images of bank note;
Recognize the crown word number information in the multiple crown word number area image;
Judge whether the crown word number information in the multiple crown word number area image is consistent;
The true and false of the bank note is recognized according to judged result.
2. the recognition methods of forge or true or paper money according to claim 1, it is characterised in that the multiple crown word number of identification
Crown word number information in area image includes:
The multiple crown word number area image is divided into multiple character subgraphs, each character respectively according to default segmentation strategy
Subgraph includes a character information;
The multiple character informations included in multiple character subgraphs of each crown word number area image are recognized respectively, and according to institute
State the crown word number information corresponding to multiple character informations generations crown word number area image.
3. the recognition methods of forge or true or paper money according to claim 2, it is characterised in that the default segmentation strategy is specific
For:
The default screens cutting board matched with the crown word number area image is chosen by template matching algorithm;
The crown word number area image is cut into the multiple character subgraph using the default screens cutting board for matching.
4. the recognition methods of the forge or true or paper money according to Claims 2 or 3, it is characterised in that described to recognize that each is preced with respectively
Multiple character informations included in multiple character subgraphs of font size area image are specially:
By often row pixel point value and each column pixel point value in the multiple character subgraph, respectively with preset configuration list in
The corresponding row pixel point value of multiple pixel characteristic value templates and row pixel point value carry out differing from square operation, obtain multiple differences squares
Value, the pixel characteristic value template one specific character of correspondence in the preset configuration list;
The multiple poor square value is sued for peace as the matching numerical value of the pixel characteristic value template;
In the multiple pixel characteristic value template, a minimum pixel characteristic value template of the matching numerical value is obtained,
Using the specific character corresponding to the minimum pixel characteristic value template of the matching numerical value as character subgraph correspondence
Character.
5. the recognition methods of forge or true or paper money according to claim 4, it is characterised in that the recognition methods of the forge or true or paper money
Also include:
The character sample image that multiple includes identical characters is obtained, the multiple character sample image is located at multiple coin respectively
In kind, face amount identical bank note in the crown word number area image of same position;
The mean pixel point value that the multiple character sample image is often gone is used as the correspondence word in the preset configuration list
Corresponding row pixel point value in the pixel characteristic value template of symbol;By the mean pixel point value of the multiple character sample image each column
As the corresponding row pixel point value of pixel characteristic value template of the correspondence character in the preset configuration list;
The pixel characteristic value template of the correspondence character is stored in preset configuration list.
6. a kind of identifying device of forge or true or paper money, it is characterised in that the identifying device of the forge or true or paper money includes:
Crown word number acquiring unit, the multiple crown word number area images for obtaining bank note;
Character information recognition unit, for recognizing the crown word number information in the multiple crown word number area image;
Character information identifying unit, it is whether consistent for judging the crown word number information in the multiple crown word number area image;
Identification unit, the true and false for recognizing the bank note according to judged result.
7. the identifying device of forge or true or paper money according to claim 6, it is characterised in that character information recognition unit includes:
Character segmentation unit, for the multiple crown word number area image to be divided into multiple words respectively according to default segmentation strategy
Symbol subgraph, each character subgraph includes a character information;
Character recognition unit, for the multiple included in the multiple character subgraphs for recognizing each crown word number area image respectively
Character information, and the crown word number information according to corresponding to the multiple character information generates the crown word number area image.
8. the identifying device of forge or true or paper money according to claim 7, it is characterised in that the default segmentation strategy is specific
For:
The default screens cutting board matched with the crown word number area image is chosen by template matching algorithm;
The crown word number area image is cut into multiple character subgraphs using the default screens cutting board for matching.
9. the identifying device of the forge or true or paper money according to claim 7 or 8, it is characterised in that the character recognition unit tool
Body includes:
Pixel point value computing unit, for by often row pixel point value and each column pixel point value in the multiple character subgraph,
Row pixel point value corresponding with the multiple pixel characteristic value templates in preset configuration list and row pixel point value are poor respectively
Square operation, obtains multiple difference square values, the pixel characteristic value template one specific word of correspondence in the preset configuration list
Symbol;
Matching value computing unit, for the multiple poor square value to be sued for peace as the coupling number of the pixel characteristic value template
Value;
Template identifying unit, an institute minimum in the multiple pixel characteristic value template, obtaining the matching numerical value
Pixel characteristic value template is stated, using the specific character corresponding to the minimum pixel characteristic value template of the matching numerical value as institute
State the corresponding character of character subgraph.
10. the identifying device of forge or true or paper money according to claim 4, it is characterised in that the identification dress of the forge or true or paper money
Putting also includes:
Character sample acquiring unit, for obtaining multiple character sample images for including identical characters, the multiple character sample
This image is located in the crown word number area image of same position in multiple currency types, face amount identical bank note respectively;
Template generation unit, for mean pixel point value that the multiple character sample image is often gone as the preset configuration
Corresponding row pixel point value in the pixel characteristic value template of the correspondence character in list;The multiple character sample image is every
The mean pixel point value of row is corresponding as the pixel characteristic value template of the correspondence character in the preset configuration list
Row pixel point value;
Template storage unit, the pixel characteristic value template for the correspondence character is stored in preset configuration list.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611112140.3A CN106846603B (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of forge or true or paper money and its device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611112140.3A CN106846603B (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of forge or true or paper money and its device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106846603A true CN106846603A (en) | 2017-06-13 |
CN106846603B CN106846603B (en) | 2019-04-26 |
Family
ID=59146329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611112140.3A Expired - Fee Related CN106846603B (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of forge or true or paper money and its device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106846603B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610317A (en) * | 2017-08-21 | 2018-01-19 | 深圳怡化电脑股份有限公司 | Counterfeit money false distinguishing method and device |
CN111311815A (en) * | 2020-03-16 | 2020-06-19 | 深圳怡化电脑股份有限公司 | Method and device for identifying crown word number, server and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013008176A (en) * | 2011-06-24 | 2013-01-10 | Hitachi Omron Terminal Solutions Corp | Automatic transaction device with image tracing function |
CN103679918A (en) * | 2014-01-06 | 2014-03-26 | 成都术有科技有限公司 | High-speed banknote serial number extraction and identification method based on DSP (digital signal processor) |
CN104036271A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying crown word number of paper money and character, and ATM (Automatic Teller Machine) |
CN205670338U (en) * | 2016-06-17 | 2016-11-02 | 光荣电子工业(苏州)有限公司 | There is the cleaning-sorting machine of the splicing pseudo-function of coin inspection |
-
2016
- 2016-12-06 CN CN201611112140.3A patent/CN106846603B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013008176A (en) * | 2011-06-24 | 2013-01-10 | Hitachi Omron Terminal Solutions Corp | Automatic transaction device with image tracing function |
CN103679918A (en) * | 2014-01-06 | 2014-03-26 | 成都术有科技有限公司 | High-speed banknote serial number extraction and identification method based on DSP (digital signal processor) |
CN104036271A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying crown word number of paper money and character, and ATM (Automatic Teller Machine) |
CN205670338U (en) * | 2016-06-17 | 2016-11-02 | 光荣电子工业(苏州)有限公司 | There is the cleaning-sorting machine of the splicing pseudo-function of coin inspection |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610317A (en) * | 2017-08-21 | 2018-01-19 | 深圳怡化电脑股份有限公司 | Counterfeit money false distinguishing method and device |
CN107610317B (en) * | 2017-08-21 | 2019-09-20 | 深圳怡化电脑股份有限公司 | Counterfeit money false distinguishing method and device |
CN111311815A (en) * | 2020-03-16 | 2020-06-19 | 深圳怡化电脑股份有限公司 | Method and device for identifying crown word number, server and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106846603B (en) | 2019-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10410309B2 (en) | Classification and authentication of identification documents using a convolutional neural network | |
Ferrer et al. | Robustness of offline signature verification based on gray level features | |
US8442319B2 (en) | System and method for classifying connected groups of foreground pixels in scanned document images according to the type of marking | |
EP2937819B1 (en) | System which uses information code | |
CN110503054B (en) | Text image processing method and device | |
US7599528B1 (en) | Offline signature verification using high pressure regions | |
US20170200247A1 (en) | Systems and methods for authentication of physical features on identification documents | |
Ahmed et al. | Forgery detection based on intrinsic document contents | |
CN102292700A (en) | System and method for enhancing security printing | |
CN110263616A (en) | A kind of character recognition method, device, electronic equipment and storage medium | |
CN112528998B (en) | Certificate image processing method and device, electronic equipment and readable storage medium | |
CN107067533A (en) | The method and device that a kind of bank note differentiates | |
CN108154132A (en) | Method, system and equipment for extracting characters of identity card and storage medium | |
CN103729656A (en) | Seal imprint identification method and identification system | |
Abramova et al. | Detecting copy–move forgeries in scanned text documents | |
CN108830275A (en) | Dot character, the recognition methods of dot matrix digit and device | |
CN108320373A (en) | A kind of method and device of the detection of guiding against false of paper currency mark | |
CN107463866A (en) | A kind of method of the hand-written laboratory report of identification for performance evaluation | |
CN106920318A (en) | The discrimination method and device of a kind of bank note | |
CN106846603A (en) | A kind of recognition methods of forge or true or paper money and its device | |
CN113888675A (en) | Method, system, apparatus, and medium for generating a document image | |
CN106898078A (en) | A kind of recognition methods of Hongkong dollar version and device | |
CN113920434A (en) | Image reproduction detection method, device and medium based on target | |
CN106355743A (en) | Banknote version identification method and device | |
CN110598575B (en) | Form layout analysis and extraction method and related device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190426 Termination date: 20211206 |