CN106846603B - 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
- CN106846603B CN106846603B CN201611112140.3A CN201611112140A CN106846603B CN 106846603 B CN106846603 B CN 106846603B CN 201611112140 A CN201611112140 A CN 201611112140A CN 106846603 B CN106846603 B CN 106846603B
- Authority
- CN
- China
- Prior art keywords
- character
- word number
- crown word
- true
- template
- 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.)
- Expired - Fee Related
Links
Abstract
The present invention relates to a kind of recognition methods of forge or true or paper money and its devices, this method comprises: obtaining multiple crown word number area images of bank note;Identify 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 identified according to judging result.The embodiment of the present invention is by judging whether the information of multiple crown word numbers is consistent, to identify the true and false of bank note, the differentiation for manually carrying out the true and false is not needed, also the image that purple light projection post analysis shows is not relying on to determine forge or true or paper money, the recognition efficiency for improving forge or true or paper money identification also reduces the cost of forge or true or paper money identification.
Description
Technical field
The invention belongs to the recognition methods of paper money recognition field more particularly to a kind of forge or true or paper money and its devices.
Background technique
With the development of economy, the amount of paper money in circulation is also corresponding increasing, and criminal 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 is mainly thrown using purple light
Penetrate after bank note, then by manually identify the bank note whether presentation attributes image, recognition efficiency is lower, and needs using purple light
Grenade instrumentation causes to identify higher cost.
Summary of the invention
A kind of recognition methods for being designed to provide forge or true or paper money of the embodiment of the present invention and its device, it is intended to solve existing
Forge or true or paper money identification method recognition efficiency it is low, and need to cause to identify higher cost using purple light grenade instrumentation.
The embodiments of the present invention are implemented as follows, a kind of recognition methods of forge or true or paper money, which comprises
Obtain multiple crown word number area images of bank note;
Identify 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 identified according to judging result.
On the other hand, the embodiment of the present invention provides a kind of identification device of forge or true or paper money, and described device includes:
Crown word number acquiring unit, for obtaining multiple crown word number area images of bank note;
Character information recognition unit, for identification the crown word number information in the multiple crown word number area image;
Character information judging unit, for judge the crown word number information in the multiple crown word number area image whether one
It causes;
Identification unit, for identifying the true and false of the bank note according to judging 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
The embodiment of the present invention is by judging whether the information of multiple crown word numbers is consistent, to identify the true and false of bank note, because illegal
Molecule is during manufacturing counterfeit money, due to the not perfect of technology and the relationship of a large amount of photocopy of urgent need, in printing crown word number mistake
Cheng Zhong, the case where often will appear wrongly typed, bite.And the legal bank note of country's distribution 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, does not need manually to carry out
The differentiation of the true and false is not relying on the image that purple light projection post analysis shows also to determine 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.
Detailed description of the invention
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 be another embodiment of the present invention provides a kind of forge or true or paper money recognition methods flow chart;
Fig. 3 be another embodiment of the present invention provides a kind of forge or true or paper money recognition methods in segmentation strategy detailed process
Figure;
Fig. 4 be another embodiment of the present invention provides a kind of forge or true or paper money recognition methods in, the specific implementation stream of S206
Cheng Tu;
Fig. 5 is a kind of structural block diagram of the identification device of forge or true or paper money provided in an embodiment of the present invention;
Fig. 6 be another embodiment of the present invention provides a kind of forge or true or paper money identification device structural block diagram;
Fig. 7 be another embodiment of the present invention provides a kind of forge or true or paper money identification device in character recognition unit it is specific
Structural block diagram.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
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.
The embodiment of the present invention mainly passes through judge whether the character information of the multiple characteristic images of bank note is consistent, 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 identification method is low, and needs to utilize purple light
Grenade instrumentation causes to identify higher cost.
In embodiments of the present invention, the executing subject of process is forge or true or paper money identification device.The forge or true or paper money identification dress
It sets and can be used alone, other devices can also be cooperated to use or be assembled in and used in other devices as component.Fig. 1 shows this hair
The implementation flow chart of the recognition methods for the forge or true or paper money that bright embodiment provides, 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 be shot by external devices to be obtained, can also be by true in bank note
Setting sensor devices directly generate corresponding image in pseudo- identification device.
In the present embodiment, since prefix code is to identify the sequence number of forge or true or paper money and comprising the relevant information of the bank note,
Therefore all types of bank note will certainly exist prefix code.Thus using prefix code as characteristic image, it may be used on existing all paper
In 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 identified.
In the present embodiment, identify crown word number information mode there are many, can the character information to crown word number identify one by one;
Crown word number can also be identified as a whole, extract the information image 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 correspondingly, different according to the difference of identification crown word number information mode.If
The character information for identifying crown word number one by one, then compare one by one by the character of crown word number information in multiple crown word number area images and sentence
It is disconnected;If crown word number information is identified as a whole, then by multiple crown word numbers in multiple crown word number area images
Judgement is integrally compared in information.
In S104, the true and false of the bank note is identified according to judging result.
In the present embodiment, if the character information for including in multiple crown word number area images in S103 is all identical,
Then determine the bank note for 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 includes is not identical, then judges the bank note for counterfeit money.
Preferably, if judging the bank note for counterfeit money, the bank note is placed in 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 difference placement is carried out with genuine notes, in case a large amount of bank note are identified
After operation, counterfeit money is still mixed into genuine notes.
The embodiment of the present invention is by judging whether the information of multiple crown word numbers is consistent, to identify the true and false of bank note, because illegal
Molecule is during manufacturing counterfeit money, due to the not perfect of technology and the relationship of a large amount of photocopy of urgent need, in printing crown word number mistake
Cheng Zhong, the case where often will appear wrongly typed, bite.And the legal bank note of country's distribution 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, does not need manually to carry out
The differentiation of the true and false is not relying on the image that purple light projection post analysis shows also to determine 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 another embodiment of the present invention provides a kind of forge or true or paper money recognition methods flow chart.Referring to fig. 2
Shown, relative to a upper embodiment, a kind of recognition methods of forge or true or paper money provided in this 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 include a character information.
In the present embodiment, for the ease of the character recognition in later period, the character picture that will include in crown word number area image,
It is unit according to character, is divided into independent character subgraph one by one.The storage order of character subgraph after segmentation, according to word
The sequence in information image region is accorded with, from left to right, is from top to bottom successively stored in registers.Character subgraph after segmentation
Indicate a corresponding character.
In the present embodiment, segmentation strategy refers specifically to the method according to matching algorithm by picture segmentation.Illustratively,
In the present embodiment, each pixel point value of continuous two column is identical or the difference of pixel point value is less than preset threshold by detecting, then
Judge to need to divide at this.
In S206, multiple characters included in multiple character subgraphs of each crown word number area image are identified respectively
Information, and according to the multiple character information generate the crown word number area image corresponding to crown word number information.
Preferably, in the present embodiment, the method for identifying character information is by the template of character subgraph and specification character
It is compared, matching template of the smallest template of selection differences as character subgraph, the corresponding character of matching template is should
Character represented by character subgraph.
In the present embodiment, it generates the corresponding crown word number information of the crown word number area image and comes specifically, will identify that
Character information, carry out rearrangement combination in the sequence 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, to reduce the operand of identification character, mentioned
The efficiency of high truth identification.The case where due to characters multiple for one mixing in one image, identification is needed by a large amount of
Permutation and combination scheme identification is compared, this will will increase the recognition time of computer, and know since multiple characters mix
The interference between image character can not be generated, to lower the accuracy rate of identification.And single character separately identify will solve it is above-mentioned
Problem.
Further, as another embodiment of the invention, the recognition methods of the forge or true or paper money further include:
In S201, obtain it is multiple include identical characters character sample image, the multiple character sample image point
Not Wei Yu multiple currency types, in the identical bank note of face amount in the crown word number area image of same position.
In the present embodiment, it in order to obtain enough samples as the matched template of character subgraph, needs at such
In type bank note, a large amount of sample image is acquired, and sample image collected should belong to positioned at the same crown word number area image
It is interior.For different characteristic images, even if indicating same character, because font and the relationship of stretcher strain, will affect the hat
The pixel distribution of character subgraph in font size area image.Therefore, the pixel in collecting sample, corresponding to the 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.A large amount of sample image quantity is acquired, can be made
Template is more representative, overcomes the error generated because of the influence of noise or shooting machine.
In S202, using the mean pixel point value of the multiple every row of character sample image 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 arranges accordingly as the pixel characteristic value template of the correspondence character in the preset configuration list
Pixel point value.
In the present embodiment, the every row pixel point value of each column in pixel characteristic value template by sample mean pixel point value structure
At.Multiple sample images are acquired in S201 step, and the pixel point value of corresponding row is added again divided by sample size
Obtain mean pixel point value.Particularly, for binary image, since sample image should only have 0 or 255 two values, because
This should choose 127 and be used as benchmark value, is i.e. the mean pixel point value is not more than 127, then sentences when being averaging pixel point value
The pixel point value of breaking is 0;Conversely, then judging the pixel point value for 255.
In S203, the pixel characteristic value template of the correspondence character is stored in preset configuration list.
In embodiments of the present invention, by the image in actual banknote as sample form, 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 can be improved 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 in embodiment illustrated in fig. 1 S101 and
It is identical that S104 implements process, therefore repeats no more in this embodiment.
Further, as another embodiment of the invention, relative to a upper embodiment, Fig. 3 shows segmentation strategy
Specific steps, the segmentation strategy specifically:
In S301, the default detent to match with the crown word number area image is chosen by template matching algorithm and is cut
Template.
In the present embodiment, different crown word number area images corresponds to different default detent cutting boards, due to font
And the reason of image stretch, elemental area shared by each character is also different, therefore, for different crown word number administrative division maps
Picture distributes different default detent cutting boards.
In the present embodiment, since crown word number is that a line is sequentially arranged, column cutting line can be first chosen, by crown word number area
Area image is that unit is successively cut apart by character.If character information described in the crown word number area image be not it is horizontally arranged,
It is horizontally arranged to character that the crown word number area image is then subjected to rotation process, then carries out above-mentioned cutting operation.
In S302, the crown word number area image is cut into multiple words using the default detent cutting board matched
Accord with subgraph.
In the present embodiment, by identifying the boundary of character, cutting operation is being carried out using default detent cutting board.It lifts
Example property, which is binary image, pixel point value detection is carried out to the subgraph from left to right, when first
The secondary pixel point value for detecting that subgraph column include is 0 pixel, then judges that this is classified as the left margin of a character subgraph;
It is 0 pixel when being consecutively detected a few pixel point values not included that arrange of the subgraph, then judges 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
Then the character boundary of subgraph applies cutting board again and carries out cutting operation.
In invention is implemented, by using identical format and size, character subgraph is intercepted, character subgraph can be convenient for
Storage and identification, to improve the accuracy rate of forge or true or paper money identification.
Further, referring to fig. 4, as another embodiment of the invention, relative to embodiment shown in Fig. 2, this reality
It applies example and identifies that multiple character informations included in multiple character subgraphs of each crown word number area image are done respectively to described
Further refinement, details are as follows:
It is described to identify multiple character informations included in multiple character subgraphs of each crown word number area image respectively
Specifically:
In S401, by row pixel point value every in the multiple character subgraph and each column pixel point value, respectively and in advance
If the corresponding row pixel point value of pixel characteristic value template and column pixel point value in configured list carry out poor square operation, obtain
Multiple difference square values, the corresponding specific character of pixel characteristic value template in the preset configuration list.
In the present embodiment, since character subgraph stores in a digital format, character subgraph is considered as one
A image being made of multiple pixel grid points, the character subgraph each column or row have several pixels, the pixel
Point has pixel point value, for colored image, constitutes the pixel point value by tri- pixel values of RGB;For gray level image, then by
Pixel point value of the gray value of the point as the point;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, template and 10 numeric words comprising corresponding to 26 upper case alphabetic characters
The template of symbol.
Preferably, in the present embodiment, the corresponding preset configuration list of each crown word number area image, 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 carried out with different fonts printing or through typesetting and stretcher strain cause display on have any different,
Therefore be conducive to improve matched accuracy using different lists.
In S402, the multiple poor square value summation is stated to 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 distribution are as follows:The wherein pixel point value distribution of a pixel characteristic value template are as follows: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 the difference square of the two is (510-255)2=65025.Remaining each row
Each Leie time calculates, and the sum of poor square value obtained is the matching numerical value of the pixel characteristic value template.
In S403, in the multiple pixel characteristic value template, the smallest picture of matching numerical value is obtained
Plain characteristic value template, using specific character corresponding to the smallest pixel characteristic value template of matching numerical value as the word
Accord with the corresponding character of subgraph.
In the present embodiment, since the matching value for after poor square operation, obtaining image can effectively indicate multiple
Matching degree between image, therefore, selection matching the smallest corresponding pixel characteristic value template of numerical value, it is believed that the template be with
The character subgraph most similar pixel characteristic value template in preset configuration list.
Preferably, if character pixel template corresponding to matching numerical value minimum is selected using identification strategy there are multiple
Optimum Matching template, the identification strategy specifically: judge whether the identical multiple pixel characteristic value templates of the matching value belong to
In same big class template, if so, using character feature diagnostic method;If it is not, then approaching diagnostic method using center.
In the present embodiment, same big class template refers 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 screen pixel characteristic value template using feature decision method.Illustratively, for word
" 6 " and character " 9 " are accorded with, can detect the area pixel point Distribution value in the character subgraph upper right corner, if only a small amount of in the region
The pixel that point value is 0, then judge the corresponding character of character subgraph for " 6 ";Conversely, then corresponding character is " 9 ", remaining
Each major class character can also be carried out further refinement by the method for same feature decision and be differentiated.
In the present embodiment, center approach diagnostic method refer to reduce borderline region differentiation, that is, leave out first trip first with
And footline terminal column, then carry out poor square matches method.Due to multiple pixel characteristic value templates for being not belonging to same major class
It is identical to match numerical value, it may be possible to cause since the noise on boundary is more;On the other hand, when two characters be not belonging to it is same big
Class, closer to picture centre, difference will be bigger, therefore, can be used and gradually decreases boundary, and the method to compare is judged.
In embodiments of the present invention, the smallest matching template of difference is selected as the character subgraph by poor square matches method
The corresponding templates of picture, to identify the character that character subgraph indicates.This method is realized simply, and simple poor square of fortune is passed through
It calculates, that is, can recognize image character, the time of forge or true or paper money identification is improved, to improve recognition efficiency.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Fig. 5 shows the structural block diagram of the identification device of forge or true or paper money provided in an embodiment of the present invention, the forge or true or paper money
The method that identification device is used to execute embodiment illustrated in fig. 1 offer.For ease of description, it illustrates only related to the present embodiment
Part.
Referring to Fig. 5, the identification device of the forge or true or paper money includes:
Crown word number acquiring unit 51, for obtaining multiple crown word number area images of bank note;
Character information recognition unit 52, for identification the crown word number information in the multiple crown word number area image;
Character information judging unit 53, for judge the crown word number information in the multiple crown word number area image whether one
It causes;
Identification unit 54, for identifying the true and false of the bank note according to judging result.
Optionally, shown in Figure 6, in another embodiment, the identification device of the forge or true or paper money in the embodiment is used for
Run the method that embodiment illustrated in fig. 2 provides, the identification device of the forge or true or paper money further include:
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 include a character information;
Character recognition unit 66, for being identified included in multiple character subgraphs of each crown word number area image respectively
Multiple character informations, and according to the multiple character information generate the crown word number area image corresponding to crown word number letter
Breath.
Optionally, the identification device of the forge or true or paper money further include:
Character sample acquiring unit 61, for obtaining multiple character sample images comprising identical characters, multiple words
Symbol sample image is located in the identical bank note of multiple currency types, face amount in the crown word number area image of same position;
Template generation unit 62, for using the mean pixel point value of multiple every rows of character sample image as described pre-
If corresponding to corresponding row pixel point value in the pixel characteristic value template of the character in configured list;By multiple character samples
Pixel characteristic value mould of the mean pixel point value of image each column as the correspondence character in the preset configuration list
The corresponding column pixel point value of plate;
Template storage unit 63, the pixel characteristic value template for the correspondence character are stored in preset configuration list
In.
It should be noted that in the present embodiment 64 and 67 due to 51 and 54 specific structures in embodiment illustrated in fig. 5
The function of making and realize is identical, therefore repeats no more in this embodiment.
Specifically, the segmentation strategy specifically:
The default detent cutting board to match 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 detent cutting board matched.
Specifically, referring to Fig. 7, the character recognition unit is specifically included:
Pixel point value computing unit 71 is used for row pixel point value every in the multiple character subgraph and each column pixel
Point value, respectively row pixel point value corresponding with multiple pixel characteristic value templates in preset configuration list and column pixel point value into
Row difference square operation obtains multiple poor square values, and pixel characteristic value template corresponding one in the preset configuration list is specific
Character;
Matching value computing unit 72, for summing the multiple poor square value as the pixel characteristic value template
With numerical value;
Template judging unit 73, for it is the smallest to obtain the matching numerical value in the multiple pixel characteristic value template
One pixel characteristic value template, by specific character corresponding to the smallest pixel characteristic value template of matching numerical value
As the corresponding character of the character subgraph.
Therefore, the identification 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 for including in area image is consistent, to identify the true and false of bank note, does not need the differentiation for manually carrying out the true and false,
The image that purple light projection post analysis shows is not relying on to determine forge or true or paper money, thus improves the efficiency of forge or true or paper money identification,
Also reduce the cost of forge or true or paper money identification device.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device and method can pass through others
Mode is realized.For example, system embodiment described above is only schematical, for example, the division of the module or unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be with
In conjunction with or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling or direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING of device or unit or
Communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional module in each embodiment of the present invention can integrate in one processing unit
It is that modules physically exist alone, can also be integrated in one unit with two or more modules.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the embodiment of the present invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be with software product in other words
Form embody, which is stored in a storage medium, including some instructions use so that one
Computer equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute this hair
The all or part of the steps of bright each embodiment the method for embodiment.And storage medium above-mentioned include: USB flash disk, mobile hard disk,
Read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic
The various media that can store program code such as dish or CD.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (6)
1. a kind of recognition methods of forge or true or paper money, which is characterized in that the recognition methods of the forge or true or paper money includes:
Obtain multiple crown word number area images of bank note;
Identify 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 identified according to judging result;
It is described to identify that the crown word number information in the multiple crown word number 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;
Multiple character informations included in multiple character subgraphs of each crown word number area image are identified respectively, and according to institute
It states multiple character informations and generates crown word number information corresponding to the crown word number area image;
It is described to identify that multiple character informations included in multiple character subgraphs of each crown word number area image are specific respectively
Are as follows:
By row pixel point value every in the multiple character subgraph and each column pixel point value, respectively and in preset configuration list
The corresponding row pixel point value of multiple pixel characteristic value templates and column pixel point value carry out poor square operation, obtain multiple differences squares
It is worth, the corresponding specific character of the pixel characteristic value template in the preset configuration list;
The matching numerical value that the multiple poor square value is summed as the pixel characteristic value template;
In the multiple pixel characteristic value template, described the smallest one pixel characteristic value template of matching numerical value is obtained,
It is corresponding using specific character corresponding to the smallest pixel characteristic value template of matching numerical value as the character subgraph
Character.
2. the recognition methods of forge or true or paper money according to claim 1, which is characterized in that the default segmentation strategy is specific
Are as follows:
The default detent cutting board to match 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 detent cutting board matched.
3. the recognition methods of forge or true or paper money according to claim 1, which is characterized in that the recognition methods of the forge or true or paper money
Further include:
Obtain it is multiple include identical characters character sample image, the multiple character sample image is located at multiple coin
In kind, the identical bank note of face amount in the crown word number area image of same position;
Using the mean pixel point value of the multiple every row of character sample image as corresponding to the 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
The corresponding column pixel point value of pixel characteristic value template as the correspondence character in the preset configuration list;
The pixel characteristic value template of the correspondence character is stored in preset configuration list.
4. a kind of identification device of forge or true or paper money, which is characterized in that the identification device of the forge or true or paper money includes:
Crown word number acquiring unit, for obtaining multiple crown word number area images of bank note;
Character information recognition unit, for identification the crown word number information in the multiple crown word number area image;
Character information judging unit, for judging whether the crown word number information in the multiple crown word number area image is consistent;
Identification unit, for identifying the true and false of the bank note according to judging result;
The 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
Subgraph is accorded with, each character subgraph includes a character information;
Character recognition unit, it is multiple included in multiple character subgraphs of each crown word number area image for identifying respectively
Character information, and according to the multiple character information generate the crown word number area image corresponding to crown word number information;
The character recognition unit specifically includes:
Pixel point value computing unit is used for row pixel point value every in the multiple character subgraph and each column pixel point value,
Row pixel point value corresponding with multiple pixel characteristic value templates in preset configuration list and column pixel point value carry out poor respectively
Square operation obtains multiple poor square values, the corresponding specific word of pixel characteristic value template in the preset configuration list
Symbol;
Matching value computing unit, the coupling number for summing the multiple poor square value as the pixel characteristic value template
Value;
Template judging unit, for obtaining the smallest institute of matching numerical value in the multiple pixel characteristic value template
Pixel characteristic value template is stated, using specific character corresponding to the smallest pixel characteristic value template of matching numerical value as institute
State the corresponding character of character subgraph.
5. the identification device of forge or true or paper money according to claim 4, which is characterized in that the default segmentation strategy is specific
Are as follows:
The default detent cutting board to match 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 detent cutting board matched.
6. the identification device of forge or true or paper money according to claim 4, which is characterized in that the identification device of the forge or true or paper money
Further include:
Character sample acquiring unit, for obtain it is multiple include identical characters character sample image, the multiple character sample
This image is located in the identical bank note of multiple currency types, face amount in the crown word number area image of same position;
Template generation unit, for using the mean pixel point value of the multiple every row of character sample image as the preset configuration
Corresponding row pixel point value in the pixel characteristic value template of the character is corresponded in list;The multiple character sample image is every
The mean pixel point value of column is corresponding as the pixel characteristic value template of the correspondence character in the preset configuration list
Column pixel point value;
Template storage unit, the pixel characteristic value template for the correspondence character are 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 CN106846603A (en) | 2017-06-13 |
CN106846603B true 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) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN111311815B (en) * | 2020-03-16 | 2022-05-13 | 深圳怡化电脑股份有限公司 | Crown word number identification method, device, 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 |
Also Published As
Publication number | Publication date |
---|---|
CN106846603A (en) | 2017-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yao et al. | Detecting texts of arbitrary orientations in natural images | |
US9031294B2 (en) | Region segmented image data creating system and feature extracting system for histopathological images | |
EP2937819B1 (en) | System which uses information code | |
Dhanya et al. | Script identification in printed bilingual documents | |
JP5219211B2 (en) | Banknote confirmation method and apparatus | |
EP3570215A1 (en) | Document verification method, device, electronic device, and storage medium | |
CN109635818A (en) | The anti-counterfeit of seals method of inspection, device and computer readable storage medium | |
US20080159614A1 (en) | Validation template for valuable media of multiple classes | |
CN110503054B (en) | Text image processing method and device | |
US7599528B1 (en) | Offline signature verification using high pressure regions | |
CN112528998B (en) | Certificate image processing method and device, electronic equipment and readable storage medium | |
CN109214385A (en) | Collecting method, data acquisition device and storage medium | |
CN110263616A (en) | A kind of character recognition method, device, electronic equipment and storage medium | |
CN110490199A (en) | A kind of method, apparatus of text identification, storage medium and electronic equipment | |
CN108154132A (en) | A kind of identity card text extraction method, system and equipment and storage medium | |
CN106846603B (en) | A kind of recognition methods of forge or true or paper money and its device | |
CN107067533A (en) | The method and device that a kind of bank note differentiates | |
CN109740417A (en) | Invoice type recognition methods, device, storage medium and computer equipment | |
CN112017352B (en) | Certificate authentication method, device, equipment and readable storage medium | |
CN103729656A (en) | Seal imprint identification method and identification system | |
CN108830275A (en) | Dot character, the recognition methods of dot matrix digit and device | |
CN110009080B (en) | Two-dimensional code generation method, verification method, server and two-dimensional code | |
CN106898078A (en) | A kind of recognition methods of Hongkong dollar version and device | |
CN108427923A (en) | A kind of palm grain identification method and device | |
EP1944737A1 (en) | Validation template for valuable media of multiple classes |
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 |
Granted publication date: 20190426 Termination date: 20211206 |
|
CF01 | Termination of patent right due to non-payment of annual fee |