CN107331030A - A kind of crown word number identification method, device, equipment and storage medium - Google Patents
A kind of crown word number identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN107331030A CN107331030A CN201710491147.9A CN201710491147A CN107331030A CN 107331030 A CN107331030 A CN 107331030A CN 201710491147 A CN201710491147 A CN 201710491147A CN 107331030 A CN107331030 A CN 107331030A
- Authority
- CN
- China
- Prior art keywords
- identified
- chain code
- code
- subchain
- word number
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Character Discrimination (AREA)
Abstract
The embodiment of the invention discloses a kind of crown word number identification method, device, equipment and storage medium.Recognition methods includes:Topography corresponding with the target identification character in crown word number region to be identified is obtained, and generates part chain code to be identified corresponding with the topography;According to subclass partition strategy, generate at least one subchain code collection to be identified corresponding with part chain code to be identified and close;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;Closed and standard character set according to the subchain code collection to be identified, the target identification character in the crown word number region to be identified is identified;The standard character set includes multiple standard characters.The embodiment of the present invention uses chain code tab character profile by being divided into single character to crown word number in banknote image, and then realizes the identification to crown word number.The interference that exclusion that can be intelligent is stained is recognized using profile chain code, so as to improve the accuracy of crown word number recognition result.
Description
Technical field
The present embodiments relate to withdrawal technical field, more particularly to a kind of crown word number identification method, device, equipment and
Storage medium.
Background technology
The gradually increase measured with note-issue, the counterfeit protection measures of RMB also strengthen therewith.Because crown word number can be made
To judge a decision factor of the RMB true and false, therefore it is widely used in the scheme of RMB truth identification.Every people
The people carry out unique mark by crown word number, and the true and false that checking can determine that crown word number is carried out by identification and to the crown word number of identification.
Have by carrying out horizontal and vertical projecting integral to binary image to position and split prefix in the prior art
Number, and then identify crown word number.
But this method is relatively low to crown word number recognition accuracy, it is therefore necessary to release a kind of new technical scheme to solve
Above-mentioned technical problem.
The content of the invention
The embodiment of the present invention provides a kind of crown word number identification method, device, equipment and storage medium, to accurately identify banknote
In serial number.
In a first aspect, the embodiments of the invention provide a kind of crown word number identification method, including:
Topography corresponding with the target identification character in crown word number region to be identified is obtained, and is generated and the part
The corresponding part of image chain code to be identified;
According to subclass partition strategy, at least one subchain code to be identified corresponding with part chain code to be identified is generated
Set;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;
Closed and standard character set according to the subchain code collection to be identified, to the mesh in the crown word number region to be identified
Mark malapropism symbol is identified;The standard character set includes multiple standard characters.
Further, the subclass partition strategy includes unequal division chain code strategy, the subchain code collection to be identified
Conjunction includes the first subchain code collection to be identified and closed and the second subchain code collection conjunction to be identified;
It is corresponding, it is described according to subclass partition strategy, generate it is corresponding with part chain code to be identified at least one
Subchain code collection to be identified, which is closed, to be included:
At least two first partitioning sites are determined according to the unequal partition strategy, and according to first partitioning site
Part chain code to be identified is divided, and generates the first subchain code collection to be identified and is closed;
At least one second partitioning site is determined according to the unequal partition strategy, and according to second partitioning site
Part chain code to be identified is divided, and generates the second subchain code collection to be identified and is closed.
Further, closed and standard character set according to the subchain code collection to be identified, to the crown word number to be identified
Target identification character in region is identified, including:
Calculate the corresponding chain code data rate of specific gravity of each subchain code to be identified during the subchain code collection to be identified is closed;
By the chain code data rate of specific gravity, chain code data proportion value set corresponding with default whole standard character difference
Matched;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then by the mesh
Mark malapropism symbol is identified as being stained.
Further, before the target identification character in the crown word number region to be identified is identified, also wrap
Include:
Calculate whole standard characters and distinguish corresponding chain code data proportion value set.
Second aspect, the embodiments of the invention provide a kind of crown word number identifying device, including:
Local chain code acquisition module to be identified, it is corresponding with the target identification character in crown word number region to be identified for obtaining
Topography, and generate corresponding with topography part chain code to be identified;
Subchain code collection to be identified closes generation module, for generate it is corresponding with part chain code to be identified at least one treat
Recognize that subchain code collection is closed;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;
Character recognition module, for being closed and standard character set according to the subchain code collection to be identified, waits to know to described
Target identification character in other crown word number region is identified, and the standard character set includes multiple standard characters.
Further, the subclass partition strategy includes unequal division chain code strategy, the subchain code collection to be identified
Conjunction includes the first subchain code collection to be identified and closed and the second subchain code collection conjunction to be identified;
Corresponding, the subchain code collection to be identified, which closes generation module, to be included:
First subchain code collection to be identified closes generation unit, for determining at least two the according to the unequal partition strategy
One partitioning site, and the part chain code to be identified is divided according to first partitioning site, and generate the first subchain to be identified
Code collection is closed;
Second subchain code collection to be identified closes generation unit, and at least one second stroke is determined according to the unequal partition strategy
Partial node, and the part chain code to be identified is divided according to second partitioning site, and generate the second subchain code collection to be identified
Close.
Further, the character recognition module includes:
Chain code data rate of specific gravity computing unit, calculates each subchain code to be identified during the subchain code collection to be identified is closed corresponding
Chain code data rate of specific gravity;
By the chain code data rate of specific gravity, chain code data proportion value set corresponding with default whole standard character difference
Matched;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then by the mesh
Mark malapropism symbol is identified as being stained.
Further, the crown word number identifying device also includes:
Chain code data rate of specific gravity set calculation module, corresponding chain code data are distinguished for calculating whole standard characters
Proportion value set.
The third aspect, the embodiments of the invention provide a kind of equipment, the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the crown word number identification method described in the embodiment of the present invention.
Fourth aspect, the embodiments of the invention provide a kind of computer-readable recording medium, is stored thereon with computer journey
Sequence, the program realizes the crown word number identification method described in the embodiment of the present invention when being executed by processor.
The embodiment of the present invention uses chain code tab character wheel by being divided into single character to crown word number in banknote image
Exterior feature, and then realize the identification to crown word number.The interference that exclusion that can be intelligent is stained is recognized using profile chain code, so as to improve
The accuracy of crown word number recognition result.
Brief description of the drawings
Fig. 1 is a kind of crown word number identification method flow chart that the embodiment of the present invention one is provided;
Fig. 2 is a kind of crown word number identification method flow chart that the embodiment of the present invention two is provided;
Fig. 3 is a kind of crown word number identifying device structural representation that the embodiment of the present invention four is provided;
Fig. 4 is a kind of structural representation for crown word number identification equipment that the embodiment of the present invention five is provided.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of crown word number identification method flow chart that the embodiment of the present invention one is provided, and the crown word number identification method can
With situation about being identified suitable for the crown word number to bank note, this method can be performed by crown word number identifying device, the device
It can be realized by the way of software and/or hardware, and can typically be integrated in the various gold for needing to carry out forge or true or paper money identification
Melt in equipment, for example, ATM or cash inspecting machine etc., the method for the present embodiment specifically include following steps:
S110, acquisition topography corresponding with the target identification character in crown word number region to be identified, and generate and institute
State the corresponding part of topography chain code to be identified.
Wherein, crown word number region is the region where serial number in bank note, can be located at the lower left corner part of bank note.Show
Example property, its size of the RMB of 100 yuan of face amounts is 165*77mm, using 1mm as coordinate system unit, crown word number region for (5,
15) rectangular area of (45,15) (45,20) (5,20) composition.
Serial number in crown word number region is used to record emission of banknotes sequence, can be by Arabic numerals and word
Mother's composition.
Optionally, the pretreatment operation is used to crown word number region segmentation distinguishing institute for multiple independent prefix sign characters
The zonule at place, can there is accomplished in many ways, for example, because the distance between multiple independent crown word numbers are determined, and crown word number area
Domain is determined, crown word number region can be divided into the region of quantity identical with independent crown word number according to region set in advance;Again
For example, binary conversion treatment can be carried out to crown word number, and according in prefix sign character region in binary conversion treatment picture
The difference of the value of pixel in pixel and white space, to crown word number region split obtaining each respective character and corresponding to respectively
Topography.
The topography includes at least one prefix sign character, can be by recognizing topography and then obtaining each only
Sign an agreement, a contract, a receipt, etc. symbol.It is preferred that, the number of topography is identical with character number in crown word number.
Local chain code to be identified is used for the curved boundary pixel for describing respective character in topography, usually using curve
Starting point coordinate and edge direction.Local chain code to be identified can according to central pixel point adjacent direction number difference,
It is divided into by 4 connection chain codes and 8 connection two kinds of coded systems of chain code.Specifically, the abutment points of 4 connection chain codes have 4, respectively in
The up, down, left and right of heart point.8 connection chain codes add 4 tilted directions than 4 connection chain codes, because around any one pixel
There are 8 abutment points,
It is preferred that, the part chain code to be identified includes:8 connection chain codes.So set and be advantageous in that, 8 connection chain codes
It is consistent with the actual conditions of pixel that respective character is constituted in topography, description central pixel point is adjacent letter a little
Breath is more accurate.
Optionally, the topography includes at least one local chain code to be identified, specifically, what topography included
The quantity of local chain code to be identified is more, and the accuracy rate recognized to respective character in topography is higher, accordingly, identification process
Middle elapsed time is more long, therefore the accuracy rate of the identification time to be consumed and identification can be considered and then set local
The quantity of chain code to be identified.
S120, according to subclass partition strategy, generate that corresponding with part chain code to be identified at least one is to be identified
Subchain code collection is closed;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed.
Wherein, subclass partition strategy is preset by designer, for part chain code to be identified to be divided into
Multiple subchain codes to be identified, number, the subchain code length for the subchain to be identified code that partition strategy is generated are closed using different subsets
Differ.
Specifically, subclass partition strategy includes unequal division chain code strategy and impartial division chain code strategy.Using institute
State the impartial subchain code length divided obtained by chain code strategy identical, therefore the impartial chain code strategy that divides is applied to criteria for classifying word
Do not have the character of similar character profile, the character such as letter r, K in symbol set.Unequal division chain code strategy is used to divide
Without the character that the character of similar character profile, symmetry are stronger in standard character set, such as letter w and M, letter O and
Q, the digital characters such as 6 and 9, the chain code of such character are divided into the subchain code of varying number, different length, to improve identification knot
The accuracy of fruit.
Exemplary, it is resulting using existing crown word number identification method in the identification process of numerical character 6 and 9
Chain code is identical, it is impossible to distinguish.Therefore need to make a distinction using equalization division chain code strategy, optionally, can be by character
Left side intermediate point is as a division points, using central point on the right side of character as another division points, and character chain code is divided into the
One subchain code, the second subchain code and the 3rd subchain three sub- chain codes of code, and based on this three sub- chain code identification prefix sign characters.
S130, closed and standard character set according to the subchain code collection to be identified, to the crown word number region to be identified
In target identification character be identified;The standard character set includes multiple standard characters.
The subchain code collection to be identified, which is closed, includes multiple subchain codes, and subchain code is the chain chip segment in chain code to be identified.
In the target identification character recognition process in crown word number region to be identified, can obtain respectively subchain code collection to be identified close with
And the chain code feature such as the chain code length of each subchain code, number, length of chain code to be identified of subchain code in standard character set, and
Match one by one, when chain code feature is mismatched, then judge that the part recognizes chain code as non-crown word number chain code, and remove the non-hat
Font size chain code, influence of the image to recognition result is stained to reduce.
Specifically, before method execution, can prestore multiple standard character chain code masterplates in database, exemplary,
Standard character chain code masterplate includes the digital chain code masterplate of at least 10 classes and 26 class-letter masterplates, and digital masterplate is used for and numeral
Match somebody with somebody, alphabetical masterplate is used to match with letter.
, can be by the part chain code to be identified in topography and crown word number character chain code masterplate in crown word number identification process
Matched, and then complete the identification to crown word number.
The technical scheme of the present embodiment, by each respective character point in crown word number regional processing and the crown word number region
Not corresponding part chain code to be identified, and then local chain code to be identified accurately identify obtaining crown word number.Solve existing
To the relatively low problem of serial number recognition accuracy in technology, so as to accurately identify the serial number in banknote.
Embodiment two
Fig. 2 is a kind of crown word number identification method flow chart that the embodiment of the present invention two is provided, and the present embodiment is in above-mentioned each reality
Apply on the basis of example, target chain code to be identified is divided using unequal partition strategy, be specially:
S210, calculating whole standard characters distinguish corresponding chain code data proportion value set.
Wherein, standard character is collected by designer, can be the character that predetermined number has regular contour, chain
Code data rate of specific gravity can be multiple chain code proportion values in the chain code for constitute standard character.Specifically, standard character " 0 "
Chain code data proportion value set can be obtained by calculating 10 0 character chain codes of different sizes, and then improve chain code data ratio
The accuracy of weight values set.
S220, acquisition topography corresponding with the target identification character in crown word number region to be identified, and generate and institute
State the corresponding part of topography chain code to be identified.
The present embodiment can carry out binary conversion treatment to the crown word number region, form two after topography is got
Value crown word number image.
Wherein, binary conversion treatment is exactly that the gray value of the pixel on image is set into 0 or 255, that is, will be whole
Image shows obvious black and white effect, image is become simple, highlights the profile of target, and can make picture number
Reduce according to amount.
Binaryzation crown word number image is carried out obtaining after binary conversion treatment by this method to crown word number region, after this method
Continuous operation is carried out all on the basis of binaryzation crown word number image.Calculate respectively and each row pair in the binaryzation crown word number image
The pixel answered and, and obtain and occur pixel and the row being mutated as target column with preceding next two columns.Wherein, mutation include pixel with
By arbitrary value to the change of a certain lowest threshold, pixel and the change by a certain lowest threshold to arbitrary value.Target column is used for sky
The region that white region and prefix sign character are covered is separated.The principle so set is:With blank in binaryzation crown word number image
The pixel value in region is 0, and the pixel value of pixel is exemplified by 255 in prefix sign character institute overlay area, pixel and in 0 row
Each pixel is first 0, illustrate the row be in white space, pixel and be 0 row in each pixel pixel value not all
For 0, illustrate that the row are in the region that prefix sign character is covered, when pixel and when undergoing mutation, illustrate that the row are exactly in sky
The intersection in the region that white region and prefix sign character are covered, now, assign the row as target column.Optionally, in crown word number
There are multiple target columns in region between two neighboring respective character, therefore second of choosing method of target column can also be by elder generation
Choose two pixels and occur respectively it is non-zero to 0 mutation with it is non-zero to 0 mutation two respective columns, and choose the two respective columns
In be used as target column in the row of center.So set and be advantageous in that, it is to avoid because target column is in prefix sign character
Edge and have influence on the segmentation to topography, and then reduce the generation of identification error.
In the binaryzation crown word number image, obtain and the image that surrounds arranged by each adjacent target, as with the prefix
Each respective character distinguishes corresponding topography in number region.
Wherein, the content of topography is relevant with the mode that target column is chosen.Specifically, when equal with preceding next two columns to obtain
Occur pixel and mutation row as target column mode selection target row when, target column be in prefix sign character edge,
Then there are two target columns between the adjacent prefix sign character of each two, the quantity of the corresponding topography got is 3, bag
The topography of a white space topography and two prefix sign character regions is included, is now needed white space office
Portion's image is removed, and then only the topography of prefix sign character region is identified.
When with second of choosing method of target column, include prefix sign character in obtained topography, therefore can
With by second of choosing method of target column it is preferred that, so set and be advantageous in that, it is to avoid remove white space local
The operation of image, saves the acquisition time of topography.
S230, at least two first partitioning sites are determined according to the unequal partition strategy, and according to described first stroke
Partial node divides the part chain code to be identified, and generates the first subchain code collection conjunction to be identified.
In the present embodiment, part chain code to be identified can twice be divided, at least three sections are divided into for the first time
Subchain code to be identified.Wherein, the first partitioning site can be randomly selected or determine the chain code node of default sequence number
For the first division points.
Exemplary, two first divisions can be determined from local chain code to be identified according to the unequal partition strategy
Node, and then generate three section of first subchain code to be identified.
S240, at least one second partitioning site is determined according to the unequal partition strategy, and according to described second stroke
Partial node divides the part chain code to be identified, and generates the second subchain code collection conjunction to be identified.
Wherein, the second partitioning site can randomly select to determine or determine the chain code node of default sequence number.
It is exemplary, can be according to the unequal partition strategy from local chain code to be identified in the second division operation
One the second partitioning site of middle determination, and then generate two section of second subchain code to be identified.
Now, five subchain codes to be identified, and difference to be calculated five can be got for a part chain code to be identified
The chain code data proportion of bar subchain code to be identified, and recognize corresponding standard character according to this five subchain codes to be identified.
Further, second partitioning site should not be excessive with the number of the first division points, and then avoids division operation
The discretization error of middle generation, reduces the accuracy of recognition result.
S250, calculate the corresponding chain code data rate of specific gravity of each subchain code to be identified during the subchain code collection to be identified is closed.
S260, by the chain code data rate of specific gravity, chain code data proportion corresponding with default whole standard character difference
Value set is matched;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then will
The target identification character recognition is to be stained.
In matching process, when both gaps are smaller, both gap numerical value can be expanded by default computing, to carry
The property easy to identify of both high matching degrees.
Specifically, the default computing is included to gap numerical value progress cube computing, to gap numerical value progress square
Computing.
The technical scheme of the present embodiment, target chain code to be identified, and the son to obtaining are divided by unequal partition strategy
The cumulative identification of chain code, improves the accuracy of recognition result.
Embodiment three
The corresponding chain code segmentation of respective character is preferably obtained many height by the present embodiment on the basis of the various embodiments described above
Chain code is simultaneously identified.Accordingly, the method for the present embodiment can include:
Crown word number region is pre-processed, generation and the corresponding part of each respective character difference in the crown word number region
Image.
Generation part chain code to be identified corresponding with each topography.
A part chain code to be identified is obtained successively is used as current operation chain code;
Current operation chain code can be any one in multiple parts chain code to be identified, with current operation in the present embodiment
Chain code is that operation object carries out subsequent operation.
To in the identification process of local chain code to be identified, it is necessary to the corresponding part of multiple topographies chain code to be identified according to
It is secondary to be operated.Operation order can be that right side is terminated since corresponding part chain code to be identified on the left of crown word number region.
Can be from since corresponding part chain code to be identified on the right side of crown word number region, left side is terminated.
According to the chain code length of the current operation chain code, the current operation chain code is divided into the subchain of setting quantity
Code;
Wherein, each chain code in current operation chain code can use numeral 0-7 (8 connection chain code) or/0-3 (4 connection chains
Code) represent, therefore the ordered series of numbers being made up of multiple numerals can be used to represent current operation chain code, chain code length is current operation chain
The number of the corresponding ordered series of numbers of code.Setting quantity can be preset by designer, and subchain code is the chain in current operation chain code
Chip segment.
Further, the setting quantity is more, i.e., subchain number of codes set in advance is more, then to current operation chain code
Middle recognition result is more accurate.
It is preferred that, the numerical value of quantity is set as 3.
According to each other correspondence image profile of subchain code division, calculate and each subchain code division not corresponding chain code spy
Levy, wherein, chain code feature includes:The width of image outline, and/or image outline height;
Wherein, correspondence image profile is the image wheel of parts of images in respective character image corresponding to current operation chain code
Exterior feature, chain code feature can be the width and height of the image outline, for the chain code feature progress pair with being stored in advance in database
Than.Coordinate where the width and height of described image profile can cover pixel by image outline is obtained.
Exemplary, when the current operation chain code is divided into 3 sub- chain codes, the corresponding chain code of the subchain code is special
The number levied is 7, including the chain code length of current chain code, the height of 3 sub- chain code corresponding image profiles and width.
By the chain code length of the current operation chain code and chain code feature not corresponding with each subchain code division, as described
The key recognition feature of current operation chain code.
Judge whether the key recognition feature of the current operation chain code matches with the standard identification feature of standard crown word number.
Whether be last local to be identified chain code, performed if it is not, returning if judging current operation chain code.
The current operation chain code is identified as non-crown word number chain code, and removal is described in part chain code to be identified
Current operation chain code, according to the part chain code to be identified of reservation, carries out crown word number identification.
Wherein, the standard crown word number is the prefix sign character masterplate being stored in advance in database, can include 10 bit digitals
With 26 capitalizations, the standard identification feature is corresponding with standard crown word number.
Optionally, crown word number chain code can be identified with non-crown word number chain code by chain code length.Exemplary, when
The chain code length of the current operation chain code is more than the maximum chain code length in prefix sign character masterplate or less than minimal chain code length
When spending, then the current operation chain code is identified as non-crown word number chain code.Otherwise current operation chain code is identified as crown word number chain
Code, and the subchain code division in the current operational chain code is not compared with the chain code feature in database, and then obtain current
Operate the corresponding prefix sign character of chain code.
Exemplary, face amount is that the number of the prefix sign character in 100 yuan of RMB is 10, then needs to perform on 10 times
Recognition methods is stated, and obtains 10 part chain codes to be identified, so as to complete the processing to global chain code to be identified, and then 10 are obtained
The complete crown word number in position.
The technical scheme of the present embodiment, by the way that the corresponding chain code segmentation of respective character in crown word number is obtained into multiple subchains
Code is identified, and further increases the accuracy of recognition result.
On the basis of above-described embodiment, in addition to:
In the chain code length according to the current operation chain code, the current operation chain code is divided into the son of setting quantity
After chain code, in addition to:
The numeric type included according to each subchain code, calculates normalization chain code value corresponding with each subchain code;
By the chain code length of the current operation chain code and chain code feature not corresponding with each subchain code division, as described
The key recognition feature of current operation chain code, further comprises:
By the chain code length of the current operation chain code, chain code feature not corresponding with each subchain code division and with each subchain
The corresponding normalization chain code value of code, is used as the key recognition feature of the current operation chain code.
Wherein, subchain code is combined by the numeral in 0-7 (8 connection chain code) or 0-3 (4 connection chain code), normalizes chain
Code value can be the ratio value shared by each numeral in subchain code, and will calculate obtained normalization chain code value and be used as crucial recognize
Feature.
In summary, the technical scheme of the embodiment of the present invention, by crown word number regional processing and the crown word number region
In each respective character distinguish corresponding part chain code to be identified, and then local chain code to be identified accurately identify obtaining prefix
Number.Solve in the prior art to the relatively low problem of serial number recognition accuracy, so as to accurately identify the prefix in banknote
Number.
Example IV
Fig. 3 show a kind of crown word number identifying device structural representation of the offer of the embodiment of the present invention four, as shown in figure 3,
The crown word number identifying device includes:Local chain code acquisition module 310 to be identified, subchain code collection to be identified close the and of generation module 320
Character recognition module 330.
On the basis of above-described embodiment, the subclass partition strategy includes unequal division chain code strategy, described to treat
Identification subchain code collection, which is closed, includes the first subchain code collection conjunction to be identified and the second subchain code collection to be identified is closed;
Corresponding, the subchain code collection to be identified, which closes generation module 320, to be included:
First subchain code collection to be identified closes generation unit, for determining at least two the according to the unequal partition strategy
One partitioning site, and the part chain code to be identified is divided according to first partitioning site, and generate the first subchain to be identified
Code collection is closed;
Second subchain code collection to be identified closes generation unit, and at least one second stroke is determined according to the unequal partition strategy
Partial node, and the part chain code to be identified is divided according to second partitioning site, and generate the second subchain code collection to be identified
Close.
On the basis of above-described embodiment, the character recognition module 330 includes:
Chain code data rate of specific gravity computing unit, calculates each subchain code to be identified during the subchain code collection to be identified is closed corresponding
Chain code data rate of specific gravity;
By the chain code data rate of specific gravity, chain code data proportion value set corresponding with default whole standard character difference
Matched;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then by the mesh
Mark malapropism symbol is identified as being stained.
On the basis of above-described embodiment, the crown word number identifying device also includes:
Chain code data rate of specific gravity set calculation module, corresponding chain code data are distinguished for calculating whole standard characters
Proportion value set.
The crown word number identifying device that the embodiment of the present invention is provided can be used for performing the hat that the embodiment of the present invention is provided
Font size recognition methods, possesses corresponding function and beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to
The crown word number identification method that any embodiment of the present invention is provided.
Embodiment five
Fig. 4 is a kind of structural representation for crown word number identification equipment that the embodiment of the present invention five is provided.The embodiment of the present invention
There is provided a kind of equipment, as shown in figure 4, the equipment includes processor 410, memory 420, input unit 430 and output device
440;The quantity of processor 410 can be one or more, in Fig. 4 by taking a processor 410 as an example;Processor in equipment
410th, memory 420, input unit 430 and output device 440 can be connected by bus or other modes.
Memory 410 can perform journey as a kind of computer-readable recording medium available for storage software program, computer
The corresponding programmed instruction of a kind of crown word number identification method in sequence and module, such as embodiment of the present invention.Processor 410 passes through fortune
Row is stored in software program, instruction and module in memory 420, so as to perform the various function application and data of equipment
Processing, that is, realize a kind of above-mentioned crown word number identification method.
Namely:Realized during the computing device described program:Obtain and the target identification in crown word number region to be identified
The corresponding topography of character, and generate part chain code to be identified corresponding with the topography;Plan is divided according to subclass
Slightly, at least one subchain code collection to be identified corresponding with part chain code to be identified is generated to close;Wherein, different subsets, which are closed, divides
The different subchain code collection to be identified of strategy correspondence is closed;Closed and standard character set according to the subchain code collection to be identified, to institute
The target identification character stated in crown word number region to be identified is identified;The standard character set includes multiple standard words
Symbol.
Memory 420 can mainly include storing program area and storage data field, wherein, storing program area can store operation system
Application program needed for system, at least one function;Storage data field can be stored uses created data etc. according to terminal.This
Outside, memory 420 can include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 420 can enter one
Step includes the memory remotely located relative to processor 410, and these remote memories can pass through network connection to equipment.On
The example for stating network includes but is not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Input unit 430 can be used for the numeral or character information for receiving input, and produce with the user of equipment set with
And the relevant key signals input of function control.Output device 440 may include the display devices such as display screen.
Embodiment six
The embodiment of the present invention six also provides a kind of storage medium for including computer executable instructions, and the computer can be held
Row instruction is used to perform a kind of crown word number identification method when being performed by computer processor, and this method includes:
Topography corresponding with the target identification character in crown word number region to be identified is obtained, and is generated and the part
The corresponding part of image chain code to be identified;
According to subclass partition strategy, at least one subchain code to be identified corresponding with part chain code to be identified is generated
Set;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;
Closed and standard character set according to the subchain code collection to be identified, to the mesh in the crown word number region to be identified
Mark malapropism symbol is identified;The standard character set includes multiple standard characters.
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present invention is provided, its computer
The method operation that executable instruction is not limited to the described above, can also carry out the crown word number knowledge that any embodiment of the present invention is provided
Associative operation in other method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to realized by hardware, but the former is more in many cases
Good embodiment.Understood based on such, what technical scheme substantially contributed to prior art in other words
Part can be embodied in the form of software product, and the computer software product can be stored in computer-readable recording medium
In, such as floppy disk, read-only storage (Read-Only Memory, ROM), the random access memory (Random of computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are to cause a computer to set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the invention.
It is worth noting that, in the embodiment of above-mentioned searcher, included unit and module are simply according to work(
Energy logic is divided, but is not limited to above-mentioned division, as long as corresponding function can be realized;In addition, each work(
The specific name of energy unit is also only to facilitate mutually distinguish, the protection domain being not intended to limit the invention.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art it is various it is obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of crown word number identification method, it is characterised in that including:
Topography corresponding with the target identification character in crown word number region to be identified is obtained, and is generated and the topography
Corresponding part chain code to be identified;
According to subclass partition strategy, at least one subchain code collection to be identified corresponding with part chain code to be identified is generated
Close;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;
Closed and standard character set according to the subchain code collection to be identified, the target in the crown word number region to be identified is known
Malapropism symbol is identified;The standard character set includes multiple standard characters.
2. according to the method described in claim 1, it is characterised in that:The subclass partition strategy includes unequal division chain code
Strategy, the subchain code collection to be identified, which is closed, includes the first subchain code collection conjunction to be identified and the second subchain code collection to be identified is closed;
It is corresponding, it is described according to subclass partition strategy, generate it is corresponding with part chain code to be identified at least one wait to know
Small pin for the case chain code set includes:
At least two first partitioning sites are determined according to the unequal partition strategy, and divided according to first partitioning site
The part chain code to be identified, and generate the first subchain code collection conjunction to be identified;
At least one second partitioning site is determined according to the unequal partition strategy, and divided according to second partitioning site
The part chain code to be identified, and generate the second subchain code collection conjunction to be identified.
3. according to the method described in claim 1, it is characterised in that closed and standard character according to the subchain code collection to be identified
Set, the target identification character in the crown word number region to be identified is identified, including:
Calculate the corresponding chain code data rate of specific gravity of each subchain code to be identified during the subchain code collection to be identified is closed;
By the chain code data rate of specific gravity, chain code data proportion value set corresponding with default whole standard character difference is carried out
Matching;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then the target is known
Malapropism symbol is identified as being stained.
4. method according to claim 3, it is characterised in that the target in the crown word number region to be identified is known
Before malapropism symbol is identified, in addition to:
Calculate whole standard characters and distinguish corresponding chain code data proportion value set.
5. a kind of crown word number identifying device, it is characterised in that including:
Local chain code acquisition module to be identified, for obtaining office corresponding with the target identification character in crown word number region to be identified
Portion's image, and generate part chain code to be identified corresponding with the topography;
Subchain code collection to be identified closes generation module, and for generating, corresponding with part chain code to be identified at least one is to be identified
Subchain code collection is closed;Wherein, different subsets are closed the different subchain code collection to be identified of partition strategy correspondence and closed;
Character recognition module, for being closed and standard character set according to the subchain code collection to be identified, to the hat to be identified
Target identification character in font size region is identified, and the standard character set includes multiple standard characters.
6. device according to claim 5, it is characterised in that:The subclass partition strategy includes unequal division chain code
Strategy, the subchain code collection to be identified, which is closed, includes the first subchain code collection conjunction to be identified and the second subchain code collection to be identified is closed;
Corresponding, the subchain code collection to be identified, which closes generation module, to be included:
First subchain code collection to be identified closes generation unit, for determining at least two first strokes according to the unequal partition strategy
Partial node, and the part chain code to be identified is divided according to first partitioning site, and generate the first subchain code collection to be identified
Close;
Second subchain code collection to be identified closes generation unit, determines that at least one second division is saved according to the unequal partition strategy
Point, and the part chain code to be identified is divided according to second partitioning site, and generate the second subchain code collection conjunction to be identified.
7. device according to claim 5, it is characterised in that the character recognition module includes:
Chain code data rate of specific gravity computing unit, calculates the corresponding chain code of each subchain code to be identified during the subchain code collection to be identified is closed
Data rate of specific gravity;
By the chain code data rate of specific gravity, chain code data proportion value set corresponding with default whole standard character difference is carried out
Matching;It is established standardses character by the target identification character recognition if the match is successful;Otherwise, then the target is known
Malapropism symbol is identified as being stained.
8. device according to claim 7, it is characterised in that the crown word number identifying device also includes:
Chain code data rate of specific gravity set calculation module, corresponding chain code data proportion is distinguished for calculating whole standard characters
Value set.
9. a kind of equipment, it is characterised in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The existing crown word number identification method as described in any in claim 1-4.
10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The crown word number identification method as described in any in claim 1-4 is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710491147.9A CN107331030B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710491147.9A CN107331030B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107331030A true CN107331030A (en) | 2017-11-07 |
CN107331030B CN107331030B (en) | 2019-11-15 |
Family
ID=60194561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710491147.9A Active CN107331030B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107331030B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115331235A (en) * | 2022-10-12 | 2022-11-11 | 南通东鼎彩印包装厂 | Fracture adhesion printing digital identification method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101916441A (en) * | 2010-08-06 | 2010-12-15 | 西北工业大学 | Freeman chain code-based method for matching curves in digital image |
CN102521911A (en) * | 2011-12-16 | 2012-06-27 | 尤新革 | Identification method of crown word number (serial number) of bank note |
CN105405204A (en) * | 2015-11-04 | 2016-03-16 | 东方通信股份有限公司 | Banknote crown word number recognition method of currency detector |
CN106447909A (en) * | 2016-09-23 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Vertical serial number identification method and vertical serial number identification device |
CN106650553A (en) * | 2015-10-30 | 2017-05-10 | 比亚迪股份有限公司 | License plate recognition method and system |
-
2017
- 2017-06-23 CN CN201710491147.9A patent/CN107331030B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101916441A (en) * | 2010-08-06 | 2010-12-15 | 西北工业大学 | Freeman chain code-based method for matching curves in digital image |
CN102521911A (en) * | 2011-12-16 | 2012-06-27 | 尤新革 | Identification method of crown word number (serial number) of bank note |
CN106650553A (en) * | 2015-10-30 | 2017-05-10 | 比亚迪股份有限公司 | License plate recognition method and system |
CN105405204A (en) * | 2015-11-04 | 2016-03-16 | 东方通信股份有限公司 | Banknote crown word number recognition method of currency detector |
CN106447909A (en) * | 2016-09-23 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Vertical serial number identification method and vertical serial number identification device |
Non-Patent Citations (2)
Title |
---|
刘炜: "《人民币冠字号码识别与图像鉴伪技术研究及应用》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
和小娟等: "《边界链码在字母与数字混合识别中的应用》", 《郑州大学学报(理学版)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115331235A (en) * | 2022-10-12 | 2022-11-11 | 南通东鼎彩印包装厂 | Fracture adhesion printing digital identification method |
Also Published As
Publication number | Publication date |
---|---|
CN107331030B (en) | 2019-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9811718B2 (en) | Method and a system for face verification | |
CN107240185B (en) | A kind of crown word number identification method, device, equipment and storage medium | |
CN109740606B (en) | Image identification method and device | |
US5917941A (en) | Character segmentation technique with integrated word search for handwriting recognition | |
CN111160140B (en) | Image detection method and device | |
CN110728290B (en) | Method and device for detecting security of data model | |
CN104915972A (en) | Image processing apparatus, image processing method and program | |
CN107274543B (en) | A kind of recognition methods of bank note, device, terminal device and computer storage medium | |
US10438083B1 (en) | Method and system for processing candidate strings generated by an optical character recognition process | |
CN107610322A (en) | Recognition methods, device, electronic equipment and the storage medium of bank note version | |
CN113379869B (en) | License plate image generation method and device, electronic equipment and storage medium | |
CN113449725A (en) | Object classification method, device, equipment and storage medium | |
CN108268641A (en) | Invoice information recognition methods and invoice information identification device, equipment and storage medium | |
CN105139508B (en) | A kind of method and device of detection bank note | |
JP3083562B2 (en) | Character recognition mechanism | |
CN107331030B (en) | A kind of crown word number identification method, device, equipment and storage medium | |
O***llah et al. | Comparison of different classifiers for script identification from handwritten document | |
CN107680246A (en) | Curved boundary localization method and equipment in a kind of banknote prints | |
CN111222558A (en) | Image processing method and storage medium | |
CN107369243B (en) | A kind of recognition methods of bank note, device, terminal device and computer storage medium | |
CN107958531B (en) | Paper money identification method and device and equipment | |
CN116311391A (en) | High-low precision mixed multidimensional feature fusion fingerprint retrieval method | |
KR101149843B1 (en) | Method for recognizing serial number of security paper money | |
US6859556B2 (en) | Word recognizing apparatus for dynamically generating feature amount of word and method thereof | |
CN107220981A (en) | Character segmentation method, device, equipment and storage medium |
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 |