CN105335741A - Smudged serial number classification method and system - Google Patents
Smudged serial number classification method and system Download PDFInfo
- Publication number
- CN105335741A CN105335741A CN201510713636.5A CN201510713636A CN105335741A CN 105335741 A CN105335741 A CN 105335741A CN 201510713636 A CN201510713636 A CN 201510713636A CN 105335741 A CN105335741 A CN 105335741A
- Authority
- CN
- China
- Prior art keywords
- precise region
- crown word
- word number
- character
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention discloses a smudged serial number classification method and system. The method includes the following steps that: a horizontal serial number-containing precise area and a longitudinal serial number-containing precise area in a banknote image are extracted; binarization processing is performed on the horizontal serial number-containing precise area and the longitudinal serial number-containing precise area; each character is cut from the binarized horizontal serial number-containing precise area and longitudinal serial number-containing precise area; the number of black spots of the characters of the horizontal serial number-containing precise area is compared with the number of black spots of characters at corresponding positions of the longitudinal serial number-containing precise area; and the serial numbers are classified according to comparison results. With the smudged serial number classification method and system of the invention adopted, the smudged serial numbers and normal serial numbers of banknotes can be accurately classified, and classified smudged serial number images are not recognized in a later stage. The smudged serial number classification method and system are of great significance for normal circulation of banknotes.
Description
Technical field
The present invention relates to crown word number identification field, particularly relate to a kind of method and system of dirty crown word number classification.
Background technology
Crown word number above bank note can realize often opening bank note from being issued to the record and management that reclaim the whole process of circulation, realize reviewing of circulating paper money, for economy and the analysis of social concern, the monitoring of counterfeit money and divisions of responsibility can, the distribution of Renminbi and supervision are all by important realistic meaning.By observing normal crown word number region, find that 100 yuan of 2015 editions and 1999 editions 100 yuan and 50 yuans exist two crown word number regions, the crown word number in two crown word number regions is consistent.But now in paper money number process, all the extraction for crown word number and identification, the crown word number image do not mentioned for the bank note of the old dirt of circulating on the market at present carries out the method processed, if the dirty position of bank note is just in the position of crown word number, the failure that crown word number then may be caused to extract and identify, causes the crown word number discrimination of Possum to reduce.
Summary of the invention
The invention provides a kind of method and system of dirty crown word number classification, the method and system can be classified accurately to the dirty crown word number of bank note and normal crown word number.
For realizing above-mentioned design, the present invention by the following technical solutions:
Adopt a kind of method of dirty crown word number classification on the one hand, comprising:
Extract the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number;
The precise region that the precise region of crown word number and described longitudinal direction contain crown word number is contained to described transverse direction and carries out binary conversion treatment;
Contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number;
The stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number;
According to comparative result, described crown word number is classified.
Wherein, stain number and the stain number of the relevant position character of the precise region longitudinally containing crown word number of the character of the described precise region relatively laterally containing crown word number, comprising:
Calculate the stain number of the character of the precise region laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, be designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents;
Relatively S1
iand S2
ithe absolute value of size;
Described according to comparative result, described crown word number is classified, comprising:
If | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character;
If | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
Wherein, describedly the precise region that the precise region of crown word number and described longitudinal direction contain crown word number contained to described transverse direction carry out binary conversion treatment, comprising:
The precise region that described longitudinal direction contains crown word number is zoomed to the size that the precise region that contains crown word number with described transverse direction adapts;
Binary conversion treatment is carried out to the precise region that the longitudinal direction after described transverse direction contains the precise region of crown word number and convergent-divergent contains crown word number.
Wherein, the described size precise region that described longitudinal direction contains crown word number being zoomed to the precise region that contains crown word number with described transverse direction and adapt, is specially:
Banknote image collection is highly 150DPI resolution, and when width is 200DPI resolution, described longitudinal direction is contained to the reduced height of the precise region of crown word number to 3/4 of former height, width is amplified to 4/3 of former width.
Wherein, described transverse direction after binary conversion treatment contains the precise region of crown word number and longitudinally cuts out each character respectively containing the precise region of crown word number, is specially:
Row projection is adopted to contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number.
Wherein, the precise region laterally containing crown word number in described extraction banknote image and the precise region longitudinally containing crown word number, comprising:
Intercept the region laterally containing crown word number in banknote image and the region longitudinally containing crown word number;
The region that described longitudinal direction contains crown word number is turned clockwise 90 °;
Adopt row projection and row projection to contain the region of crown word number and postrotational longitudinal direction from described transverse direction to contain the region of crown word number and extract the precise region laterally containing crown word number and the precise region longitudinally containing crown word number respectively.
Obtain the crown word number image after binaryzation, cavity is carried out to described crown word number image and fills, extract the crown word number after filling;
Have employed a kind of system of dirty crown word number classification on the other hand, comprising:
Extraction module, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number;
Binarization block, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment;
Cut module, contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number;
Comparison module, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number;
Sort module, according to comparative result, classifies to described crown word number.
Wherein, described comparison module comprises:
Computing module, calculates the stain number of the character of the precise region laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, is designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents;
First comparison module, compares S1
iand S2
ithe absolute value of size;
Described sort module comprises:
First sort module, if | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character;
Second sort module, if | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
Wherein, described binarization block comprises:
Zoom module, zooms to the size that the precise region that contains crown word number with described transverse direction adapts by the precise region that described longitudinal direction contains crown word number;
Binaryzation submodule, carries out binary conversion treatment to the precise region that the longitudinal direction after described transverse direction contains the precise region of crown word number and convergent-divergent contains crown word number.
Wherein, described extraction module comprises:
Interception module, intercepts the region laterally containing crown word number in banknote image and the region longitudinally containing crown word number;
Rotary module, turns clockwise the region that described longitudinal direction contains crown word number 90 °;
First extraction module, adopts row projection and row projection to contain the region of crown word number and postrotational longitudinal direction from described transverse direction and contains the region of crown word number and extract the precise region laterally containing crown word number and the precise region longitudinally containing crown word number respectively.
Beneficial effect of the present invention is: the present invention is by extracting the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number; The precise region that the precise region of crown word number and described longitudinal direction contain crown word number is contained to described transverse direction and carries out binary conversion treatment; Contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number; The stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number; According to comparative result, described crown word number is classified.The present invention can classify accurately to the dirty crown word number of bank note and normal crown word number, no longer identifies follow-up for the dirty crown word number image sorted out, and the normal stream for bank note is logical to have great significance.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing the embodiment of the present invention is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to the content of the embodiment of the present invention and these accompanying drawings.
Fig. 1 is the method flow diagram of the first embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Fig. 2 is the method flow diagram of the second embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Fig. 3 is the method flow diagram of the 3rd embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Fig. 4 is the method flow diagram of the 4th embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Fig. 5 is the block diagram of the system of a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Fig. 6 is another block diagram of the system of a kind of dirty crown word number classification provided in the specific embodiment of the invention.
Embodiment
The technical matters solved for making the present invention, the technical scheme of employing and the technique effect that reaches are clearly, be described in further detail below in conjunction with the technical scheme of accompanying drawing to the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those skilled in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Please refer to Fig. 1, it is the method flow diagram of the first embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, the method, comprising:
Step S101, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number.
Concrete, for Renminbi, 1999 editions 100 yuan and 50 yuans and 2015 editions 100 yuans all have two crown word number, and in two crown word number, the crown word number character of relevant position is identical, is distributed in the lower left corner and the right side boundary place in front respectively.Extract the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number: be the precise region extracting these two crown word number places in banknote image.
Step S102, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment.
Concrete, contain to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carry out binary conversion treatment, make the background of two precise regions for white, character is black.Conventional binary processing method has: fixed threshold binaryzation, adaptive threshold binaryzation, local threshold binaryzation etc.
Step S103, contains the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cuts out each character respectively containing the precise region of crown word number.
Concrete, have 10 crown word number characters in the precise region of crown word number, the precise region containing crown word number from the transverse direction after binary conversion treatment cuts out this 10 characters respectively; And cut out this 10 characters respectively from the precise region that the longitudinal direction after binary conversion treatment contains crown word number.
Step S104, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Concrete, each stain is a pixel, and the number of stain determined by the resolution of image during image acquisition.In the present embodiment, for each crown word number character, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Step S105, according to comparative result, classifies to described crown word number.
Concrete, if the stain number of the character of the precise region laterally containing crown word number is more than or equal to stain threshold value with the absolute value of the difference of the stain number of the relevant position character of the precise region longitudinally containing crown word number, then described character is dirty character; If the stain number of the character of the precise region laterally containing crown word number is less than stain threshold value with the absolute value of the difference of the stain number of the relevant position character of the precise region longitudinally containing crown word number, then described character is not for having dirty character.
In sum, the embodiment of the present invention is by extracting the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number; The precise region that the precise region of crown word number and described longitudinal direction contain crown word number is contained to described transverse direction and carries out binary conversion treatment; Contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number; The stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number; According to comparative result, described crown word number is classified.The embodiment of the present invention can be classified accurately to the dirty crown word number of bank note and normal crown word number, no longer identifies follow-up for the dirty crown word number image sorted out, and the normal stream for bank note is logical to have great significance.
Please refer to Fig. 2, it is the method flow diagram of the second embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, the method, comprising:
Step S201, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number.
Step S202, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment.
Step S203, contains the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cuts out each character respectively containing the precise region of crown word number.
Concrete, after binaryzation, according to the gray-scale value of each row in row projection and difference can locate the precise region laterally containing crown word number and the position longitudinally containing each character in the precise region of crown word number accurately.Row projection is adopted to contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number.
Step S204, calculates the stain number of the character of the precise region laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, is designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents.
Step S205, compares S1
iand S2
ithe absolute value of size.
Concrete, calculate | S1
i-S2
i| value.
Step S206, | S1
i-S2
i| be more than or equal to and be less than stain threshold value?
Step S207, described character is dirty character.
Concrete, if | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
Step S208, described character is not for having dirty character.
Concrete, if | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character.
In sum, the embodiment of the present invention make use of the consistance of horizontal crown word number and vertical crown word number, stain number in 10 characters in horizontal crown word number and vertical crown word number is compared respectively, thus whether distinguish crown word number character be accurately dirty character, contrast number of times is few, and the efficiency of dirty crown word number classification is high.
Please refer to Fig. 3, it is the method flow diagram of the 3rd embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, the method, comprising:
Step S301, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number.
Step S302, zooms to the size that the precise region that contains crown word number with described transverse direction adapts by the precise region that described longitudinal direction contains crown word number.
Concrete, need the precise region that described longitudinal direction contains crown word number to adjust to contain the in the same size of the precise region of crown word number with described transverse direction.The precise region that described longitudinal direction contains crown word number can be zoomed to the size that the precise region that contains crown word number with described transverse direction adapts, also the precise region that described transverse direction contains crown word number can be zoomed to the size that the precise region that contains crown word number with described longitudinal direction adapts.
In the present embodiment, the precise region that described longitudinal direction contains crown word number is zoomed to the size that the precise region that contains crown word number with described transverse direction adapts.Preferably, banknote image collection is highly 150DPI resolution, and when width is 200DPI resolution, described longitudinal direction is contained to the reduced height of the precise region of crown word number to 3/4 of former height, width is amplified to 4/3 of former width.
Step S303, carries out binary conversion treatment to the precise region that the longitudinal direction after described transverse direction contains the precise region of crown word number and convergent-divergent contains crown word number.
Step S304, contains the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cuts out each character respectively containing the precise region of crown word number.
Step S305, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Step S306, according to comparative result, classifies to described crown word number.
In sum, the precise region that described longitudinal direction contains crown word number is adjusted to and is contained the in the same size of the precise region of crown word number with described transverse direction by the embodiment of the present invention, the absolute value of the number difference of each character stain and threshold value is only utilized to compare, contrast number of times is few, shorten the time, improve the efficiency judging that dirty crown word number is classified.
Please refer to Fig. 4, it is the method flow diagram of the 4th embodiment of the method for a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, the method, comprising:
Step S401, intercepts the region laterally containing crown word number in banknote image and the region longitudinally containing crown word number.
Concrete, according to the Position Approximate that crown word number horizontal in banknote image and longitudinal crown word number exist, intercept the region laterally containing crown word number in banknote image and the region longitudinally containing crown word number.
Step S402, turns clockwise the region that described longitudinal direction contains crown word number 90 °.
Concrete, the region that described longitudinal direction contains crown word number is turned clockwise 90 °, to make two regions containing crown word number all be in horizontal, make corresponding character in two crown word number regions be in position identical in whole crown word number character.
Step S403, adopts row projection and row projection to contain the region of crown word number and postrotational longitudinal direction from described transverse direction and contains the region of crown word number and extract the precise region laterally containing crown word number and the precise region longitudinally containing crown word number respectively.
Concrete, contain in the region of crown word number in the region laterally containing crown word number and postrotational longitudinal direction, there is the gray-scale value of crown word number character position obviously different from the gray-scale value of background positions, adopt the projection of the row of gray-scale value and row projection can locate the precise region laterally containing crown word number and the precise region longitudinally containing crown word number accurately, thus can realize containing the region of crown word number and postrotational longitudinal direction from described transverse direction and contain the region of crown word number and extract the precise region laterally containing crown word number and the precise region longitudinally containing crown word number respectively.
Step S404, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment.
Concrete, the precise region that the precise region of crown word number and described longitudinal direction contain crown word number is contained to described transverse direction and carries out binary conversion treatment, comprising: the precise region that described longitudinal direction contains crown word number is zoomed to the size that the precise region that contains crown word number with described transverse direction adapts; Binary conversion treatment is carried out with the precise region that the longitudinal direction after described transverse direction being contained to the precise region of crown word number and convergent-divergent contains crown word number.
Preferably, banknote image collection is highly 150DPI resolution, and when width is 200DPI resolution, described longitudinal direction is contained to the reduced height of the precise region of crown word number to 3/4 of former height, width is amplified to 4/3 of former width.
Step S405, contains the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cuts out each character respectively containing the precise region of crown word number.
Concrete, adopt row projection contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number.
Step S406, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Concrete, each stain is a pixel, and the number of stain determined by the resolution of image during image acquisition.In the present embodiment, for each crown word number character, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
In the present embodiment, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, comprise: calculate the stain number of the character of the precise region laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, be designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents; With compare S1
iand S2
ithe absolute value of size.
Step S407, according to comparative result, classifies to described crown word number.
Concrete, if the stain number of the character of the precise region laterally containing crown word number is more than or equal to stain threshold value with the difference of the absolute value of the stain number of the relevant position character of the precise region longitudinally containing crown word number, then described character is dirty character; If the stain number of the character of the precise region laterally containing crown word number is less than stain threshold value with the difference of the absolute value of the stain number of the relevant position character of the precise region longitudinally containing crown word number, then described character is not for having dirty character.
In the present embodiment, if | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character; If | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
In sum, the embodiment of the present invention utilizes the consistance of horizontal crown word number and vertical crown word number, have employed each absolute value of character stain number difference and the method for certain threshold comparison, determines whether crown word number is dirty crown word number.The embodiment of the present invention only utilizes the absolute value of the number difference of each character stain and threshold value to compare, and contrast number of times is few, shortens the time.Improve the efficiency judging that dirty crown word number is classified.
It is below the embodiment of the system of a kind of dirty crown word number classification of this programme, a kind of embodiment of system of dirty crown word number classification realizes based on a kind of embodiment of method of dirty crown word number classification, description not most in a kind of embodiment of system of dirty crown word number classification, please refer to a kind of embodiment of method of dirty crown word number classification.
Please refer to Fig. 5, it is the block diagram of the system of a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, this system, comprising:
Extraction module 510, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number.
Binarization block 520, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment.
Cut module 530, contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number.
Comparison module 540, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Sort module 550, according to comparative result, classifies to described crown word number.
In sum, above-mentioned each module cooperative work, extraction module 510 extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number; Binarization block 520 contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment; Cut module 530 contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number; The stain number of the character of the precise region of comparison module 540 relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number; Sort module 550, according to comparative result, is classified to described crown word number.The embodiment of the present invention can be classified accurately to the dirty crown word number of bank note and normal crown word number, no longer identifies follow-up for the dirty crown word number image sorted out, and the normal stream for bank note is logical to have great significance.
Please refer to Fig. 6, it is another block diagram of the system of a kind of dirty crown word number classification provided in the specific embodiment of the invention.As shown in the figure, this system, comprising:
Extraction module 510, extracts the precise region laterally containing crown word number in banknote image and the precise region longitudinally containing crown word number.
Concrete, extraction module 510 comprises: interception module 511, rotary module 512 and the first extraction module 513.
Interception module 511, intercepts the region laterally containing crown word number in banknote image and the region longitudinally containing crown word number.
Rotary module 512, turns clockwise the region that described longitudinal direction contains crown word number 90 °.
First extraction module 513, adopts row projection and row projection to contain the region of crown word number and postrotational longitudinal direction from described transverse direction and contains the region of crown word number and extract the precise region laterally containing crown word number and the precise region longitudinally containing crown word number respectively.
Binarization block 520, contains to described transverse direction the precise region that the precise region of crown word number and described longitudinal direction contain crown word number and carries out binary conversion treatment.
Concrete, binarization block 520 comprises Zoom module 521 and binaryzation submodule 522.
Zoom module 521, zooms to the size that the precise region that contains crown word number with described transverse direction adapts by the precise region that described longitudinal direction contains crown word number.
Binaryzation submodule 522, carries out binary conversion treatment to the precise region that the longitudinal direction after described transverse direction contains the precise region of crown word number and convergent-divergent contains crown word number.
Cut module 530, contain the precise region of crown word number from the transverse direction after binary conversion treatment and longitudinally cut out each character respectively containing the precise region of crown word number.
Comparison module 540, the stain number of the character of the precise region relatively laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number.
Concrete, comparison module 540 comprises computing module 541 and the first comparison module 542.
Computing module 541, calculates the stain number of the character of the precise region laterally containing crown word number and the stain number of the relevant position character of the precise region longitudinally containing crown word number, is designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents.
First comparison module 542, compares S1
iand S2
ithe absolute value of size.
Sort module 550, according to comparative result, classifies to described crown word number.
Concrete, sort module 550 comprises the first sort module 551 and the second sort module 552.
First sort module 551, if | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character.
Second sort module 552, if | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
In sum, above-mentioned each module cooperative work, utilizes the consistance of horizontal crown word number and vertical crown word number, have employed each absolute value of character stain number difference and the method for certain threshold comparison, determines whether crown word number is dirty crown word number.The embodiment of the present invention only utilizes the absolute value of the number difference of each character stain and threshold value to compare, and contrast number of times is few, shortens the time.Improve the efficiency judging that dirty crown word number is classified.
Below know-why of the present invention is described in conjunction with specific embodiments.These describe just in order to explain principle of the present invention, and can not be interpreted as limiting the scope of the invention by any way.Based on explanation herein, those skilled in the art does not need to pay performing creative labour can associate other embodiment of the present invention, and these modes all will fall within protection scope of the present invention.
Claims (10)
1. a method for dirty crown word number classification, is characterized in that, comprising:
Extract the horizontal precise region containing crown word number in banknote image and longitudinal precise region;
Binary conversion treatment is carried out to described horizontal precise region and described longitudinal precise region;
Each character is cut out respectively from the horizontal precise region after binary conversion treatment and longitudinal precise region;
The stain number of the stain number of the character of more horizontal precise region and the relevant position character of longitudinal precise region;
According to comparative result, described crown word number is classified.
2. method according to claim 1, is characterized in that, the stain number of the stain number of the character of described more horizontal precise region and the relevant position character of longitudinal precise region, comprising:
Calculate the stain number of the stain number of the character of horizontal precise region and the relevant position character of longitudinal precise region, be designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents;
Relatively S1
iand S2
ithe absolute value of size;
Described according to comparative result, described crown word number is classified, comprising:
If | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character;
If | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
3. method according to claim 1, is characterized in that, describedly carries out binary conversion treatment to described horizontal precise region and described longitudinal precise region, comprising:
Described longitudinal precise region is zoomed to the size adapted with described horizontal precise region;
Binary conversion treatment is carried out to the longitudinal precise region after described horizontal precise region and convergent-divergent.
4. method according to claim 3, is characterized in that, describedly described longitudinal precise region is zoomed to the size adapted with described horizontal precise region, is specially:
Banknote image collection is highly 150DPI resolution, and when width is 200DPI resolution, to the reduced height of described longitudinal precise region to 3/4 of former height, width is amplified to 4/3 of former width.
5. method according to claim 1, is characterized in that, cuts out each character respectively, be specially described horizontal precise region after binary conversion treatment and longitudinal precise region:
Row projection is adopted to cut out each character respectively from the horizontal precise region after binary conversion treatment and longitudinal precise region.
6. the method according to claim 1-5 any one, is characterized in that, the horizontal precise region containing crown word number in described extraction banknote image and longitudinal precise region, comprising:
Intercept the transverse area containing crown word number in banknote image and longitudinal region;
Described longitudinal region is turned clockwise 90 °;
Row projection and row projection is adopted to extract respectively containing the horizontal precise region of crown word number and longitudinal precise region from described transverse area and postrotational longitudinal region.
7. a system for dirty crown word number classification, is characterized in that, comprising:
Extraction module, extracts the horizontal precise region containing crown word number in banknote image and longitudinal precise region;
Binarization block, carries out binary conversion treatment to described horizontal precise region and described precise region;
Cut module, from the horizontal precise region after binary conversion treatment and longitudinal precise region, cut out each character respectively;
Comparison module, the stain number of the stain number of the character of more horizontal precise region and the relevant position character of longitudinal precise region;
Sort module, according to comparative result, classifies to described crown word number.
8. system according to claim 7, is characterized in that, described comparison module comprises:
Computing module, calculates the stain number of the stain number of the character of horizontal precise region and the relevant position character of longitudinal precise region, is designated as S1 respectively
i, S2
i, wherein, i=1,2 ..., which character 10, i represents; And
First comparison module, compares S1
iand S2
ithe absolute value of size;
Described sort module comprises:
First sort module, if | S1
i-S2
i| be less than stain threshold value, then described character is not for having dirty character; And
Second sort module, if | S1
i-S2
i| be more than or equal to stain threshold value, then described character is dirty character.
9. system according to claim 7, is characterized in that, described binarization block comprises:
Zoom module, zooms to the size adapted with described horizontal precise region by described longitudinal precise region;
Binaryzation submodule, carries out binary conversion treatment to the longitudinal precise region after described horizontal precise region and convergent-divergent.
10. system according to claim 7, is characterized in that, described extraction module comprises:
Interception module, intercepts the transverse area containing crown word number in banknote image and longitudinal region;
Rotary module, turns clockwise described longitudinal region 90 °;
First extraction module, adopts row projection and row projection to extract respectively containing the horizontal precise region of crown word number and longitudinal precise region from described transverse area and postrotational longitudinal region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510713636.5A CN105335741A (en) | 2015-10-28 | 2015-10-28 | Smudged serial number classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510713636.5A CN105335741A (en) | 2015-10-28 | 2015-10-28 | Smudged serial number classification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105335741A true CN105335741A (en) | 2016-02-17 |
Family
ID=55286257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510713636.5A Pending CN105335741A (en) | 2015-10-28 | 2015-10-28 | Smudged serial number classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105335741A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204894A (en) * | 2016-06-27 | 2016-12-07 | 深圳怡化电脑股份有限公司 | A kind of medium classification method and device |
| CN106780953A (en) * | 2017-01-13 | 2017-05-31 | 广州广电运通金融电子股份有限公司 | A kind of paper money discrimination method and system based on double comb font size |
| CN106855948A (en) * | 2016-12-13 | 2017-06-16 | 深圳市海云天科技股份有限公司 | It is a kind of to detect that answering card scanning produces the method and device of secondary pollution |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
| CN107067000A (en) * | 2017-03-31 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note degree and device |
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
| CN108960222A (en) * | 2017-05-26 | 2018-12-07 | 深圳怡化电脑股份有限公司 | Image binaryzation method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060104498A1 (en) * | 2004-11-16 | 2006-05-18 | Kruppa Robert W | Apparatus, system, and method for fraud detection using multiple scan technologies |
| CN101506851A (en) * | 2006-08-31 | 2009-08-12 | 光荣株式会社 | Paper sheet identification device and paper sheet identification method |
| CN104574636A (en) * | 2015-01-16 | 2015-04-29 | 北京印钞有限公司 | Bill mandarin-duck-number recognition and check system |
-
2015
- 2015-10-28 CN CN201510713636.5A patent/CN105335741A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060104498A1 (en) * | 2004-11-16 | 2006-05-18 | Kruppa Robert W | Apparatus, system, and method for fraud detection using multiple scan technologies |
| CN101506851A (en) * | 2006-08-31 | 2009-08-12 | 光荣株式会社 | Paper sheet identification device and paper sheet identification method |
| CN104574636A (en) * | 2015-01-16 | 2015-04-29 | 北京印钞有限公司 | Bill mandarin-duck-number recognition and check system |
Non-Patent Citations (2)
| Title |
|---|
| 关宇东 等: "基于图像处理的变造币识别技术", 《仪器仪表学报》 * |
| 张君: "车牌数字特征提取与残缺数字识别关系的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204894A (en) * | 2016-06-27 | 2016-12-07 | 深圳怡化电脑股份有限公司 | A kind of medium classification method and device |
| CN106855948A (en) * | 2016-12-13 | 2017-06-16 | 深圳市海云天科技股份有限公司 | It is a kind of to detect that answering card scanning produces the method and device of secondary pollution |
| CN106780953A (en) * | 2017-01-13 | 2017-05-31 | 广州广电运通金融电子股份有限公司 | A kind of paper money discrimination method and system based on double comb font size |
| WO2018130119A1 (en) * | 2017-01-13 | 2018-07-19 | 广州广电运通金融电子股份有限公司 | Double prefix number-based paper money authenticity identification method and system |
| CN107067000A (en) * | 2017-03-31 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note degree and device |
| CN107067000B (en) * | 2017-03-31 | 2019-09-20 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note degree and device |
| CN108960222A (en) * | 2017-05-26 | 2018-12-07 | 深圳怡化电脑股份有限公司 | Image binaryzation method, device, equipment and storage medium |
| CN108960222B (en) * | 2017-05-26 | 2022-01-28 | 深圳怡化电脑股份有限公司 | Image binarization method, device, equipment and storage medium |
| CN107085882A (en) * | 2017-06-02 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of method and device for determining counterfeit money |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
| CN107025716B (en) * | 2017-06-05 | 2019-12-10 | 深圳怡化电脑股份有限公司 | Method and device for detecting contamination of paper money crown word number |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105335741A (en) | Smudged serial number classification method and system | |
| CN103258201B (en) | A kind of form lines extracting method of amalgamation of global and local message | |
| CN101923741B (en) | Paper currency number identification method based on currency detector | |
| US20190188528A1 (en) | Text detection method and apparatus, and storage medium | |
| CN111382704B (en) | Vehicle line pressing violation judging method and device based on deep learning and storage medium | |
| Yu et al. | An approach to Korean license plate recognition based on vertical edge matching | |
| CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
| CN105225335A (en) | A kind of stained recognition methods of paper money number and system | |
| CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
| CN100498820C (en) | Automatic recognising method and automatic recognising recording system for number of paper money | |
| CN104298982A (en) | Text recognition method and device | |
| CN104732220A (en) | Specific color human body detection method oriented to surveillance videos | |
| CN112906695B (en) | Form recognition method adapting to multi-class OCR recognition interface and related equipment | |
| CN103606220A (en) | Check printed number recognition system and check printed number recognition method based on white light image and infrared image | |
| WO2023279966A1 (en) | Multi-lane-line detection method and apparatus, and detection device | |
| CN112818952B (en) | Coal rock boundary recognition method and device and electronic equipment | |
| CN114387591A (en) | License plate recognition method, system, equipment and storage medium | |
| CN106485708A (en) | A kind of round log method of counting based on image recognition | |
| CN110378351B (en) | Seal identification method and device | |
| Louloudis et al. | Text line detection in unconstrained handwritten documents using a block-based Hough transform approach | |
| CN108269349B (en) | Paper money processing method, device, equipment and storage medium | |
| CN105336035B (en) | A kind of method and system of dirty crown word number image classification | |
| CN110598575B (en) | Form layout analysis and extraction method and related device | |
| CN112530079B (en) | Method, device, terminal equipment and storage medium for detecting bill factors | |
| CN106683257A (en) | Serial number location method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160217 |