CN102693431A - Method and device for identifying type of white number plate - Google Patents
Method and device for identifying type of white number plate Download PDFInfo
- Publication number
- CN102693431A CN102693431A CN2012101777884A CN201210177788A CN102693431A CN 102693431 A CN102693431 A CN 102693431A CN 2012101777884 A CN2012101777884 A CN 2012101777884A CN 201210177788 A CN201210177788 A CN 201210177788A CN 102693431 A CN102693431 A CN 102693431A
- Authority
- CN
- China
- Prior art keywords
- white
- license plate
- plate area
- car plate
- distance
- 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
Images
Abstract
The invention discloses a method and a device for identifying the type of a white number plate. The problems of low precision and accuracy during the identification of the type of the white number plate in the prior art are solved. The method for identifying the type of the white number plate comprises the following steps of: performing character segmentation on a preprocessed white number plate area, identifying a character sequence in line with each white number plate type in the white number plate according to a distance between every two segmented characters, and determining the type of the white number plate according to a matching distance between a template corresponding to each white number plate type and the character sequence. The number plate sequence in line with each type is determined according to the distances between the characters, and then the type of the number plate is finally determined according to the distance between the template corresponding to the number plate type and the character sequence, so that the accuracy and precision of an identification result can be ensured under twice identification condition.
Description
Technical field
The present invention relates to the computer image processing technology field, relate in particular to a kind of recognition methods and device of white car plate type.
Background technology
Along with The development in society and economy, the quantity of vehicle constantly increases, and therefore becomes inevitable through computer information, intelligentized project management vehicle.Car plate is identified in the important role of intelligent transportation field performer in the prior art, and it has widely in traffic flow monitoring, the charge of highway bayonet socket, red light violation vehicle monitoring and community's automatic fare collection system uses.
But existing vehicle license type commonly used is many, is divided into wrongly written or mispronounced character car plate of the blue end from background color, yellow end surplus car plate, black matrix wrongly written or mispronounced character car plate and white gravoply, with black engraved characters car plate; Can be divided into again on the type normal blue board, common individual layer yellow card, double-deck yellow card, coach with board, list temporarily, black licence plate, white alert board, white army board and white People's Armed Police's car plate etc.Promptly to the car plate adularescent of white background surplus alert board, white army board and white People's Armed Police's car plate.
The car plate of white gravoply, with black engraved characters is when discerning in the prior art; The general method that adopts comprises: utilize the color of car plate to orient white car plate; Three kinds of corresponding according to the white gravoply, with black engraved characters car plate afterwards car plate types; White car plate to orienting carries out Character segmentation, at last through identification, selects the maximum last recognition result of conduct of degree of confidence.In the identifying of above-mentioned car plate type, only confirm the car plate type according to degree of confidence, the standard of judgement is more single, can not effectively distinguish the car plate type, and therefore the recognition methods precision of white car plate type of the prior art is low, poor accuracy.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of recognition methods and device of white car plate type, and is low in order to solve prior art precision when the type of white car plate is discerned, the problem of poor accuracy.
The present invention provides a kind of recognition methods of white car plate type, and said method comprises:
In the image of input, carry out the license plate area location, in the license plate area of location, identify white license plate area;
White license plate area to identifying carries out pre-service, and pretreated white license plate area is carried out Character segmentation;
According to the distance between per two characters after the Character segmentation, identify the character string that satisfies every kind of white car plate type in this white car plate;
With each character string, mate with the template of the corresponding car plate type of this character string, confirm the type of each white car plate based on average matching distance.
The present invention provides a kind of recognition device of white car plate type, and said device comprises:
Identification module is used for carrying out the license plate area location at the image of input, in the license plate area of location, identifies white license plate area;
Module is cut apart in pre-service, is used for the white license plate area that identifies is carried out pre-service, and pretreated white license plate area is carried out Character segmentation;
Character string is selected module, is used for identifying the character string that satisfies every kind of white car plate type in this white car plate according to the distance between per two characters after the Character segmentation;
Matching module is used for each character string, matees with the template of the corresponding car plate type of this character string, confirms the type of each white car plate according to average matching distance.
The invention provides a kind of recognition methods and device of white car plate type; This method is when carrying out white car plate type identification; Pretreated white license plate area has been carried out Character segmentation, and the distance according to cutting apart between per two characters in back identifies the character string that satisfies every kind of white car plate type in this white car plate; According to the template corresponding and the matching distance of this character string, confirm the car plate type of this white car plate with every kind of white car plate type.Because in the present invention according to the distance between the character string; Confirm to satisfy every type car plate sequence; Afterwards again according to the final type of definite this car plate of the distance of the corresponding template of the type car plate and this character string; Therefore under the situation of twice identification, can guarantee the accuracy and the degree of accuracy of recognition result.
Description of drawings
Accompanying drawing described herein is used to provide further understanding of the present invention, constitutes a part of the present invention, and illustrative examples of the present invention and explanation thereof are used to explain the present invention, does not constitute improper qualification of the present invention.In the accompanying drawings:
Fig. 1 is an identifying synoptic diagram that should white car plate type provided by the invention;
Fig. 2 is the process synoptic diagram that this white license plate area is carried out rectification provided by the invention;
Fig. 3 removes the process synoptic diagram that up-and-down boundary is handled for provided by the invention to this white license plate area;
Fig. 4 is the process synoptic diagram through the white car plate type of distance identification provided by the invention;
Fig. 5 is a detailed identifying synoptic diagram that should white car plate type provided by the invention;
Fig. 6 is a structural representation that should white car plate type identification device provided by the invention.
Embodiment
The embodiment of the invention provides a kind of recognition methods and device of white car plate type in order to improve accuracy of identification and the accuracy to the type of white car plate.
Below in conjunction with Figure of description, the present invention is elaborated.
Fig. 1 is an identifying synoptic diagram that should white car plate type provided by the invention, and this identifying may further comprise the steps:
S101: in the image of input, carry out the license plate area location, in the license plate area of location, identify white license plate area.
Because the recognition methods of this white car plate type; Can be applied in a plurality of systems such as traffic flow monitoring, the charge of highway bayonet socket, the automatic charge of red light violation vehicle monitoring and community, concrete discerns white car plate type through white car plate type identification device in the present invention.
After the image of the vehicle that will comprise license board information is input in this device; This device carries out the license plate area location in the image of input; Concrete can adopt several different methods of the prior art when carrying out the license plate area location, for example can adopt edge detection method or machine learning scheduling algorithm in the image of input, to carry out the car plate location, and concrete for example can carry out the sobel rim detection; According to the result who detects, the zone that marginal density is bigger is as the car plate region.
Owing in the image of input, carry out the license plate area location, discern white license plate area, be the common method of this area, just this content is not given unnecessary details in the present invention.
S102: the white license plate area to identifying carries out pre-service, and pretreated white license plate area is carried out Character segmentation.
Concrete when the white license plate area that identifies is carried out pre-service, can adopt multiple preprocess method, for example can directly carry out binary conversion treatment to license plate area.
In order further to improve the accuracy of white car plate type identification; In the present invention the white license plate area that identifies being carried out pre-service comprises: at least a preprocess method below the employing carries out pre-service to the white license plate area that identifies, rectification preprocess method and removal up-and-down boundary preprocess method.
The rectification preprocess method should be used in combination with removal up-and-down boundary preprocess method, and carries out horizontal tilt earlier and proofread and correct, and then removes BORDER PROCESSING.Because pretreated process has been carried out rectification to white license plate area, and has removed the interference to the up-and-down boundary in the car plate type identification, therefore can in this pretreated car plate white portion, carry out Character segmentation.Concrete when carrying out Character segmentation, promptly in the zone at white car plate place, confirm the border of each character, thereby confirm the position of each character.
S103:, identify the character string that satisfies every kind of white car plate type based on the distance between per two characters after the Character segmentation.
After white license plate area carried out Character segmentation, the position at each character place can be confirmed,, the distance between any two adjacent characters can be confirmed based on the position at each character place.In the present invention since the distance between any two characters can confirm, and every type white car plate, there is certain relation in the distance between the one of which fixed number purpose character string; For example for the alert board of white, between its 7 character strings, the distance between preceding two characters is greater than the distance between other any two characters; And for white army board; Between its 7 character strings, the distance between second character and the 3rd character is greater than the distance between other any two characters, and for white People's Armed Police's board; In its 5 character strings, the distance between any two characters is basic identical.
Therefore based on the distance feature between the character of above-mentioned every type white car plate, can be directed against each white license plate area, identify the character string that satisfies every kind of white car plate type.
S104: with each character string, mate, confirm the type of each white car plate according to average matching distance with the template of the corresponding car plate type of this character string.
Owing to be from each character that white license plate area comprises in the present invention; The character string of every kind of white car plate type is satisfied in selection; And to the character that comprises in the same white license plate area, its different character string possibly satisfy different white car plate types.Therefore when carrying out follow-up identification; To the character that comprises in the same white license plate area, the white car plate type that its different character string satisfies is selected the template corresponding with the type; This template and this character string are mated, confirm the type of each white car plate according to matching distance.
For example; The character that comprises for a certain white license plate area; Its 3 character strings are respectively first character string, second character string and three-character doctrine sequence, and wherein first character string is to satisfy the character string of white army board, and second character string is for satisfying the character string of the alert board of white; The three-character doctrine sequence is to satisfy the character string of white People's Armed Police's board; Then adopt the zone at first corresponding template of white army board and first character string place to mate, adopt the zone at second corresponding template of the alert board of white and second character string place to mate, adopt the zone at the 3rd corresponding template of white People's Armed Police's board and three-character doctrine sequence place to mate; When the regional matching distance at second template and second character string place the most in short-term, confirm the white car plate be that white is warned board.
The present invention is when carrying out white car plate type identification; Pretreated white license plate area has been carried out Character segmentation; According to the distance of cutting apart between per two characters in back; Identify the character string that satisfies every kind of white car plate type in this white car plate,, confirm the car plate type of this white car plate according to the template corresponding and the matching distance of this character string with every kind of white car plate type.Because in the present invention according to the distance between the character string; Confirm to satisfy every type car plate sequence; Afterwards again according to the final type of definite this car plate of the distance of the corresponding template of the type car plate and this character string; Therefore under the situation of twice identification, can guarantee the accuracy and the degree of accuracy of recognition result.
Through concrete embodiment, car plate type identification process of the present invention is elaborated below.
When in the image of input, be generally gray level image in the present invention, carry out license plate area location after, can confirm the zone at car plate place in this image, and through corresponding method, with the white car plate identification processing in these car plates.
To the zone at each white car plate place of identifying, pre-service is carried out in this zone, concrete preprocessing process comprises rectification and/or removes up-and-down boundary.When this preprocessing process comprises rectification and removes up-and-down boundary, the better effects if of identification.
Fig. 2 carries out the process synoptic diagram of rectification for provided by the invention to this white license plate area, and this process may further comprise the steps:
S201: adopt corresponding method to carry out binary conversion treatment to the said white license plate area that identifies.
S202: according to the saltus step of pixel value in the white license plate area after the binary conversion treatment that identifies, the position assignment of the pixel that white pixel point is corresponding during with this saltus step in the horizontal edge hum pattern is 1, and the position assignment of other pixels is 0.
S203:,, confirm that in the angular range of setting every row comprises the number of white pixel point in the horizontal direction to postrotational each angle with the step-length rotation horizontal edge hum pattern of setting.
S204: to postrotational each angle, select the more setting line number of number of white pixel point, add up this setting line number white pixel point number and.
S205: according to the number of white pixel point and the corresponding anglec of rotation of maximal value, confirm the RA of this white license plate area this white license plate area to be carried out rectification.
Concrete when this white license plate area is carried out rectification, carry out corresponding binary conversion treatment to this white license plate area, for example can adopt otsu binaryzation algorithm.After the binary conversion treatment, character is a black, and background is a white.For identify after this binary conversion treatment should the white license plate area in the state of each pixel, adopted the horizontal edge hum pattern in the present invention.
In a certain order; Search for each pixel in the white license plate area after this binary conversion treatment; When the pixel value of this pixel and the next pixel that is adjacent that searches was identical, the position assignment with the corresponding pixel of this pixel in this horizontal edge hum pattern was 0; When the pixel value of this pixel and the next pixel that is adjacent that searches not simultaneously; Be that the pixel value of pixel is when saltus step occurring; The pixel value that is pixel is 1 by 0 saltus step, is 0 o'clock by 1 saltus step perhaps, in this horizontal edge hum pattern; The pixel position assignment corresponding with this white pixel point position is 1, and the position assignment of pixel that will be corresponding with the black pixel point position is 0.Through above-mentioned search, finally confirm the assignment of each pixel in the horizontal edge hum pattern to each pixel in the white license plate area of binaryzation.
To the final horizontal edge hum pattern of confirming; Pixel with the upper left corner of this horizontal edge hum pattern is the center of circle; And definite transverse axis, the step-length of setting in the present invention can be 1 degree, is this horizontal edge hum pattern of step-length rotation with 1 degree promptly; The rotation back is in the scope of positive and negative 20 degree of transverse axis; Confirm every row projection value in the horizontal direction in the horizontal edge hum pattern, every capable pixel value is 1 pixel in promptly definite this horizontal edge hum pattern, the number in the scope that positive and negative 20 of this transverse axis is spent.
Behind each number of degrees of rotation; Every row projection value in the horizontal direction in the horizontal edge hum pattern confirms that promptly the number of the white pixel point that every row comprises in the horizontal edge hum pattern, the selection white pixel more n that counts out is capable in this angular range; Preferably; This n value is 4 in the present invention, promptly behind these number of degrees of rotation, selects 4 maximum row of projection value.To this angle, add up this 4 row projection value in the horizontal direction with, the number of promptly selecting these white pixel points of in this angular range, comprising of 4 row with.
Based on the rotation each angle, projection value bigger 4 the row, the number of the white pixel point that in this angular range, comprises and, confirm this number and maximum.When confirmed this number and maximal value after, the corresponding angle of this maximal value also can be confirmed, can carry out rectification to this white license plate area according to this angle.Concrete when this white license plate area is carried out rectification, when this angle is A, utilizes bilinear interpolation to carry out horizontal tilt and correct.
In the present invention in order to improve the accuracy of white car plate type identification, after the white license plate area that obtains after to the location carries out rectification, the processing that can remove up-and-down boundary again to the white license plate area behind this rectification.
Fig. 3 removes the process synoptic diagram that up-and-down boundary is handled for provided by the invention to this white license plate area, and this process may further comprise the steps:
S301: the white license plate area to behind the said rectification carries out binary conversion treatment.
S302: in the white license plate area after binary conversion treatment, discern the transition times of every capable pixel value, and confirm the longest white line length and the longest black line length that every row comprises.
S303:,, confirm the upper and lower border of this white license plate area with the respective distances threshold value of setting according in said transition times, the longest white line length and the longest black line length at least one.
Concrete when this white license plate area being removed up-and-down boundary and handle, at first carrying out the white license plate area of rectification, adopting otsu binaryzation algorithm, this white license plate area is being carried out binary conversion treatment.After this white license plate area carried out binary conversion treatment, begin, search for each row respectively up and down from the middle line position of this white license plate area.
Whenever search delegation, this row carried out following treatment step:
Discern the hop value of this row, promptly the pixel value of two adjacent pixels points becomes 0 by 1 in this row, and becomes 1 number of times by 0, with the hop value SumLineJump of this number of times as this row.In addition; When this is advanced line search; Also to identify every the black line comprising in this row and the length of white line; Promptly identify the number of the pixel that every black line and white line comprise, and therefrom determine the length L ineWhiteLength of the longest white line that this row comprises and the length L ineBlackLength of long black line.
Because in the identifying of car plate type; The situation that the character adhesion may occur, error will occur this moment when carrying out the interpretation of white line length, in the present invention in order further to improve the accuracy of white car plate type identification; When the white line of identification in the white license plate area; Need judge at first whether this white line is real white line, because possibly be the white line that adhesion forms between two characters, rather than the white line of real character representative; When being judged as real white line, this white line is joined in the selection set of the longest white line length.
Concrete when judging whether to real white line, at first confirm to constitute in this row the scope of this white line, promptly in this row initial pixel to the scope that stops pixel.In this row constitutes the scope of this white line; The pixel corresponding from the starting point of this white line begins, and judges adjacently with this pixel, and whether the two capable pixels up and down that are arranged in same row exist black pixel point; When having a black pixel point; The identification parameter iSumBlack that is initialized as 0 is added 1, when detecting one other pixel point, this identification parameter is added 1 more also for black pixel point; Afterwards; To second pixel in this white line; Judge adjacent with this pixel, be arranged in same row up and down two the row pixels whether have black pixel point, this identification parameter is added 1 again; Said process is carried out in circulation, up to each pixel in this white line has all been carried out above-mentioned judgement.
According to the numerical value of this identification parameter after the judgement completion, the length iWhiteLineLen of this white line, and the first proportion threshold value α that is provided with; Confirm whether this white line is real white line, specifically when judging, judge whether long-pending greater than this first proportion threshold value α and this white line length of this parameter; Promptly judge whether iSumBlack>α * iWhiteLineLen; When this identification parameter during greater than the first proportion threshold value α and this white line length iWhiteLineLen long-pending, confirm that this white line is real white line, this white line is joined in the selection set of the longest white line length; Otherwise; Confirm as interference, do not handle, wherein the general value in 0.5 to 0.8 scope of the first proportion threshold value α as white line.
Perhaps; When whether every the white line that identifies in judgement is real white line, also can confirm, concrete be the length of judging this white line amassing whether greater than the second proportion threshold value β and this car plate width W according to the length iWhiteLineLen of this white line, the second proportion threshold value β of setting and the width W of car plate; Promptly judge whether iWhiteLineLen>β * W; As the length iWhiteLineLen of white line during greater than the second proportion threshold value β and this car plate width W long-pending, confirm that this white line is real white line, this white line is joined in the selection set of the longest white line length; Otherwise; Confirm as interference, do not handle, wherein the general value in 0.3 to 0.5 scope of the second proportion threshold value β as white line.
As the hop value SumLineJump that has confirmed every row; And behind the longest black line length L ineBlackLength and the longest white line length L ineWhiteLength of every row; Can judge whether this row is the border; Specifically when judging: whether the hop value SumLineJump that can judge this row is less than the saltus step threshold value Thr1 that sets; Judge whether that promptly < Thr1 as the hop value SumLineJump of this row during less than the saltus step threshold value Thr1 that is provided with, thinks behavior coboundary or lower boundary to SumLineJump;
Perhaps; Whether the longest black line length L ineBlackLength that also can judge this row is greater than the black line length threshold Thr2 that is provided with; Promptly judge whether LineBlackLength>Thr2; As the longest black line length L ineBlackLength of this row during, think behavior coboundary or lower boundary greater than the black line length threshold Thr2 that is provided with;
Perhaps, whether the longest white line length L ineWhiteLength that also can judge this row greater than the white line length threshold Thr3 that is provided with, wherein the value of Thr1, Thr2 and Thr3 1/4th of the board width of generally picking up the car.Promptly judge whether LineWhiteLength>Thr3, as the longest white line length L ineWhiteLength of this row during greater than the white line length threshold Thr3 that is provided with, think behavior coboundary or lower boundary.
After having confirmed the coboundary and lower boundary of white license plate area, remove in the zone that can surpass upper and lower border, thus minimizing when follow-up white car plate type identification, borderline region is to the interference of identifying.
After white license plate area carried out pre-service, in this white license plate area, promptly comprise character zone and background area, can in this white license plate area, carry out having cut apart of character.Concrete when in this white license plate area, carrying out Character segmentation, should pretreated white license plate area carry out binary conversion treatment after, carry out inverse again and blow, make that character is partly for white in this white license plate area, background parts is a black.
In the white license plate area after this binaryzation and inverse are handled, carry out the projection of vertical direction and calculate, promptly calculate the number sum of every row white pixel point, concrete when calculating, can be according to following formula:
Wherein, Sum
iBe the number sum of the white pixel point of i row in the white license plate area after binaryzation and the inverse processing, WhitePlate (j, i) white pixel point array; Represent the white pixel point of the capable i row of j,, iHeight is the width of this white license plate area; The line number that promptly comprises; After carrying out the inverse processing, the pixel value of each white pixel point is 1 in this white license plate area, and the pixel value of black pixel point is 0.
According to the projection of confirming that whenever is listed in vertical direction, confirm character zone.Confirm that when definite character region, the order according to setting is generally order from left to right, searches the projection value that whenever is listed in vertical direction, is listed in the projection value Sum of vertical direction as i
iGreater than zero the time, confirm that then this i classifies the left margin of character as, continue to search next column afterwards, as the projection value Sum of m row
mEqual at 0 o'clock, confirm that then this m classifies the right margin of character as, then the zone between left margin and the right margin is the character region.According to said method, in a certain order, can in white license plate area, confirm the position at each character place, thereby realize cutting apart of character.
Owing in white license plate area, character is cut apart; Confirmed the position at each character place; Therefore the distance between per two characters can be confirmed, the zone at each character place is the rectangular area in the present invention, can confirm the distance between the character through the center of rectangle.
Three kinds of its structural formulas of dissimilar licence plates of white car plate are different, therefore can be according to the structure of every kind of car plate type, and identification car plate type.For example for alert board, in 7 continuous character strings, the distance between first each and every one and second character is greater than the distance between all the other any two adjacent characters, that is:
d
12>max(d
23,d
34,d
45,d
56,d
67)
D wherein
12, d
23, d
34, d
45, d
56, d
67, be respectively in these 7 continuous character strings the distance between any two adjacent characters.For army's board, in 7 continuous character strings, the distance between second and the 3rd character is greater than the distance between all the other any two adjacent characters, that is:
d
23>max(d
12,d
34,d
45,d
56,d
67)
And for People's Armed Police's car plate, in 5 continuous character strings, the distance between per two characters equates, when the spacing of each adjacent character during less than 3 pixel values, can think that the distance between two characters is equal in the present invention.
According to the distance feature of above-mentioned every kind of car plate type corresponding characters sequence, after each white is cut apart for the character of license plate area, discern corresponding character string in the present invention, judge whether each character string satisfies corresponding distance condition.Fig. 4 is the process synoptic diagram through the white car plate type of distance identification provided by the invention, and this process may further comprise the steps:
S401: according to the distance between per two characters after the Character segmentation, judge the distance between the adjacent character sequence of setting quantity, whether satisfy first distance condition, second distance conditioned disjunction the 3rd distance condition of setting.
S402:, confirm the car plate type of this character string ownership according to the distance condition that this character string satisfies.
S403: adopt the corresponding template of this car plate type, confirm the distance between this template and this character string, select with template apart from the sequence of minimum as car plate, the type of this template correspondence is this car plate type.
Concrete according to the distance between the character in the white car plate; When confirming the car plate type,, take out any 7 continuous character strings and 5 continuous character strings in this car plate to each car plate; A plurality of character strings that satisfy above-mentioned condition possibly arranged in each white license plate area; To each character string of taking out,, select corresponding distance condition according to the length of this character string; Judge whether this character string satisfies this corresponding distance condition; When promptly for example this character string was the character string of 5 characters, then its tool distance condition was whether distance between per two the adjacent character equates, when this character string is the character string of 7 characters; Whether then judge in the character string of this 7 character the distance between preceding two characters greater than the distance between all the other any two adjacent characters, judge that perhaps whether distance between second and the 3rd character is greater than the distance between all the other any two adjacent characters.The character string that satisfies above-mentioned distance condition is taken out, and write down the corresponding distance condition of each character string.
Satisfy the character string of above-mentioned distance condition based on each that select, adopt the corresponding template of this distance condition, mate, confirm the distance of this character string and this template with this character string.According to each character string of from this white car plate sequence, taking out and the average matching distance between its template, selecting the corresponding car plate type of template of mean distance minimum value is the type of this white car plate.Promptly adopt following formula:
Wherein, d
AvgBe average matching distance, d
iBe the distance of i character in the character string and template correspondence position, N is the length of this character string.
For example in this white license plate area, have 3 character strings, wherein; Wherein first character string is the character string of 7 characters, and it satisfies first distance condition, promptly satisfies the distance condition of alert board; Second character string is the character string of 7 characters, and it satisfies the second distance condition, promptly satisfies the distance condition of army's board; The three-character doctrine sequence is the character string of 5 characters, and it satisfies the 3rd distance condition, promptly satisfies the distance condition of People's Armed Police's board; Then these 3 character strings are taken out respectively, template that the army's of employing board is corresponding respectively and first character string coupling, the template that army's board is corresponding promptly satisfies the template of army's board distance condition; The position that each character is corresponding in this template is confirmed; The center of each character is also confirmed, and the center of each character is also confirmed in the character string, therefore according to the center of each character in the template; And the center of corresponding each character; The matching distance that can confirm template and character string with, according to the length of this character string, can confirm the average matching distance of character string and template.Owing to have 3 character strings all to satisfy the distance condition of respective type car plate in this white car plate sequence; Therefore each character string and template corresponding can be confirmed corresponding average matching distance, then select the corresponding car plate type of template of average matching distance minimum value to be the corresponding type of this white car plate.
Fig. 5 is a detailed identifying synoptic diagram that should white car plate type provided by the invention, and this process may further comprise the steps:
S501: in the image of input, carry out the license plate area location, in the license plate area of location, identify white license plate area.
S502: this white license plate area is carried out binary conversion treatment, this white license plate area is carried out rectification.
S503: among the binaryzation white license plate area figure behind rectification, remove up-and-down boundary.
S504: the white license plate area of having removed up-and-down boundary is carried out binary conversion treatment and carries out the inverse processing, confirm the projection of the white license plate area vertical direction after this inverse is handled, the character in the white license plate area is cut apart.
S505: after the Character segmentation, according to the distance between per two adjacent characters in the character string that comprises in this white license plate area, and corresponding distance condition, the character string of every kind of distance condition is satisfied in selection.
S506: according to the character string of selecting, adopt this character string to mate, confirm average matching distance with corresponding template.
S507: selecting the minimum character string of average matching distance is this car plate sequence, and the corresponding car plate type of this template is the type of this white car plate.
Because in the present invention according to the distance between the character string; Confirm to satisfy every type car plate sequence; Afterwards again according to the final type of definite this car plate of the distance of the corresponding template of the type car plate and this character string; Therefore under the situation of twice identification, can guarantee the accuracy and the degree of accuracy of recognition result.
Fig. 6 is a structural representation that should white car plate type identification device provided by the invention, and this device comprises:
Character string is selected module 63, is used for identifying the character string that satisfies every kind of white car plate type in this white car plate based on the distance between per two characters after the Character segmentation;
To the white line of every row, the number of the pixel that comprises according to this white line, and whether the neighbor pixel of pixel same column is black pixel point in this white line, confirms the value of identification parameter; Long-pending greater than the length of first proportion threshold value and white line whether according to the value of identification parameter judges whether this white line is real white line.
Said matching module 64 specifically is used for based on the distance between per two characters after the Character segmentation, judges the distance between the adjacent character sequence of setting quantity, whether satisfies first distance condition, second distance conditioned disjunction the 3rd distance condition of setting; Based on the distance condition that this character string satisfies, confirm the car plate type of this character string ownership; Adopt the corresponding template of this car plate type, confirm the matching distance between this template and this character string, select the minimum sequence of average matching distance as car plate, the corresponding type of this template is this car plate type.
The invention provides a kind of recognition methods and device of white car plate type; This method is when carrying out white car plate type identification; Pretreated white license plate area has been carried out Character segmentation, and the distance according to cutting apart between per two characters in back identifies the character string that satisfies every kind of white car plate type in this white car plate; According to the template corresponding and the matching distance of this character string, confirm the car plate type of this white car plate with every kind of white car plate type.Because in the present invention according to the distance between the character string; Confirm to satisfy every type car plate sequence; Afterwards again according to the final type of definite this car plate of the distance of the corresponding template of the type car plate and this character string; Therefore under the situation of twice identification, can guarantee the accuracy and the degree of accuracy of recognition result.
Above-mentioned explanation illustrates and has described a preferred embodiment of the present invention; But as previously mentioned; Be to be understood that the present invention is not limited to the form that this paper discloses, should do not regard eliminating as, and can be used for various other combinations, modification and environment other embodiment; And can in invention contemplated scope described herein, improve through the technology or the knowledge of above-mentioned design or association area.And change that those skilled in the art carried out and variation do not break away from the spirit and scope of the present invention, then all should be in the protection domain of accompanying claims of the present invention.
Claims (10)
1. the recognition methods of a white car plate type is characterized in that, said method comprises:
In the image of input, carry out the license plate area location, in the license plate area of location, identify white license plate area;
White license plate area to identifying carries out pre-service, and pretreated white license plate area is carried out Character segmentation;
According to the distance between per two characters after the Character segmentation, identify the character string that satisfies every kind of white car plate type in this white car plate;
With each character string, mate with the template of the corresponding car plate type of this character string, confirm the type of each white car plate based on average matching distance.
2. recognition methods as claimed in claim 1 is characterized in that, said below at least a preprocess method to the white license plate area that identifies is carried out pre-service:
Rectification and removal up-and-down boundary;
Adopt said rectification preprocess method, the white license plate area that identifies carried out pre-service comprise:
Adopt corresponding method to carry out binary conversion treatment to the said white license plate area that identifies;
According to the saltus step of pixel value in the white license plate area after the binary conversion treatment that identifies, the position assignment of the pixel that white pixel point is corresponding during with this saltus step in the horizontal edge hum pattern is 1, and the position assignment of other pixels is 0;
With the step-length rotation horizontal edge hum pattern of setting,, confirm that in the angular range of setting every row comprises the number of white pixel point in the horizontal direction to postrotational each angle;
To postrotational each angle, select the more setting line number of number of white pixel point, add up this setting line number white pixel point number and;
Based on the number of white pixel point and the corresponding anglec of rotation of maximum, confirm the RA of this white license plate area this white license plate area to be carried out rectification;
Adopt said taking-up border preprocess method, the white license plate area that identifies carried out pre-service comprise:
Said white license plate area is carried out binary conversion treatment;
In the white license plate area after binary conversion treatment, discern the transition times of every capable pixel value, and confirm the longest white line length and the longest black line length that every row comprises;
According in said transition times, the longest white line length and the longest black line length at least one,, confirm the upper and lower border of this white license plate area with the respective distances threshold value of setting.
3. method as claimed in claim 2 is characterized in that, said before confirming the longest white line length that every row comprises, said method also comprises:
The number of the pixel that this white line is comprised is as the length of this white line, whether greater than the amassing of the car plate width of second proportion threshold value of setting and setting, judges whether this white line is real white line according to the length of this white line; Or
To the white line of every row, the number of the pixel that comprises according to this white line, and whether the neighbor pixel of pixel same column is black pixel point in this white line, confirms the value of identification parameter;
Long-pending greater than the length of first proportion threshold value and white line whether according to the value of identification parameter judges whether this white line is real white line;
When confirming that this white line is real white line, this white line is joined in the selection set of the longest white line length.
4. according to claim 1 or claim 2 recognition methods is characterized in that, saidly pretreated white license plate area is carried out Character segmentation comprises:
Said pretreated white license plate area is carried out binary conversion treatment, and carry out inverse and handle;
The number of adding up every row white pixel point with;
According to the number of every row white pixel point with, judge whether every row are the left and right border of character.
5. recognition methods as claimed in claim 1 is characterized in that, the said character string that satisfies every kind of white car plate type that identifies comprises:
According to the distance between per two characters after the Character segmentation, judge the distance between the adjacent character sequence of setting quantity, whether satisfy first distance condition, second distance conditioned disjunction the 3rd distance condition of setting;
Based on the distance condition that this character string satisfies, confirm the car plate type of this character string ownership;
Adopt the corresponding template of this car plate type, confirm the matching distance between this template and this character string, select the minimum sequence of average matching distance as car plate, the corresponding type of this template is this car plate type.
6. the recognition device of a white car plate type is characterized in that, said device comprises:
Identification module is used for carrying out the license plate area location at the image of input, in the license plate area of location, identifies white license plate area;
Module is cut apart in pre-service, is used for the white license plate area that identifies is carried out pre-service, and pretreated white license plate area is carried out Character segmentation;
Character string is selected module, is used for identifying the character string that satisfies every kind of white car plate type in this white car plate according to the distance between per two characters after the Character segmentation;
Matching module is used for each character string, matees with the template of the corresponding car plate type of this character string, confirms the type of each white car plate according to average matching distance.
7. device as claimed in claim 6 is characterized in that module is cut apart in said pre-service, specifically is used for adopting corresponding method to carry out binary conversion treatment to the said white license plate area that identifies; According to the saltus step of pixel value in the white license plate area after the binary conversion treatment that identifies, the position assignment of the pixel that white pixel point is corresponding during with this saltus step in the horizontal edge hum pattern is 1, and the position assignment of other pixels is 0; With the step-length rotation horizontal edge hum pattern of setting,, confirm that in the angular range of setting every row comprises the number of white pixel point in the horizontal direction to postrotational each angle; To postrotational each angle, select the more setting line number of number of white pixel point, add up this setting line number white pixel point number and; According to the number of white pixel point and the corresponding anglec of rotation of maximal value, confirm the RA of this white license plate area this white license plate area to be carried out rectification; Said white license plate area is carried out binary conversion treatment; In the white license plate area after binary conversion treatment, discern the transition times of every capable pixel value, and confirm the longest white line length and the longest black line length that every row comprises; According in said transition times, the longest white line length and the longest black line length at least one,, confirm the upper and lower border of this white license plate area with the respective distances threshold value of setting.
8. like claim 6 or 7 described devices; It is characterized in that; Module is cut apart in said pre-service; The number of the pixel that specifically is used for this white line is comprised is as the length of this white line, whether greater than the amassing of the car plate width of second proportion threshold value of setting and setting, judges whether this white line is real white line according to the length of this white line; Or
To the white line of every row, the number of the pixel that comprises according to this white line, and whether the neighbor pixel of pixel same column is black pixel point in this white line, confirms the value of identification parameter; Long-pending greater than the length of first proportion threshold value and white line whether according to the value of identification parameter judges whether this white line is real white line;
When confirming that this white line is real white line, this white line is joined in the selection set of the longest white line length.
9. device as claimed in claim 6 is characterized in that module is cut apart in said pre-service, and said pretreated white license plate area is carried out binary conversion treatment, and carries out inverse and handle; The number of adding up every row white pixel point with; According to the number of every row white pixel point with, judge whether every row are the left and right border of character.
10. device as claimed in claim 6; It is characterized in that; Said matching module; Specifically be used for based on the distance between per two characters after the Character segmentation; Judge the distance between the adjacent character sequence of setting quantity, whether satisfy first distance condition, second distance conditioned disjunction the 3rd distance condition of setting; Based on the distance condition that this character string satisfies, confirm the car plate type of this character string ownership; Adopt the corresponding template of this car plate type, confirm the matching distance between this template and this character string, select the minimum sequence of average matching distance as car plate, the corresponding type of this template is this car plate type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210177788.4A CN102693431B (en) | 2012-05-31 | 2012-05-31 | Method and device for identifying type of white number plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210177788.4A CN102693431B (en) | 2012-05-31 | 2012-05-31 | Method and device for identifying type of white number plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102693431A true CN102693431A (en) | 2012-09-26 |
| CN102693431B CN102693431B (en) | 2014-09-24 |
Family
ID=46858848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210177788.4A Expired - Fee Related CN102693431B (en) | 2012-05-31 | 2012-05-31 | Method and device for identifying type of white number plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102693431B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093245A (en) * | 2013-01-21 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Signal lamp identifying method in video image |
| CN104200210A (en) * | 2014-08-12 | 2014-12-10 | 合肥工业大学 | License plate character segmentation method based on parts |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN107368771A (en) * | 2016-05-12 | 2017-11-21 | 北京君正集成电路股份有限公司 | A kind of method and device of positioning licence plate |
| CN108108734A (en) * | 2016-11-24 | 2018-06-01 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| WO2018130216A1 (en) * | 2017-01-16 | 2018-07-19 | 杭州海康威视数字技术股份有限公司 | Method and device for recognizing characters on license plate |
| CN109063702A (en) * | 2018-08-08 | 2018-12-21 | 北京旷视科技有限公司 | Licence plate recognition method, device, equipment and storage medium |
| CN109271993A (en) * | 2018-09-28 | 2019-01-25 | 徐常柏 | A kind of document scanning system, computer equipment and readable storage medium storing program for executing |
| CN109657664A (en) * | 2017-10-12 | 2019-04-19 | 杭州海康威视数字技术股份有限公司 | A kind of recognition methods, device and the electronic equipment of license plate type |
| CN110135416A (en) * | 2018-02-09 | 2019-08-16 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| CN110533019A (en) * | 2018-05-23 | 2019-12-03 | 杭州海康威视数字技术股份有限公司 | License plate locating method, device and storage medium |
| CN110956169A (en) * | 2018-09-27 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1825381A (en) * | 2005-02-24 | 2006-08-30 | 株式会社日立制作所 | Number plate recognition device, adjusting method of electric lens of number plate recognition device |
| CN101383003A (en) * | 2008-10-31 | 2009-03-11 | 江西赣粤高速公路股份有限公司 | Real-time precise recognition method for vehicle number board |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
-
2012
- 2012-05-31 CN CN201210177788.4A patent/CN102693431B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1825381A (en) * | 2005-02-24 | 2006-08-30 | 株式会社日立制作所 | Number plate recognition device, adjusting method of electric lens of number plate recognition device |
| CN101383003A (en) * | 2008-10-31 | 2009-03-11 | 江西赣粤高速公路股份有限公司 | Real-time precise recognition method for vehicle number board |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093245A (en) * | 2013-01-21 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Signal lamp identifying method in video image |
| CN104200210A (en) * | 2014-08-12 | 2014-12-10 | 合肥工业大学 | License plate character segmentation method based on parts |
| CN104200210B (en) * | 2014-08-12 | 2018-11-06 | 合肥工业大学 | A kind of registration number character dividing method based on component |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN104268509B (en) * | 2014-09-17 | 2018-05-29 | 深圳市捷顺科技实业股份有限公司 | The method and system of dump truck car plate detection |
| CN107368771A (en) * | 2016-05-12 | 2017-11-21 | 北京君正集成电路股份有限公司 | A kind of method and device of positioning licence plate |
| CN107368771B (en) * | 2016-05-12 | 2020-10-09 | 北京君正集成电路股份有限公司 | Method and device for positioning license plate |
| CN108108734A (en) * | 2016-11-24 | 2018-06-01 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| CN108108734B (en) * | 2016-11-24 | 2021-09-24 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device |
| CN108319951B (en) * | 2017-01-16 | 2020-10-02 | 杭州海康威视数字技术股份有限公司 | Method and device for recognizing characters in license plate |
| CN108319951A (en) * | 2017-01-16 | 2018-07-24 | 杭州海康威视数字技术股份有限公司 | The method and device of character in a kind of identification car plate |
| WO2018130216A1 (en) * | 2017-01-16 | 2018-07-19 | 杭州海康威视数字技术股份有限公司 | Method and device for recognizing characters on license plate |
| CN109657664A (en) * | 2017-10-12 | 2019-04-19 | 杭州海康威视数字技术股份有限公司 | A kind of recognition methods, device and the electronic equipment of license plate type |
| CN110135416A (en) * | 2018-02-09 | 2019-08-16 | 杭州海康威视数字技术股份有限公司 | A kind of licence plate recognition method and device |
| CN110135416B (en) * | 2018-02-09 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device |
| CN110533019A (en) * | 2018-05-23 | 2019-12-03 | 杭州海康威视数字技术股份有限公司 | License plate locating method, device and storage medium |
| CN110533019B (en) * | 2018-05-23 | 2022-08-12 | 杭州海康威视数字技术股份有限公司 | License plate positioning method and device and storage medium |
| CN109063702A (en) * | 2018-08-08 | 2018-12-21 | 北京旷视科技有限公司 | Licence plate recognition method, device, equipment and storage medium |
| CN110956169A (en) * | 2018-09-27 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | License plate recognition method and device and electronic equipment |
| CN109271993A (en) * | 2018-09-28 | 2019-01-25 | 徐常柏 | A kind of document scanning system, computer equipment and readable storage medium storing program for executing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102693431B (en) | 2014-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102693431B (en) | Method and device for identifying type of white number plate | |
| CN102722733A (en) | Identification method and device of license plate types | |
| CN103116751B (en) | A kind of Method of Automatic Recognition for Character of Lcecse Plate | |
| CN103093181B (en) | A kind of method and apparatus of license plate image location | |
| CN104616009A (en) | Character cutting and recognizing method | |
| CN103745600B (en) | The implementation method of a kind of radio-frequency (RF) identification and Car license recognition comparison | |
| CN103136528B (en) | A kind of licence plate recognition method based on dual edge detection | |
| CN101877050B (en) | Automatic extracting method for characters on license plate | |
| US9977975B2 (en) | Traffic light detection using multiple regions of interest and confidence scores | |
| CN106991820B (en) | Illegal vehicle processing method and device | |
| CN103345766A (en) | Method and device for identifying signal light | |
| CN104766042A (en) | Method and apparatus for and recognizing traffic sign board | |
| CN105702045A (en) | Intelligent detection processing system and method for motor vehicle traffic violation | |
| CN103824452A (en) | Lightweight peccancy parking detection device based on full view vision | |
| CN101334836A (en) | License plate positioning method incorporating color, size and texture characteristic | |
| CN100385452C (en) | Registration number character dividing method | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN111539425A (en) | License plate recognition method, storage medium and electronic equipment | |
| CN104036244A (en) | Checkerboard pattern corner point detecting method and device applicable to low-quality images | |
| CN106845482A (en) | A kind of license plate locating method | |
| CN102750530A (en) | Character recognition method and device | |
| CN105654561A (en) | Multilane free flow vehicle matching method | |
| CN108172008B (en) | Method, device and system for marking parking spaces | |
| CN114495509B (en) | Method for monitoring tunnel running state based on deep neural network | |
| CN111639640B (en) | License plate recognition method, device and equipment based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: HE JIANGTAO Free format text: FORMER OWNER: XINZHENG ELECTRONIC TECHNOLOGY (BEIJING) CO., LTD. Effective date: 20131122 Owner name: LIU ZHONGXUAN TONG HUIYONG Effective date: 20131122 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20131122 Address after: 100085, A, block 6A, block 28, information road, Beijing, Haidian District Applicant after: He Jiangtao Applicant after: Liu Zhongxuan Applicant after: Tong Huiyong Address before: 100085, room 228, Section 2, building 1, building C, 3rd Street, Haidian District, Beijing Applicant before: Xinzheng Electronic Technology (Beijing) Co., Ltd. |
|
| ASS | Succession or assignment of patent right |
Free format text: FORMER OWNER: LIU ZHONGXUAN TONG HUIYONG Effective date: 20140418 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20140418 Address after: 100085, A, block 6A, block 28, information road, Beijing, Haidian District Applicant after: He Jiangtao Address before: 100085, A, block 6A, block 28, information road, Beijing, Haidian District Applicant before: He Jiangtao Applicant before: Liu Zhongxuan Applicant before: Tong Huiyong |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140924 Termination date: 20190531 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |