CN101510258B - Certificate verification method, system and certificate verification terminal - Google Patents
Certificate verification method, system and certificate verification terminal Download PDFInfo
- Publication number
- CN101510258B CN101510258B CN200910077158.8A CN200910077158A CN101510258B CN 101510258 B CN101510258 B CN 101510258B CN 200910077158 A CN200910077158 A CN 200910077158A CN 101510258 B CN101510258 B CN 101510258B
- Authority
- CN
- China
- Prior art keywords
- image
- passport
- area image
- carried out
- certificate
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012795 verification Methods 0.000 title claims abstract description 43
- 230000011218 segmentation Effects 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 9
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 238000009432 framing Methods 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 18
- 238000013528 artificial neural network Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000005484 gravity Effects 0.000 description 5
- 239000012467 final product Substances 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Landscapes
- Character Input (AREA)
Abstract
The invention provides a certificate verification method, a system and a certificate verification terminal, aiming at solving the problem in the traditional checking system which checks the verification of certificates by manually inputting the certificate number and has the disadvantages of wasting time and energy and having high error rate. The method comprises the following steps of: obtaining an area image containing a certificate number; carrying out character segmentation to the area image, thus obtaining images of all the characters; utilizing a classifier obtained by training in advance to carry out identification to the images of all the characters, thus obtaining the certificate number information; and sending the certificate number information to a server side for verification and then receiving the returned checking result. The invention can identify certificate numbers automatically and does not need to input certificate numbers manually, thus greatly raising the efficiency of certificate checking; besides, the identification processing of certificate numbers is carried out in a system terminal, thus occupying little bandwidth and reducing the demand for the performance of network and server terminals.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of certificate verification method, system and a kind of certificate verification terminal.
Background technology
In important sports events and movable holding, the place such as the traffic such as railway station, airport or other important public places need in the security monitoring process unusual pedestrian's identity is checked in real time, to guarantee security.
At present, use electronic information technology to realize that safety, efficiently certificate verification have become an important means of security monitoring, have obtained popularization energetically in recent years.This certificate checking method need to be inputted first unusual pedestrian's passport NO. (such as ID (identity number) card No. etc.), then the passport NO. of inputting is sent to control center, carries out data base querying, and return results, thereby reaches the purpose of the real-time verification of identity.
But traditional checking system input relies on operating personnel manually to input passport NO. by keyboard, waste time and energy, and error rate is high, and a lot of inconvenience is often arranged in the use.
Summary of the invention
Technical matters to be solved by this invention provides a kind of certificate verification method, system and a kind of certificate verification terminal, manually inputs passport NO. to solve traditional checking system, wastes time and energy and problem that error rate is high.
In order to address the above problem, the invention discloses a kind of certificate verification method, comprising:
Obtain the area image that comprises passport NO.;
Described area image is carried out Character segmentation, obtain the image of each character;
Described area image is carried out Character segmentation, obtain the image of each character, specifically comprise: for the first time scanning, from one end to the other side scan every delegation, obtain the foreground segments of all connections in every row, and the foreground segments of each connection is carried out mark; For the second time scanning, from one end to the other side, two row of scanning neighbor are judged the foreground segments that is connected between two row successively, merge the different foreground segments that still are connected of mark; Calculate the peripheral rectangle of each connected region according to foreground segments corresponding to isolabeling not; According to priori, reject and disturb rectangle frame, each character picture after obtaining cutting apart; The sorter that utilizes training in advance to obtain is identified described each character picture, obtains passport NO. information; Described passport NO. information is sent to server end verify, and receive the result that returns.
Preferably, the described area image that comprises passport NO. that obtains specifically comprises: the certificate that the hardware draw-in groove fixes insertion is set, and described hardware arranges the Charge Coupled Device (CCD) imageing sensor in the position of corresponding passport NO.; The area image that comprises passport NO. by the collection of described Charge Coupled Device (CCD) imageing sensor.
Preferably, the described area image that comprises passport NO. that obtains specifically comprises: the whole image that gathers certificate; According to the passport NO. characteristic fixing in the additional clause position, in the whole image of certificate, determine the described area image that comprises passport NO..
Preferably, described obtaining after the area image that comprises passport NO. also comprises: described area image is carried out pre-service, obtain pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation; Then described area image being carried out Character segmentation is: described pretreated area image is carried out Character segmentation.
Preferably, described area image is carried out pre-service, obtain also comprising after the pretreated area image: by setting threshold described pretreated area image is carried out binary conversion treatment, obtain black and white binary image; Described black and white binary image is carried out medium filtering, obtain filtered black and white binary image; Then described area image being carried out Character segmentation is: described filtered black and white binary image is carried out Character segmentation.
Preferably, described method also comprises: gather figure information by camera head, then described figure information is sent to server end and verify, and receive the result that returns.
The invention also discloses a kind of certificate verification system, comprise end device and authentication server, described end device comprises:
Image acquisition unit is used for obtaining the area image that comprises passport NO.;
The Character segmentation unit is used for described area image is carried out Character segmentation, obtains the image of each character;
Described Character segmentation unit specifically comprises:
The first scanning subelement is used for for the first time scanning, from one end to the other side scans every delegation, obtains the foreground segments of all connections in every row, and the foreground segments of each connection is carried out mark;
The second scanning subelement, for for the second time scanning, from one end to the other side, two row of scanning neighbor are judged the foreground segments that is communicated with between two row successively, merge the different foreground segments that still are connected of mark;
Computation subunit is used for calculating according to foreground segments corresponding to isolabeling not the peripheral rectangle of each connected region;
Character picture generates subelement, is used for according to priori, rejects and disturbs rectangle frame, each character picture after obtaining cutting apart;
The number recognition unit, the sorter that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit is used for that described passport NO. information is sent to described authentication server and verifies, and receives the result that returns.
Preferably, described image acquisition unit specifically comprises: the hardware draw-in groove is used for the fixing certificate that inserts; The Charge Coupled Device (CCD) imageing sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
Preferably, described image acquisition unit specifically comprises: the image acquisition subelement, for the whole image that gathers certificate; The framing subelement is used for determining the described area image that comprises passport NO. according to the passport NO. characteristic fixing in the additional clause position in the whole image of certificate.
Preferably, described end device also comprises: pretreatment unit, be used for described area image is carried out pre-service, and obtain pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation; Then described Character segmentation unit is used for described pretreated area image is carried out Character segmentation.
Preferably, described end device also comprises: binarization unit, be used for by setting threshold described pretreated area image being carried out binary conversion treatment, and obtain black and white binary image; Median filter unit is used for described black and white binary image is carried out medium filtering, obtains filtered black and white binary image; Then described Character segmentation unit is used for described filtered black and white binary image is carried out Character segmentation.
Preferably, described end device also comprises: image unit be used for to gather figure information, and by described data transmission unit described figure information is sent to described authentication server and verify; Described authentication server returns the result.
Preferably, described end device also comprises: display unit, the result that is used for described authentication server is returned shows.
The invention also discloses a kind of certificate verification terminal, comprising:
Image acquisition unit is used for obtaining the area image that comprises passport NO.;
Pretreatment unit is used for described area image is carried out pre-service, obtains pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Binarization unit is used for by setting threshold described pretreated area image being carried out binary conversion treatment, obtains black and white binary image;
Median filter unit is used for described black and white binary image is carried out medium filtering, obtains filtered black and white binary image;
The Character segmentation unit is used for described filtered black and white binary image is carried out Character segmentation, obtains the image of each character;
The number recognition unit, the sorter that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit is used for that described passport NO. information is sent to described authentication server and verifies, and receives the result that returns;
Display unit is used for the result that described data transmission unit receives is shown.
Preferably, described image acquisition unit specifically comprises: the hardware draw-in groove is used for the fixing certificate that inserts; The Charge Coupled Device (CCD) imageing sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
Compared with prior art, the present invention has the following advantages:
At first, certificate verification method provided by the invention is a kind of image-based character recognition identity checking method, the method Schema-based recognition technology is analyzed passport NO., by processing such as Character segmentation and identifications, automatic lifting is got passport NO. information, and send into the relevant information (such as name, native place etc.) of this number of data base querying of server end, and send back to again and export on display screen, finish whole ID inquiring checking procedure.This certificate verification method can be identified passport NO. automatically, does not need manually to input passport NO., has improved greatly the efficient of certificates checking, has saved personnel cost.Therefore, have extremely widely at aspects such as the safeguard protection in the public safety places such as customs, personnel cost savings and use.
And, the present invention places system terminal with the identifying processing of passport NO., carry out immediately the identifying processing of number after the certificate image collection, terminal only needs that the passport NO. that identifies is sent to server end in real time and gets final product, do not need to transmit entire image, occupied bandwidth is little, and real-time is good, greatly reduces the performance requirement to network and server end.And described terminal operation is easy, is easy to carry, and is convenient for users.
Secondly, certificate verification provided by the invention system passes through hardware design, Charge Coupled Device (CCD) imageing sensor (CCD is set in the position of corresponding passport NO., Charge Coupled Device), can only take pictures to the zone that comprises passport NO., comprise the area image of passport NO. thereby directly gather, and do not need to carry out again in the software processing procedure localization process in number zone, therefore so that locate more quick and precisely.
Again, the present invention carefully thinks out, and image that can the collector by additional camera head carries out verification for server end, has improved the accuracy of identity examination.
Description of drawings
Fig. 1 is the described a kind of certificate verification method process flow diagram of the embodiment of the invention;
Fig. 2 adopts labelling method to carry out the process flow diagram of Character segmentation in the embodiment of the invention;
Fig. 3 is the synoptic diagram of neural network classifier in the embodiment of the invention;
Fig. 4 .1 is the gray level image synoptic diagram before the binary conversion treatment in the embodiment of the invention;
Fig. 4 .2 is the black white image synoptic diagram after the binary conversion treatment in the embodiment of the invention;
Fig. 4 .3 adopts labelling method to carry out the result schematic diagram of Character segmentation in the embodiment of the invention;
Fig. 5 is the structural drawing of the described a kind of certificate verification of system embodiment of the present invention system;
Fig. 6 is the structural drawing of the described a kind of certificate verification terminal of system embodiment of the present invention.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
The embodiment of the invention provides a kind of certificate verification method, can be used for certificate verification occasion personnel identity is checked.The method is a kind of image-based character identifying method, by processing such as Character segmentation and identifications, automatic lifting is got passport NO. information, and send into the relevant information (such as name, native place etc.) of this number of data base querying of server end, send back to again and export on display screen, finish whole ID inquiring checking procedure.The present invention is applicable to the checking of all kinds of certificates, and the below is elaborated with the example that is verified as of I.D..
With reference to Fig. 1, the described a kind of certificate verification method process flow diagram of the embodiment of the invention.
Step 101 is obtained the area image that comprises passport NO.;
The described area image that comprises passport NO. refers to the image of number zone in the certificate and close region thereof, is not the image in whole certificate zone.The below introduces two kinds of obtain manners relatively more commonly used:
A kind of obtain manner is, by the mode such as take pictures image acquisition carried out in the whole zone of I.D. first, then whole image carried out software analysis, therefrom extracts the described zone that comprises passport NO..Because the number position of all kinds of certificates such as I.D. is fixed in whole certificate, so according to this characteristic, can analyze the number position by modes such as coordinate judgements, thereby in the whole image of certificate, determine the described area image (this process is called the location) that comprises passport NO..
This mode need to be carried out analytical calculation, therefore present embodiment provides another kind of preferred obtain manner: pass through hardware design, the certificate that the hardware draw-in groove fixes insertion is set, and the position of corresponding passport NO. arranges CCD area array sensor (being the Charge Coupled Device (CCD) imageing sensor) on described hardware, and only check numbers zone and close region thereof of the camera of this CCD area array sensor taken.Therefore, just can directly collect the area image that comprises passport NO. by the CCD area array sensor, and not need to carry out the software positioning analysis, so this locator meams more quick and precisely.
Step 102 is carried out Character segmentation to described area image, obtains the image of each character;
For ID (identity number) card No., the area image that obtains through above-mentioned obtaining step has comprised a plurality of numbers, the ID (identity number) card No. in should the zone can be divided into individual digit by the Character segmentation step, and then identify respectively.The Character segmentation method also has multiple, such as vertical projection method etc., does not describe in detail at this.Present embodiment is owing to locate in the zone of having checked numbers in step 101, so can adopt labelling method to carry out Character segmentation, with reference to Fig. 2, detailed processing procedure is as follows:
Step 203 is calculated the peripheral rectangle of each connected region according to foreground segments corresponding to isolabeling not;
Step 204 according to priori, should be on the same level direction such as the center of all characters, rejects and disturbs rectangle frame, each character picture after just can obtaining cutting apart.
The segmentation result of employing labelling method can be with reference to shown in Fig. 4 .3.
Carry out Character segmentation and obtain after the image of single character, continue following steps.
Present character recognition technologies mainly contains based on template matching algorithm with based on artificial neural network algorithm.Character binaryzation after at first will cutting apart based on template matching algorithm, and its size is scaled the size of template in the character database, then mate with all templates, select at last optimum matching as a result of.Based on artificial neural network's algorithm in advance according to character feature neural network training sorter, then the character picture after will cutting apart is sent into described neural network classifier, and sorter just can extract feature and identifies according to the sorting technique of setting from character to be identified.Sorter after described neural network training sorter and the utilization training carries out the known technology that character recognition belongs to those skilled in the art, is not described in detail in this.
Present embodiment adopts and identifies based on artificial neural network algorithm.For ID (identity number) card No., concrete characteristic information comprises:
1) number of edges
Referring to that the edge of a character is communicated with the number of profile, is 2 such as the number of edges of character 6.
2) edge gravity center
Edge gravity center is 2 character mainly for number of edges, calculates respectively the coordinate of top, two edges and bottom, is designated as y
Edge1 Top, y
Edge1 Bottom, y
Edge2 Top, y
Edge2 Bottom, the difference at two edges of this that ask respectively again
So work as D
Top/ D
Bottom＜0.5, edge gravity center is at the first half; Work as D
Top/ D
Bottom＞2, edge gravity center is in Lower Half.
3) contour feature value
Utilize the single order differential variation tendency definition of profile to consist of the elementary cell of character outline, be divided into five classes: left tiltedly, right tiltedly, straight line, circular arc, sudden change.
4) duty information
Utilize top, bottom, left side, the right side of contour feature calculating character image and all directions of 45 degree that are clipped in the middle to the duty amount in totally 12 zones.
5) stroke number
Take to a certain position of character up and down or about draw arbitrarily straight line, check that it is through the number of times of white portion;
6) projection
Character is carried out vertically and horizontal projection the projection amount of statistics diverse location.
7) nose
Calculate vertically or the white line length of horizontal direction connected region, then find out wherein long one, can look for also and can look in certain zone in entire image;
8) Area Ratio
Calculate the area that character is put in a certain zone, be mainly used to distinguish such as " 0 " or " D " and characters such as " Q ".Need when quadraturing the black region that white connected region comprises is filled.
Based on above characteristic information, the neural network classifier that training obtains can with reference to shown in Figure 3, only list number of edges, edge gravity center and three features of contour feature value and describe, but be not limited to illustrated three features among the figure.
In actual applications, also have other characteristic informations to can be used for training classifier, do not enumerate one by one at this.
Above-mentioned utilize neural network classifier to identify each character after, make up and namely obtain complete ID (identity number) card No..
Step 104 sends to server end with described passport NO. information and verifies, and receives the result that returns.
The passport NO. information exchange that identifies is crossed wireless network send to server end, server end can return Query Result, and show by data base querying.
This certificate verification method can be identified passport NO. automatically, does not need manually to input passport NO., has improved greatly the efficient of certificates checking, has saved personnel cost.Therefore, have extremely widely at aspects such as the safeguard protection in the public safety places such as customs, personnel cost savings and use.
And, described method places system front end with the identifying processing of passport NO., carry out immediately the identifying processing of number after the certificate image collection, front end only needs that the passport NO. that identifies is sent to server end in real time and gets final product, do not need to transmit entire image, occupied bandwidth is little, and real-time is good, greatly reduces the performance requirement to network and server end.
Preferably, in the above-mentioned treatment step, between step 101 and 102, can insert a pre-treatment step: described area image is carried out pre-service, obtain pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation.Then step 102 pair described area image carries out Character segmentation and is: described pretreated area image is carried out Character segmentation.
In image processing process, described preprocessing process mainly comprises simple noise reduction process and image enhancement processing.Wherein, described simple noise reduction process can be filtered the initial pictures that collects, the interference that filtering is large, and then continue following treatment scheme.
Described figure image intensifying refers to strengthen selectively some information of image, and such as edge, profile, contrast etc., purpose is edge and the details of outstanding image, so that follow-up processing and analysis.In image processing field, the method for figure image intensifying has a variety of, such as the image enchancing method based on mathematical morphology, and based on the image enchancing method of rough set theory, etc.The image enchancing method that present embodiment adopts is greyscale transformation.
The greyscale transformation of image (Gray-Scale Transformation; GST) processing is a kind of very basic, direct spatial domain image processing method in the image enhancement processing technology, also is an important component part of image digitazation software and image software for display.Greyscale transformation refers to that purpose is in order to improve image quality, to make the display effect of image more clear according to the method for certain goal condition by each grey scale pixel value in certain transformation relation pointwise change original image.
At this, present embodiment does not limit adoptable image enchancing method.
Preferably, can also insert the processing of a binaryzation before step 102 is carried out Character segmentation, this is processed usually after above-mentioned pre-treatment step.The purpose of binaryzation is to remove background image, and the character in the image is removed more.The method of binaryzation has a lot, and a kind of method commonly used is threshold method, namely specifies in advance or generates a threshold value T by algorithm, then with T the data of image is divided into the two large divisions: greater than the pixel group of T with less than the pixel group of T.The binarization method that present embodiment adopts is: by setting threshold described pretreated area image is carried out binary conversion treatment, obtain black and white binary image.With reference to Fig. 4 .1, be the gray level image synoptic diagram before the binary conversion treatment, and Fig. 4 .2 is the image synoptic diagram after the binary conversion treatment.Like this, step 102 is carried out Character segmentation to described filtered black and white binary image exactly.
Carry out after the binary conversion treatment, in order further to reduce noise, can also continue image is carried out medium filtering, filtering impulsive noise is on the impact of Character segmentation.The principle of described medium filtering is: if the number of foreground pixel point is lacked (namely less than 5) than background pixel point in 3 * 3 the window, the central point of this window is exactly a noise spot so.Concrete operations are: to each the foreground pixel point in the bianry image, and the summation of the value of 9 pixels in 3 * 3 the image window of statistics centered by it; If summation so just thinks that less than the threshold value (default value is 5) of setting this pixel is noise spot, the pixel value of its correspondence position is set to 0, otherwise is set to 1.
Preferably, when ID (identity number) card No. is checked, for improving the accuracy of identity examination, can also gather figure information by camera head, then described figure information be sent to server end and verify, and receive the result that returns.
For the description of said method embodiment, the present invention also provides the embodiment of a kind of certificate verification system.With reference to Fig. 5, it is the structural drawing of the described a kind of certificate verification of embodiment system.Described certificate verification system comprises end device 51 and authentication server 52, and described end device 51 is arranged at system front end, is mainly used in gathering image and carries out immediately identifying processing, then the passport NO. information that identifies is sent to authentication server 52; Described authentication server 52 is mainly used in described passport NO. is carried out data base querying, and returns Query Result to described end device 51.
Described end device 51 mainly comprises:
Image acquisition unit 511 is used for obtaining the area image that comprises passport NO.;
Character segmentation unit 513 is used for described pretreated area image is carried out Character segmentation, obtains the image of each character;
Number recognition unit 514, the divider that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit 515 is used for that described passport NO. information is sent to described authentication server 52 and verifies, and receives the result that returns.
Wherein, described image acquisition unit 511 can be realized by software mode, specifically comprises:
The image acquisition subelement is for the whole image that gathers certificate;
The framing subelement is used for determining the described area image that comprises passport NO. according to the passport NO. characteristic fixing in the additional clause position in the whole image of certificate.
Preferably, described image acquisition unit 511 can also be realized by hardware mode, determines more rapidly and accurately the number zone, specifically comprises:
The hardware draw-in groove is used for the fixing certificate that inserts;
Ccd sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
Preferably, described Character segmentation unit 513 specifically comprises:
The first scanning subelement is used for for the first time scanning, from one end to the other side scans every delegation, obtains the foreground segments of all connections in every row, and the foreground segments of each connection is carried out mark;
The second scanning subelement, for for the second time scanning, from one end to the other side, two row of scanning neighbor are judged the foreground segments that is communicated with between two row successively, merge the different foreground segments that still are connected of mark;
Computation subunit is used for calculating according to foreground segments corresponding to isolabeling not the peripheral rectangle of each connected region;
Character picture generates subelement, is used for according to priori, rejects and disturbs rectangle frame, each character picture after obtaining cutting apart.
Above-mentioned certificate verification system can identify passport NO. automatically, does not need manually to input passport NO., has improved greatly the efficient of certificates checking, has saved personnel cost.And, the identifying processing of passport NO. is placed system terminal, occupied bandwidth is little, and real-time is good, greatly reduces the performance requirement to network and server end.And described level of integrated system is high, and modular structure is clear, and each module division of labor is clear and definite, and independence is strong, has improved stability and the reliability of entire system.
Preferably, described end device 51 can also comprise:
Pretreatment unit 512 is used for described area image is carried out pre-service, obtains pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Then described Character segmentation unit 513 is used for described pretreated area image is carried out Character segmentation.
Preferably, described end device 51 can also comprise:
Binarization unit is used for by setting threshold described pretreated area image being carried out binary conversion treatment, obtains black and white binary image;
Median filter unit is used for continuing the black white image after the binaryzation is carried out medium filtering, and filtering impulsive noise obtains filtered black and white binary image to the impact of Character segmentation.
Then described Character segmentation unit 513 is used for described filtered black and white binary image is carried out Character segmentation.
Preferably, described end device 51 can also comprise image unit, can improve the accuracy of identity examination.Described image unit be used for to gather figure information, and by described data transmission unit 515 described figure information is sent to described authentication server 52 and verify; Described authentication server 52 returns the result.
Preferably, described end device 51 can also comprise: display unit 516, the result that is used for described authentication server 52 is returned shows.Wherein, described the result can comprise the Query Result of passport NO. and the Query Result of figure information.
The present invention also provides a kind of embodiment of certificate verification terminal.With reference to Fig. 6, it is the structural drawing of the described a kind of certificate verification terminal of embodiment.Described certificate verification terminal mainly comprises:
Image acquisition unit 61 is used for obtaining the area image that comprises passport NO.;
Pretreatment unit 62 is used for described area image is carried out pre-service, obtains pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Binarization unit 63 is used for by setting threshold described pretreated area image being carried out binary conversion treatment, obtains black and white binary image;
Median filter unit 64 is used for described black and white binary image is carried out medium filtering, obtains filtered black and white binary image;
Character segmentation unit 65 is used for described filtered black and white binary image is carried out Character segmentation, obtains the image of each character;
Number recognition unit 66, the sorter that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit 67 is used for that described passport NO. information is sent to described authentication server and verifies, and receives the result that returns;
Display unit 68 is used for the result that described data transmission unit receives is shown.
Preferably, described image acquisition unit 61 can be realized by hardware mode, determines more rapidly and accurately the number zone, specifically comprises:
The hardware draw-in groove is used for the fixing certificate that inserts;
Ccd sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
Preferably, described certificate verification terminal can also comprise image unit, can improve the accuracy of identity examination.Described image unit be used for to gather figure information, and by described data transmission unit 65 described figure information is sent to described authentication server and verify; Described authentication server returns the result.
Described certificate verification terminal operation is easy, is easy to carry, and is convenient for users.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is and the difference of other embodiment that identical similar part is mutually referring to getting final product between each embodiment.For system embodiment because itself and embodiment of the method basic simlarity, so describe fairly simple, relevant part gets final product referring to the part explanation of embodiment of the method.
More than to a kind of certificate verification method provided by the present invention, system and a kind of certificate verification terminal, be described in detail, used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (15)
1. a certificate verification method is characterized in that, comprising:
Obtain the area image that comprises passport NO.;
Described area image is carried out Character segmentation, obtain the image of each character;
Described area image is carried out Character segmentation, obtains the image of each character, specifically comprise:
Scanning from one end to the other side scans every delegation for the first time, obtains the foreground segments of all connections in every row, and the foreground segments of each connection is carried out mark;
For the second time scanning, from one end to the other side, two row of scanning neighbor are judged the foreground segments that is connected between two row successively, merge the different foreground segments that still are connected of mark;
Calculate the peripheral rectangle of each connected region according to foreground segments corresponding to isolabeling not;
According to priori, reject and disturb rectangle frame, each character picture after obtaining cutting apart;
The sorter that utilizes training in advance to obtain is identified described each character picture, obtains passport NO. information;
Described passport NO. information is sent to server end verify, and receive the result that returns.
2. the method for claim 1 is characterized in that, the described area image that comprises passport NO. that obtains specifically comprises:
The certificate that the hardware draw-in groove fixes insertion is set, and described hardware arranges the Charge Coupled Device (CCD) imageing sensor in the position of corresponding passport NO.;
The area image that comprises passport NO. by the collection of described Charge Coupled Device (CCD) imageing sensor.
3. the method for claim 1 is characterized in that, the described area image that comprises passport NO. that obtains specifically comprises:
Gather the whole image of certificate;
According to the passport NO. characteristic fixing in the additional clause position, in the whole image of certificate, determine the described area image that comprises passport NO..
4. the method for claim 1 is characterized in that, described obtaining after the area image that comprises passport NO. also comprises:
Described area image is carried out pre-service, obtain pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Then described area image being carried out Character segmentation is: described pretreated area image is carried out Character segmentation.
5. method as claimed in claim 4 is characterized in that, described area image is carried out pre-service, obtains also comprising after the pretreated area image:
By setting threshold described pretreated area image is carried out binary conversion treatment, obtain black and white binary image;
Described black and white binary image is carried out medium filtering, obtain filtered black and white binary image;
Then described area image being carried out Character segmentation is: described filtered black and white binary image is carried out Character segmentation.
6. the method for claim 1 is characterized in that, also comprises:
Gather figure information by camera head, then described figure information is sent to server end and verify, and receive the result that returns.
7. a certificate verification system is characterized in that, comprises end device and authentication server, and described end device comprises:
Image acquisition unit is used for obtaining the area image that comprises passport NO.;
The Character segmentation unit is used for described area image is carried out Character segmentation, obtains the image of each character;
Described Character segmentation unit specifically comprises:
The first scanning subelement is used for for the first time scanning, from one end to the other side scans every delegation, obtains the foreground segments of all connections in every row, and the foreground segments of each connection is carried out mark;
The second scanning subelement, for for the second time scanning, from one end to the other side, two row of scanning neighbor are judged the foreground segments that is communicated with between two row successively, merge the different foreground segments that still are connected of mark;
Computation subunit is used for calculating according to foreground segments corresponding to isolabeling not the peripheral rectangle of each connected region;
Character picture generates subelement, is used for according to priori, rejects and disturbs rectangle frame, each character picture after obtaining cutting apart;
The number recognition unit, the sorter that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit is used for that described passport NO. information is sent to described authentication server and verifies, and receives the result that returns.
8. system as claimed in claim 7 is characterized in that, described image acquisition unit specifically comprises:
The hardware draw-in groove is used for the fixing certificate that inserts;
The Charge Coupled Device (CCD) imageing sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
9. system as claimed in claim 7 is characterized in that, described image acquisition unit specifically comprises:
The image acquisition subelement is for the whole image that gathers certificate;
The framing subelement is used for determining the described area image that comprises passport NO. according to the passport NO. characteristic fixing in the additional clause position in the whole image of certificate.
10. system as claimed in claim 7 is characterized in that, described end device also comprises:
Pretreatment unit is used for described area image is carried out pre-service, obtains pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Then described Character segmentation unit is used for described pretreated area image is carried out Character segmentation.
11. system as claimed in claim 10 is characterized in that, described end device also comprises:
Binarization unit is used for by setting threshold described pretreated area image being carried out binary conversion treatment, obtains black and white binary image;
Median filter unit is used for described black and white binary image is carried out medium filtering, obtains filtered black and white binary image;
Then described Character segmentation unit is used for described filtered black and white binary image is carried out Character segmentation.
12. system as claimed in claim 7 is characterized in that, described end device also comprises:
Image unit be used for to gather figure information, and by described data transmission unit described figure information is sent to described authentication server and verify;
Described authentication server returns the result.
13. such as claim 7 or 12 described systems, it is characterized in that described end device also comprises:
Display unit, the result that is used for described authentication server is returned shows.
14. a certificate verification terminal is characterized in that, comprising:
Image acquisition unit is used for obtaining the area image that comprises passport NO.;
Pretreatment unit is used for described area image is carried out pre-service, obtains pretreated area image; Wherein said pre-service comprises noise reduction and greyscale transformation;
Binarization unit is used for by setting threshold described pretreated area image being carried out binary conversion treatment, obtains black and white binary image;
Median filter unit is used for described black and white binary image is carried out medium filtering, obtains filtered black and white binary image; The Character segmentation unit is used for described filtered black and white binary image is carried out Character segmentation, obtains the image of each character;
The number recognition unit, the sorter that is used for utilizing training in advance to obtain is identified described each character picture, obtains passport NO. information;
Data transmission unit is used for that described passport NO. information is sent to described authentication server and verifies, and receives the result that returns;
Display unit is used for the result that described data transmission unit receives is shown.
15. certificate verification terminal as claimed in claim 14 is characterized in that, described image acquisition unit specifically comprises:
The hardware draw-in groove is used for the fixing certificate that inserts;
The Charge Coupled Device (CCD) imageing sensor is arranged at the position of corresponding passport NO. on the described hardware, is used for gathering the area image that comprises passport NO..
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910077158.8A CN101510258B (en) | 2009-01-16 | 2009-01-16 | Certificate verification method, system and certificate verification terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910077158.8A CN101510258B (en) | 2009-01-16 | 2009-01-16 | Certificate verification method, system and certificate verification terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101510258A CN101510258A (en) | 2009-08-19 |
| CN101510258B true CN101510258B (en) | 2013-02-13 |
Family
ID=41002653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910077158.8A Active CN101510258B (en) | 2009-01-16 | 2009-01-16 | Certificate verification method, system and certificate verification terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101510258B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217202A (en) * | 2013-06-03 | 2014-12-17 | 支付宝（中国）网络技术有限公司 | Method, apparatus and system for recognizing information |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156853B (en) * | 2010-02-11 | 2013-08-28 | 深圳鼎识科技有限公司 | Certificate reading system and certificate reading method |
| CN101923741B (en) * | 2010-08-11 | 2012-07-18 | 西安理工大学 | Paper currency number identification method based on currency detector |
| CN102402684B (en) * | 2010-09-15 | 2015-02-11 | 富士通株式会社 | Method and device for determining type of certificate and method and device for translating certificate |
| CN102288619B (en) * | 2011-07-01 | 2013-04-24 | 明基材料有限公司 | Method and system for detecting defects of three-dimensional optical film |
| CN103593642A (en) * | 2012-08-16 | 2014-02-19 | 阿里巴巴集团控股有限公司 | Card-information acquisition method and system |
| CN103632102B (en) * | 2012-08-21 | 2018-01-12 | 中兴通讯股份有限公司 | Certificate processing method and terminal |
| CN103116752A (en) * | 2013-02-25 | 2013-05-22 | 新浪网技术(中国)有限公司 | Picture auditing method and system |
| DE102013107951A1 (en) * | 2013-07-25 | 2015-01-29 | Bundesdruckerei Gmbh | Procedure for verifying the authenticity of a document |
| CN105528600A (en) * | 2015-10-30 | 2016-04-27 | 小米科技有限责任公司 | Region identification method and device |
| CN106034135B (en) * | 2016-01-21 | 2019-06-28 | 李明 | Identity card cloud authentication device |
| CN106407245B (en) * | 2016-06-23 | 2021-05-07 | 平安科技（深圳）有限公司 | Information processing method and device |
| CN106203415B (en) * | 2016-06-30 | 2019-12-10 | 三峡大学 | bank card number automatic identification device based on digital image processing |
| CN106778748A (en) * | 2016-12-30 | 2017-05-31 | 江西憶源多媒体科技有限公司 | Identity card method for quickly identifying and its device based on artificial neural network |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN109409349B (en) * | 2018-02-02 | 2021-04-27 | 深圳壹账通智能科技有限公司 | Credit certificate authentication method, credit certificate authentication device, credit certificate authentication terminal and computer readable storage medium |
| CN108492087A (en) * | 2018-03-28 | 2018-09-04 | 施益斌 | Architectural design bidding platform registers auditing system |
| CN110135288B (en) * | 2019-04-28 | 2023-04-18 | 佛山科学技术学院 | Method and device for quickly checking electronic certificate |
| CN110232759A (en) * | 2019-06-12 | 2019-09-13 | 浙江机电职业技术学院 | A kind of station ticket selling and checking system and method |
| CN110458238A (en) * | 2019-08-02 | 2019-11-15 | 南通使爱智能科技有限公司 | A kind of method and system of certificate arc point detection and positioning |
| CN110427739A (en) * | 2019-08-09 | 2019-11-08 | 泰康保险集团股份有限公司 | Information Authentication method and device, electronic equipment and computer readable storage medium |
| CN111709413A (en) * | 2020-06-22 | 2020-09-25 | 中国平安财产保险股份有限公司 | Certificate verification method and device based on image recognition, computer equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6886136B1 (en) * | 2000-05-05 | 2005-04-26 | International Business Machines Corporation | Automatic template and field definition in form processing |
| CN2800378Y (en) * | 2005-04-22 | 2006-07-26 | 郭杰 | Universal checking, recognizing device for identity card |
| CN101064600A (en) * | 2006-04-29 | 2007-10-31 | 上海祥网瑞电子科技有限公司 | Telecom client identity document information management method |
-
2009
- 2009-01-16 CN CN200910077158.8A patent/CN101510258B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6886136B1 (en) * | 2000-05-05 | 2005-04-26 | International Business Machines Corporation | Automatic template and field definition in form processing |
| CN2800378Y (en) * | 2005-04-22 | 2006-07-26 | 郭杰 | Universal checking, recognizing device for identity card |
| CN101064600A (en) * | 2006-04-29 | 2007-10-31 | 上海祥网瑞电子科技有限公司 | Telecom client identity document information management method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217202A (en) * | 2013-06-03 | 2014-12-17 | 支付宝（中国）网络技术有限公司 | Method, apparatus and system for recognizing information |
| US10210415B2 (en) | 2013-06-03 | 2019-02-19 | Alipay.Com Co., Ltd | Method and system for recognizing information on a card |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101510258A (en) | 2009-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101510258B (en) | Certificate verification method, system and certificate verification terminal | |
| CN107748888B (en) | A kind of image text row detection method and device | |
| CN103034848B (en) | A kind of recognition methods of form types | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| CN103914686B (en) | A kind of face alignment authentication method and system shone based on certificate photo with collection | |
| CN102629322B (en) | Character feature extraction method based on stroke shape of boundary point and application thereof | |
| CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
| CN102915433B (en) | Character combination-based license plate positioning and identifying method | |
| CN106096667B (en) | Bill images sorting technique based on SVM | |
| CN103903018A (en) | Method and system for positioning license plate in complex scene | |
| CN106875546A (en) | A kind of recognition methods of VAT invoice | |
| CN102880863B (en) | Method for positioning license number and face of driver on basis of deformable part model | |
| CN105427320A (en) | Image segmentation and extraction method | |
| CN101038686A (en) | Method for recognizing machine-readable travel certificate | |
| CN103902981A (en) | Method and system for identifying license plate characters based on character fusion features | |
| CN104408449A (en) | Intelligent mobile terminal scene character processing method | |
| CN107886047A (en) | A kind of detecting system and method for vehicle annual test survey report | |
| CN102194275A (en) | Automatic ticket checking method for train tickets | |
| CN103295009B (en) | Based on the license plate character recognition method of Stroke decomposition | |
| CN109447067A (en) | A kind of bill angle detecting antidote and automatic ticket checking system | |
| CN109657676A (en) | Licence plate recognition method and system based on convolutional neural networks | |
| CN103699876B (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| CN103324958A (en) | License plate locating method based on projection method and SVM under complex background | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN106846815A (en) | A kind of efficient intelligent traffic administration system big data analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C57 | Notification of unclear or unknown address | ||
| DD01 | Delivery of document by public notice |
Addressee: Li Yan Document name: Notification to Make Rectification |
|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160516 Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -478 Patentee after: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee before: Beijing Vimicro Corporation |