CN110533643A

CN110533643A - Certificate identification method and device

Info

Publication number: CN110533643A
Application number: CN201910774059.9A
Authority: CN
Inventors: 黄江波; 郭明宇; 徐炎; 徐崴
Original assignee: Alibaba Group Holding Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-08-21
Filing date: 2019-08-21
Publication date: 2019-12-03
Anticipated expiration: 2039-08-21
Also published as: CN110533643B

Abstract

This specification embodiment provides a kind of certificate identification method and device, wherein method includes: to obtain in the case where setting lighting condition to the first image of document photography to be identified, wherein first image includes the image of the certificate to be identified；Spot detection is carried out to first image；If spot detection result meets preset hot spot existence condition, the detection of detection pattern is carried out to the peripheral region of the hot spot detected；According to the material information of certificate to be identified and the testing result of detection pattern, certificate to be identified is identified.

Description

Certificate identification method and device

Technical field

This document is related to field of anti-counterfeit technology more particularly to a kind of certificate identification method and device, equipment and storage medium.

Background technique

There are the demands of a large amount of remote validation certificates in reality, for example apply for new cell-phone card on the net, open security account on the net Family, online application schooling certificate etc. require the certificate of remote validation applicant.A kind of common verification method requires on user Pass certificate image, through it is manual or automatic distinguish the true and false after complete authentication.

This verification process first has to the validity for the certificate image for ensuring that user is uploaded, and mainly prevents attacker sharp Image is forged with various means, for example common forgery means include: screen reproduction, papery duplicating, copper sheet printing etc..Currently, Means are forged for screen reproduction, papery duplicating, copper sheet printing etc., never therefore effective identification method needs one kind The method that effectively certificate can be identified.

Summary of the invention

The purpose of this specification one or more embodiment is to provide a kind of certificate identification method and device, equipment and storage Medium, to provide a kind of method that can be effectively identified certificate.

In order to solve the above technical problems, this specification one or more embodiment is achieved in that

On the one hand, this specification one or more embodiment provides a kind of certificate identification method, comprising:

It obtains in the case where setting lighting condition to the first image of document photography to be identified, wherein the first image includes The image of the certificate to be identified；

Spot detection is carried out to the first image；

If spot detection result meets preset hot spot existence condition, the peripheral region of the hot spot detected is examined The detection of mapping sample；

According to the material information of the certificate to be identified and the testing result of detection pattern, the certificate to be identified is carried out Identification.

Optionally, the material information according to the certificate to be identified and detect the testing result of pattern, to it is described to Identification certificate is identified, comprising:

If the material of the certificate to be identified be first kind material, and it is described detection pattern testing result do not meet it is default Detection pattern existence condition, it is determined that the certificate to be identified be forged certificate；Wherein, the certificate of the first kind material exists Captured image under the setting lighting condition, spot detection result meets the preset hot spot existence condition, and examines The testing result of mapping sample meets the preset detection pattern existence condition；

If the material of the certificate to be identified be the second class material, and it is described detection pattern testing result meet it is preset Detect pattern existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, the certificate of the second class material is in institute Image captured under setting lighting condition is stated, spot detection result meets the preset hot spot existence condition, and detects The testing result of pattern does not meet the preset detection pattern existence condition.

Optionally, described to include: to the first image progress spot detection

Gray level image is converted by the first image；

Based on a gray threshold, the largest connected domain in the gray level image is obtained；

Judge whether the pixel quantity in the largest connected domain is greater than preset quantity；

The spot detection result of the first image is determined according to the judging result.

Optionally, described to include: to the first image progress spot detection

The first image is aligned template with pre-set certificate to be aligned；

The image of the certificate to be identified is intercepted in the first image of alignment；

The image of the certificate to be identified is converted into gray level image；

Optionally, the spot detection result that the first image is determined according to the judging result includes:

If the pixel quantity in the largest connected domain is greater than preset quantity, it is determined that the spot detection knot of the first image Fruit meets preset hot spot existence condition, and the largest connected domain is the hot spot detected；

If the pixel quantity in the largest connected domain is not more than preset quantity, it is determined that the first image does not meet default Hot spot existence condition.

Optionally, described to be based on a gray threshold, the largest connected domain obtained in the gray level image includes:

The brightness of the gray level image is adjusted, so that the brightness of the gray level image meets predetermined luminance requirement；

Based on a gray threshold, the largest connected domain in the gray level image after adjusting brightness is obtained.

Optionally, the peripheral region of the described pair of hot spot detected carry out detection pattern detection include:

The detection pattern classification device obtained based on one by deep learning network training, the peripheral region to the hot spot detected Carry out the detection of detection pattern.

On the other hand, this specification one or more embodiment provides a kind of certificate identification apparatus, comprising:

Module is obtained, for obtaining the first image in the case where setting lighting condition to document photography to be identified, wherein described First image includes the image of the certificate to be identified；

Spot detection module, for carrying out spot detection to the first image；

Pattern detection module is detected, if meeting preset hot spot existence condition for spot detection result, to detecting Hot spot peripheral region carry out detection pattern detection；

Module is identified, for according to the material information of the certificate to be identified and detecting the testing result of pattern, to described Certificate to be identified is identified.

Optionally, the identification module, comprising:

First determination unit, if the material for the certificate to be identified is first kind material, and the detection pattern Testing result does not meet preset detection pattern existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, described The certificate of first kind material image captured under the setting lighting condition, spot detection result meets described preset Hot spot existence condition, and the testing result for detecting pattern meets the preset detection pattern existence condition；

Second determination unit, if the material for the certificate to be identified is the second class material, and the detection pattern Testing result meets preset detection pattern existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, described The certificate of two class materials image captured under the setting lighting condition, spot detection result meet the preset light Spot existence condition, and the testing result for detecting pattern does not meet the preset detection pattern existence condition.

Optionally, the spot detection module includes:

Conversion unit, for converting gray level image for the first image；

Acquiring unit obtains the largest connected domain in the gray level image for being based on a gray threshold；

Judging unit, for judging whether the pixel quantity in the largest connected domain is greater than preset quantity；

Determination unit, for determining the spot detection result of the first image according to the judging result.

Optionally, the spot detection module includes:

Alignment unit is aligned for the first image to be aligned template with pre-set certificate；

Interception unit, for intercepting the image of the certificate to be identified in the first image of alignment；

Conversion unit, for the image of the certificate to be identified to be converted to gray level image；

Optionally, the determination unit includes:

First determines subelement, if the pixel quantity for the largest connected domain is greater than preset quantity, it is determined that described The spot detection result of first image meets preset hot spot existence condition, and the largest connected domain is the hot spot detected；

Second determines subelement, if the pixel quantity for the largest connected domain is not more than preset quantity, it is determined that institute It states the first image and does not meet preset hot spot existence condition.

Optionally, the acquiring unit includes:

Regulator unit, for adjusting the brightness of the gray level image so that the brightness of the gray level image meet it is default Brightness requirement；

Subelement is obtained, for being based on a gray threshold, obtains the most Dalian in the gray level image after adjusting brightness Logical domain.

Optionally, the detection pattern detection module exists if meeting preset hot spot specifically for spot detection result Condition, then the detection pattern classification device obtained based on one by deep learning network training, the peripheral region to the hot spot detected Carry out the detection of detection pattern.

In another aspect, this specification one or more embodiment provides a kind of certificate evaluation apparatus, comprising:

Processor；And

It is arranged to the memory of storage computer executable instructions, the computer executable instructions make when executed The processor:

Spot detection is carried out to the first image；

In another aspect, this specification one or more embodiment provides a kind of storage medium, can be held for storing computer Row instruction, the computer executable instructions realize following below scheme when executed:

Spot detection is carried out to the first image；

Using the technical solution of this specification one or more embodiment, by the case where setting lighting condition to be identified First image of document photography carries out spot detection, and when spot detection result meets default hot spot and exists, to detecting Hot spot peripheral region carry out detection pattern detection, and according to detection pattern testing result and certificate to be identified material Matter information identifies certificate to be identified.On the one hand, a kind of mode for identifying certificate to be identified is provided, and step is simply easy In execution；It on the other hand, only only can be right in such a way that spot detection identifies certificate due in the related art Papery is duplicated this forgery means and is identified, can not recognition screen reproduction, copper sheet printing etc. forge means, and the present embodiment By way of combining spot detection and the detection mode of the detection pattern of the peripheral region of hot spot, it can identify that a variety of certificates are pseudo- Means are made, and then improve the accuracy rate of certificate identification, so as to effectively identify certificate.

Detailed description of the invention

In order to illustrate more clearly of this specification one or more embodiment or technical solution in the prior art, below will A brief introduction will be made to the drawings that need to be used in the embodiment or the description of the prior art, it should be apparent that, it is described below Attached drawing is only some embodiments recorded in this specification one or more embodiment, and those of ordinary skill in the art are come It says, without any creative labor, is also possible to obtain other drawings based on these drawings.

Fig. 1 is the flow diagram one for the certificate identification method that this specification embodiment provides；

Fig. 2 is the flow diagram one that spot detection is carried out to the first image that this specification embodiment provides；

Fig. 3 is the flow diagram two that spot detection is carried out to the first image that this specification embodiment provides；

Fig. 4 is the flow diagram three that spot detection is carried out to the first image that this specification embodiment provides；

Fig. 5 is the flow diagram four that spot detection is carried out to the first image that this specification embodiment provides；

Fig. 6 is the composition schematic diagram for the certificate identification apparatus that this specification embodiment provides；

Fig. 7 is the structural schematic diagram for the certificate evaluation apparatus that this specification embodiment provides.

Specific embodiment

This specification one or more embodiment provides a kind of certificate identification method and device, equipment and storage medium, uses To provide a kind of method that can be effectively identified certificate.

In order to make those skilled in the art more fully understand the technical solution in this specification one or more embodiment, Below in conjunction with the attached drawing in this specification one or more embodiment, to the technology in this specification one or more embodiment Scheme is clearly and completely described, it is clear that and described embodiment is only this specification a part of the embodiment, rather than Whole embodiments.Based on this specification one or more embodiment, those of ordinary skill in the art are not making creativeness The model of this specification one or more embodiment protection all should belong in every other embodiment obtained under the premise of labour It encloses.

This specification embodiment provides a kind of certificate identification method, and the executing subject of the certificate identification method for example can be with Be independent a server, or the server cluster being made of multiple servers, the present exemplary embodiment to this not Do particular determination.Fig. 1 is the flow diagram one for the certificate identification method that this specification embodiment provides, as shown in Figure 1, the party Method may comprise steps of:

Step S102, it obtains in the case where setting lighting condition to the first image of document photography to be identified, wherein the first image Image including certificate to be identified.

In this specification embodiment, setting lighting condition can refer to that under the conditions of flash lamp illumination, the flash lamp can be with For the flash lamp carried on terminal device, it can also be independent flash lamp, the present exemplary embodiment does not do particular determination to this. Specifically, user can by the camera in terminal device (such as mobile phone, tablet computer), and open flash lamp condition Under to the first image of document photography to be identified；User can also be by the camera of camera and under conditions of opening flash lamp To first image of document photography to be identified etc., this specification embodiment does not do particular determination to this.The certificate identification method is held Row main body it is available under conditions of flash lamp is taken pictures to the first image of document photography to be identified.It should be noted that should First image includes the image of certificate to be identified.

Certificate to be identified can be identity card, academic certificate, diploma etc., and it is special that this specification embodiment does not do this It limits.

Step S104, spot detection is carried out to the first image.

In this specification embodiment, spot detection can be carried out to the first image by following four mode, in which:

Mode one: Fig. 2 is the flow diagram one that spot detection is carried out to the first image that this specification embodiment provides. As shown in Fig. 2, may comprise steps of:

Step S202, gray level image is converted by the first image.Specifically, image processing operations can be used the first figure As being converted into gray level image.

Step S204, it is based on a gray threshold, obtains the largest connected domain in gray level image.

In this specification embodiment, it is possible, firstly, to the gray value of each pixel in gray level image be obtained, by each picture The gray value of element is compared with gray threshold, and the pixel that gray value in gray level image is greater than gray threshold is determined as target Pixel；Then, Connected area disposal$ is carried out to the object pixel in gray level image, to obtain at least one connected domain and near The maximum connected domain of area is determined as largest connected domain in a few connected domain.It should be noted that the numerical value of the gray threshold It can rule of thumb be arranged, or be obtained by experiment, the present exemplary embodiment does not do particular determination to this.

By taking the maximum connected domain of area, hot spot noise can be removed, to increase the accuracy of certificate identification.

Step S206, judge whether the pixel quantity in largest connected domain is greater than preset quantity.Obtain largest connected domain Pixel quantity, and the pixel quantity in largest connected domain is compared with preset quantity, the preset quantity can be according to testing It arrives, the present exemplary embodiment does not do particular determination to this.

Step S208, the spot detection result of the first image is determined according to judging result.Specifically, if largest connected domain Pixel quantity is greater than preset quantity, it is determined that the spot detection result of the first image meets preset hot spot existence condition, and should Largest connected domain is the hot spot detected；If the pixel quantity in largest connected domain is not more than preset quantity, it is determined that the first image Preset hot spot existence condition is not met.In the present specification, the foundation for setting hot spot existence condition can be according to specific application Scene and specific requirements are adjusted, such as to Mr. Yu's class certificate, and in the case where the first illumination condition is shot, are then set The foundation of hot spot existence condition can be more than first threshold for the number of laser image spot element, to another kind of certificate, and in second of light It is shot according under the conditions of, then the foundation of the hot spot existence condition set can be more than second threshold for the number of laser image spot element. Hot spot existence condition can be adjusted according to the feedback of detection environment and testing result, so as to be detected based on the condition Testing result it is more acurrate.

Mode two: Fig. 3 is the flow diagram two that spot detection is carried out to the first image that this specification embodiment provides. As shown in figure 3, may comprise steps of:

Step S302, gray level image is converted by the first image.Since the step has been explained above, because This is not being repeated herein.

Step S304, the brightness for adjusting gray level image, so that the brightness of gray level image meets predetermined luminance requirement.

In this specification embodiment, the range of the gray value of pixel is 0~255, and gray value is bigger, and the pixel is brighter, Gray value is smaller, and the pixel is darker.Based on this, the process for adjusting the brightness of gray level image may include: in search gray level image The gray value of each pixel, to obtain the maximum pixel of gray value.Judge the maximum pixel of the gray value gray value whether be 255, if so, being not required to be adjusted the brightness of gray level image；If it is not, then equal proportion adjusts each of whole gray level image The gray value of pixel, so that the gray value of the maximum pixel of gray value is 255.Predetermined luminance requires after can referring to adjustment brightness The gray value of the maximum pixel of gray value in gray level image is 255.

By the brightness of adjusting gray level image, predetermined luminance requirement can not be met to avoid the brightness due to gray level image, And lead to the phenomenon that can not find hot spot generation.

Step S306, it is based on a gray threshold, obtains the largest connected domain in the gray level image after adjusting brightness.In this theory In bright book embodiment, since the realization principle of step S206 is identical as the realization principle of step S204, no longer carry out herein It repeats.

Step S308, judge whether the pixel quantity in largest connected domain is greater than preset quantity.The step is hereinbefore It is illustrated, therefore is no longer repeated herein.

Step S310, the spot detection result of the first image is determined according to judging result.The step hereinbefore into It has gone explanation, therefore has no longer been repeated herein.

Mode three: Fig. 4 is the flow diagram three that spot detection is carried out to the first image that this specification embodiment provides. As shown in figure 4, may comprise steps of:

Step S402, the first image template is aligned with pre-set certificate to be aligned.

In this specification embodiment, it is possible, firstly, to the certificate alignment template of every kind of certificate is preset, then, according to The type of certificate to be identified selects corresponding certificate alignment template from the certificate of the certificate pre-set alignment template；Most Afterwards, by the matched picture alignment algorithm of SIFT feature, the first image is aligned template with the certificate of selection and is aligned.

Step S404, the image of certificate to be identified is intercepted in the first image of alignment.In this specification embodiment, by Not only include the image of certificate to be identified in the first image, further includes background image, since background image is there may be noise, These noises may influence whether the accuracy rate of identification, therefore, in order to further increase the accuracy rate of certificate identification, need right The image of certificate to be identified is intercepted in the first neat image, to carry out subsequent processing according to the image of certificate to be identified.

Step S406, the image of certificate to be identified is converted into gray level image.It can use image processing operations will be wait reflect The image for determining certificate is converted into gray level image.

Step S408, it is based on a gray threshold, obtains the largest connected domain in gray level image.Since the realization of the step is former Reason is identical as the realization principle of step S204, therefore details are not described herein again.

Step S410, judge whether the pixel quantity in largest connected domain is greater than preset quantity.Due to the realization of step S410 Principle has been explained above, therefore is no longer repeated herein.

Step S412, the spot detection result of the first image is determined according to judging result.Specifically, if largest connected domain Pixel quantity is greater than preset quantity, it is determined that the spot detection result of the first image meets preset hot spot existence condition, and should Largest connected domain is the hot spot detected；If the pixel quantity in largest connected domain is not more than preset quantity, it is determined that the first image Preset hot spot existence condition is not met.

Mode four: Fig. 5 is the flow diagram four that spot detection is carried out to the first image that this specification embodiment provides. As shown in figure 5, may comprise steps of:

Step S502, the first image template is aligned with pre-set certificate to be aligned.Due to the realization of the step Principle has been explained above, therefore is no longer repeated herein.

Step S504, the image of certificate to be identified is intercepted in the first image of alignment.Due to the realization principle of the step It has been be explained above that, therefore details are not described herein again.

Step S506, the image of certificate to be identified is converted into gray level image.Since the realization principle of the step has existed It is above illustrated, therefore details are not described herein again.

Step S508, the brightness for adjusting gray level image, so that the brightness of gray level image meets predetermined luminance requirement.Due to this The principle of step has been explained above, therefore details are not described herein again.

Step S510, it is based on a gray threshold, obtains the largest connected domain in the gray level image after adjusting brightness.Due to this The realization principle of step has been explained above, therefore is no longer repeated herein.

Step S512, judge whether the pixel quantity in largest connected domain is greater than preset quantity.Since the realization of the step is former Reason is hereinbefore illustrated, therefore details are not described herein again.

Step S514, the spot detection result of the first image is determined according to judging result.Due to the realization principle of the step It is hereinbefore illustrated, therefore details are not described herein again.

If step S106, spot detection result meets preset hot spot existence condition, around the hot spot detected Region carries out the detection of detection pattern.

Wherein, the detection mode of the detection pattern in this specification embodiment includes the detection mode of various optical effects, Such as spiral lamination detection or the detection of other optical effects, such as ripple detection.The detection side of specific detection pattern Formula can be determined that details are not described herein according to the had optical characteristics of type of specific application scenarios and certificate to be identified. Below to detect pattern as spiral lamination, the detection mode for detecting pattern is to be illustrated for spiral lamination detects.It can think It arrives, the technical concept based on the program also can be suitably used for the detection of other optical effects.

In this specification embodiment, if spot detection result does not meet preset hot spot existence condition, i.e., according to above-mentioned Mode determines in the first image there is no hot spot, it is determined that certificate to be identified is forged certificate, if spot detection result meet it is pre- If hot spot existence condition, i.e., determine that there are hot spots in the first image according to aforesaid way, then to the hot spot detected around Region carries out spiral lamination detection, it should be noted that the hot spot detected is the maximum that above-mentioned pixel quantity is greater than preset quantity Connected domain.Specifically, the spiral lamination classifier that can be obtained based on one by deep learning network training, to the hot spot detected Peripheral region carries out spiral lamination detection.In the following, being illustrated to the building process of spiral lamination classifier.

Firstly, obtaining training sample, training sample is to intercept from the various certificate images obtained under setting lighting condition Spot area, which includes the peripheral region of hot spot and hot spot, it should be noted that spot area be various cards Pixel quantity in part image is greater than the largest connected domain of preset quantity and the peripheral region in largest connected domain, wherein training sample This includes two classes, there are spiral lamination in the peripheral region of the hot spot in one kind, is not present in the peripheral region of the hot spot in one kind Spiral lamination；

Then, spiral lamination label is carried out to each training sample, it can mark in the training sample there are spiral lamination Spiral lamination out, it is marked in the training sample there is no spiral lamination, and there is no spiral laminations.

It is trained finally, the training sample marked is input in deep learning network, to obtain spiral lamination classification Device.The deep learning network can be for example CNN (convolutional neural networks) model etc., and it is special that the present exemplary embodiment does not do this It limits.

It may include: the hot spot that interception detects to the process that the peripheral region of the hot spot detected carries out spiral lamination detection And its peripheral region, that is, largest connected domain and its peripheral region are intercepted, the hot spot of interception and its peripheral region are input to spiral In line classifier, spiral lamination classifier, which can export the hot spot peripheral region, whether there is the result of spiral lamination.Specifically, if spiral The result of line classifier output is that there are spiral laminations for the hot spot peripheral region, it is determined that spiral lamination testing result meets preset spiral shell Lira existence condition, if the result of spiral lamination classifier output is that spiral lamination is not present in the hot spot peripheral region, it is determined that spiral Line testing result does not meet spiral lamination existence condition.

Step S108, according to the material information of certificate to be identified and detect pattern testing result, to certificate to be identified into Row identification.

In this specification embodiment, for the detection mode to detect pattern is spiral lamination detection, hot spot peripheral region It is determined with the presence or absence of spiral lamination by the material of certificate, that is, is directed to the certificate of part material, to certificate under to setting lighting condition When the peripheral region of the hot spot detected in the image of shooting carries out spiral lamination detection, spiral lamination testing result meets preset spiral shell Lira existence condition, that is, there are spiral laminations for the hot spot peripheral region in the image of the certificate shot；For another part material Certificate, when the hot spot detected in image to document photography under to setting lighting condition carries out spiral lamination detection, spiral shell Lira testing result does not meet preset spiral lamination existence condition, that is, in the hot spot peripheral region in the image of the certificate shot not There are spiral laminations.Based on this, can in advance the certificate to every kind of material hot spot peripheral region carry out spiral lamination detection, Yi Jigen According to the spiral lamination testing result of the certificate of every kind of material, the material of certificate is divided into first kind material and the second class material, In, the certificate of the first kind material image captured in the case where setting lighting condition, spot detection result meets preset hot spot Existence condition, and spiral lamination testing result meets preset spiral lamination existence condition, that is, there are light in the image of the certificate shot Spot and there are spiral laminations for hot spot peripheral region；The certificate of the second class material image captured in the case where setting lighting condition, light Spot testing result meets preset hot spot existence condition, and spiral lamination testing result does not meet preset spiral lamination existence condition, There are hot spot but spiral lamination is not present in hot spot peripheral region in the image of the certificate shot.

Certificate to be identified is identified according to the material information of certificate to be identified and spiral lamination testing result based on this Process may include:

It is possible, firstly, in conjunction with above-mentioned ready-portioned first kind material and the second class material in advance and according to certificate to be identified Material information determines that the material of the certificate to be identified is first kind material or the second class material；

Then, if the material of certificate to be identified is first kind material, and spiral lamination testing result does not meet preset spiral Line existence condition, it is determined that certificate to be identified is forged certificate；If the material of certificate to be identified is first kind material, and spiral lamination Testing result meets preset spiral lamination existence condition, it is determined that certificate to be identified is real docu-ment；For more accurate identification Certificate to be identified, if the material of certificate to be identified is first kind material, and spiral lamination testing result meets preset spiral lamination and deposits In condition, then other identification of means can also be combined further to identify certificate to be identified on this basis.

If the material of certificate to be identified is the second class material, and spiral lamination testing result meets preset spiral lamination there are items Part, it is determined that certificate to be identified is forged certificate；If the material of certificate to be identified is the second class material, and spiral lamination testing result Preset spiral lamination existence condition is not met, it is determined that the certificate to be identified is real docu-ment；In order to it is more accurate identification to Identify certificate, if the material of certificate to be identified is the second class material, and spiral lamination testing result does not meet preset spiral lamination and deposits In condition, then other identification of means can also be combined further to identify certificate to be identified on this basis.

In conclusion providing a kind of mode for identifying certificate to be identified, and step is simply easy to carry out；In addition, due to In the related art, only only this forgery means can be duplicated to papery in such a way that spot detection identifies certificate Identified, can not recognition screen reproduction, copper sheet printing etc. forge means, and the present embodiment pass through combine spot detection side The detection mode of the spiral lamination of the peripheral region of formula and hot spot can identify that papery duplicating, screen reproduction, copper sheet printing etc. are forged Means, and then the accuracy rate of certificate identification is improved, so as to effectively identify certificate.

Corresponding above-mentioned certificate identification method, based on the same technical idea, this specification embodiment additionally provides a kind of card Part identification apparatus, Fig. 6 are the composition schematic diagram for the certificate identification apparatus that this specification embodiment provides, and the device is for executing Certificate identification method is stated, as described in Figure 6, which may include: to obtain module 601, spot detection module 602, detection figure Sample detection module 603, identification module 604, in which:

Module 601 is obtained, for obtaining the first image in the case where setting lighting condition to document photography to be identified, wherein The first image includes the image of the certificate to be identified；

Spot detection module 602, for carrying out spot detection to the first image；

Pattern detection module 603 is detected, if meeting preset hot spot existence condition for spot detection result, to detection To hot spot peripheral region carry out detection pattern detection；

Module 604 is identified, for according to the material information of the certificate to be identified and detecting the testing result of pattern, to institute Certificate to be identified is stated to be identified.

Optionally, the identification module 604, comprising:

Optionally, the spot detection module 602 includes:

Conversion unit, for converting gray level image for the first image；

Optionally, the spot detection module 602 includes:

Optionally, the determination unit includes:

Optionally, the acquiring unit includes:

Optionally, the detection pattern detection module 603, is deposited if meeting preset hot spot specifically for spot detection result In condition, then the detection pattern classification device obtained based on one by deep learning network training, the peripheral region to the hot spot detected Domain carries out the detection of detection pattern.

Certificate identification apparatus in this specification embodiment provides a kind of mode for identifying certificate to be identified, and step It is simple easy to carry out；It, only only can be in such a way that spot detection identifies certificate in addition, due in the related art This forgery means are duplicated to papery to identify, can not recognition screen reproduction, copper sheet printing etc. forge means, and this implementation Example can identify that papery is multiple by way of combining spot detection and the detection mode of the detection pattern of the peripheral region of hot spot Means are forged in print, screen reproduction, copper sheet printing etc., and then improve the accuracy rate of certificate identification, so as to effectively verify Part is identified.

Corresponding above-mentioned certificate identification method, based on the same technical idea, this specification embodiment additionally provides a kind of card Part evaluation apparatus, Fig. 7 are the structural schematic diagram for the certificate evaluation apparatus that this specification embodiment provides, and the equipment is for executing The certificate identification method stated.

As shown in fig. 7, certificate evaluation apparatus can generate bigger difference because configuration or performance are different, it may include one A or more than one processor 701 and memory 702 can store one or more storages in memory 702 and answered With program or data.Wherein, memory 702 can be of short duration storage or persistent storage.It is stored in the application program of memory 702 It may include one or more modules (diagram is not shown), each module may include to the system in certificate evaluation apparatus Column count machine executable instruction.Further, processor 701 can be set to communicate with memory 702, set in certificate identification Series of computation machine executable instruction in standby upper execution memory 702.Certificate evaluation apparatus can also include one or one The above power supply 703, one or more wired or wireless network interfaces 704, one or more input/output interfaces 705, one or more keyboards 706 etc..

In a specific embodiment, certificate evaluation apparatus includes memory and one or more journey Sequence, perhaps more than one program is stored in memory and one or more than one program may include one for one of them Or more than one module, and each module may include the series of computation machine executable instruction in certificate evaluation apparatus, and pass through Configuration includes for carrying out following calculate to execute this or more than one program by one or more than one processor Machine executable instruction:

Spot detection is carried out to the first image；

Optionally, computer executable instructions when executed, the material information according to the certificate to be identified and The testing result for detecting pattern, identifies the certificate to be identified, comprising:

If the material of the certificate to be identified is the second class material, and the detection pattern testing result meets preset inspection Mapping sample existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, the certificate of the second class material is described Image captured under lighting condition is set, spot detection result meets the preset hot spot existence condition, and detects figure The testing result of sample does not meet the preset detection pattern existence condition.

Optionally, computer executable instructions are when executed, described to include: to the first image progress spot detection

Gray level image is converted by the first image；

The first image is aligned template with pre-set certificate to be aligned；

Optionally, computer executable instructions are when executed, described to determine first figure according to the judging result The spot detection result of picture includes:

Optionally, computer executable instructions are when executed, described to be based on a gray threshold, obtain the gray level image In largest connected domain include:

Optionally, computer executable instructions when executed, examine by the peripheral region of the described pair of hot spot detected The detection of mapping sample includes:

Certificate evaluation apparatus in this specification embodiment provides a kind of mode for identifying certificate to be identified, and step It is simple easy to carry out；It, only only can be in such a way that spot detection identifies certificate in addition, due in the related art This forgery means are duplicated to papery to identify, can not recognition screen reproduction, copper sheet printing etc. forge means, and this implementation Example can identify that papery is multiple by way of combining spot detection and the detection mode of the detection pattern of the peripheral region of hot spot Means are forged in print, screen reproduction, copper sheet printing etc., and then improve the accuracy rate of certificate identification, so as to effectively verify Part is identified.

Corresponding above-mentioned certificate identification method, based on the same technical idea, this specification embodiment additionally provides one kind and deposits Storage media, for storing computer executable instructions.

In a specific embodiment, which can store for USB flash disk, CD, hard disk etc., the storage medium Computer executable instructions are able to achieve following below scheme when being executed by processor:

Spot detection is carried out to the first image；

Optionally, the computer executable instructions of storage medium storage are described according to when being executed by processor The material information of certificate to be identified and the testing result for detecting pattern, identify the certificate to be identified, comprising:

Optionally, the computer executable instructions of storage medium storage are described to described the when being executed by processor One image carries out spot detection

Gray level image is converted by the first image；

The first image is aligned template with pre-set certificate to be aligned；

Optionally, the computer executable instructions of storage medium storage are described according to when being executed by processor Judging result determines that the spot detection result of the first image includes:

Optionally, the computer executable instructions of storage medium storage are described to be based on an ash when being executed by processor Threshold value is spent, the largest connected domain obtained in the gray level image includes:

Optionally, when being executed by processor, described pair detects the computer executable instructions of storage medium storage Hot spot peripheral region carry out detection pattern detection include:

The computer executable instructions of storage medium storage in this specification embodiment are provided when being executed by processor A kind of mode that identifying certificate to be identified, and step is simply easy to carry out；In addition, only passing through light due in the related art The mode that certificate is identified in spot detection only can duplicate this forgery means to papery and identify, can not identify screen Means are forged in curtain reproduction, copper sheet printing etc., and the present embodiment is by way of combining spot detection and the peripheral region of hot spot The detection mode for detecting pattern can identify the forgeries means such as papery duplicating, screen reproduction, copper sheet printing, and then improve card The accuracy rate of part identification, so as to effectively identify certificate.

In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example, Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit. Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device (Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development, And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language (Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL (Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL (Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages, The hardware circuit for realizing the logical method process can be readily available.

Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit, ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc. Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions For either the software module of implementation method can be the structure in hardware component again.

System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity, Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment The combination of equipment.

For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this The function of each unit can be realized in the same or multiple software and or hardware when specification.

It should be understood by those skilled in the art that, the embodiment of this specification can provide as method, system or computer journey Sequence product.Therefore, in terms of this specification can be used complete hardware embodiment, complete software embodiment or combine software and hardware Embodiment form.Moreover, it wherein includes computer usable program code that this specification, which can be used in one or more, The computer implemented in computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) The form of program product.

This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute In the dress for realizing the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram It sets.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.

In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net Network interface and memory.

Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium Example.

Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.

It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want There is also other identical elements in the process, method of element, commodity or equipment.

It will be understood by those skilled in the art that the embodiment of this specification can provide as the production of method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or implementation combining software and hardware aspects can be used in this specification The form of example.Moreover, it wherein includes the computer of computer usable program code that this specification, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.

This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects, Component, data structure etc..This specification can also be practiced in a distributed computing environment, in these distributed computing environment In, by executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module It can be located in the local and remote computer storage media including storage equipment.

All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part explanation.

The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.

Claims

1. a kind of certificate identification method, comprising:

It obtains in the case where setting lighting condition to the first image of document photography to be identified, wherein the first image includes described The image of certificate to be identified；

Spot detection is carried out to the first image；

If spot detection result meets preset hot spot existence condition, detection figure is carried out to the peripheral region of the hot spot detected The detection of sample；

According to the material information of the certificate to be identified and the testing result of detection pattern, reflect to the certificate to be identified It is fixed.

2. certificate identification method according to claim 1, the material information and detection according to the certificate to be identified The testing result of pattern identifies the certificate to be identified, comprising:

If the material of the certificate to be identified is first kind material, and the testing result of the detection pattern does not meet preset inspection Mapping sample existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, the certificate of the first kind material is described Image captured under lighting condition is set, spot detection result meets the preset hot spot existence condition, and detects figure The testing result of sample meets the preset detection pattern existence condition；

If the material of the certificate to be identified is the second class material, and the testing result of the detection pattern meets preset detection Pattern existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, the certificate of the second class material is set described Determine image captured under lighting condition, spot detection result meets the preset hot spot existence condition, and detects pattern Testing result do not meet the preset detection pattern existence condition.

3. certificate identification method according to claim 1, described to include: to the first image progress spot detection

Gray level image is converted by the first image；

4. certificate identification method according to claim 1, described to include: to the first image progress spot detection

The first image is aligned template with pre-set certificate to be aligned；

5. certificate identification method according to claim 3 or 4, described to determine the first image according to the judging result Spot detection result include:

If the pixel quantity in the largest connected domain is greater than preset quantity, it is determined that the spot detection result of the first image accords with Preset hot spot existence condition is closed, and the largest connected domain is the hot spot detected；

If the pixel quantity in the largest connected domain is not more than preset quantity, it is determined that the first image does not meet preset light Spot existence condition.

6. certificate identification method according to claim 3 or 4, described to be based on a gray threshold, the gray level image is obtained In largest connected domain include:

7. the peripheral region of certificate identification method according to claim 1, the described pair of hot spot detected carries out detection figure The detection of sample includes:

The detection pattern classification device obtained based on one by deep learning network training carries out the peripheral region of the hot spot detected Detect the detection of pattern.

8. the peripheral region of certificate identification method according to claim 1, the described pair of hot spot detected carries out detection figure The detection of sample includes:

Spiral lamination detection is carried out to the peripheral region of the hot spot detected.

9. a kind of certificate identification apparatus, comprising:

Spot detection module, for carrying out spot detection to the first image；

Pattern detection module is detected, if meeting preset hot spot existence condition for spot detection result, to the light detected The peripheral region of spot carries out the detection of detection pattern；

Module is identified, for according to the material information of the certificate to be identified and detecting the testing result of pattern, to described wait reflect Determine certificate to be identified.

10. certificate identification apparatus according to claim 9, the identification module, comprising:

First determination unit, if for the certificate to be identified material be first kind material, and it is described detection pattern detection As a result preset detection pattern existence condition is not met, it is determined that the certificate to be identified is forged certificate；Wherein, described first The certificate of class material image captured under the setting lighting condition, spot detection result meet the preset hot spot Existence condition, and the testing result for detecting pattern meets the preset detection pattern existence condition；

Second determination unit, if for the certificate to be identified material be the second class material, and it is described detection pattern detection As a result meet preset detection pattern existence condition, it is determined that the certificate to be identified is forged certificate；Wherein, second class The certificate of material image captured under the setting lighting condition, spot detection result meet the preset hot spot and deposit In condition, and the testing result for detecting pattern does not meet the preset detection pattern existence condition.

11. certificate identification apparatus according to claim 9, the spot detection module include:

Conversion unit, for converting gray level image for the first image；

12. certificate identification apparatus according to claim 9, the spot detection module include:

13. certificate identification apparatus according to claim 11 or 12, the determination unit include:

First determines subelement, if the pixel quantity for the largest connected domain is greater than preset quantity, it is determined that described first The spot detection result of image meets preset hot spot existence condition, and the largest connected domain is the hot spot detected；

Second determines subelement, if the pixel quantity for the largest connected domain is not more than preset quantity, it is determined that described the One image does not meet preset hot spot existence condition.

14. certificate identification apparatus according to claim 11 or 12, the acquiring unit include:

Regulator unit, for adjusting the brightness of the gray level image, so that the brightness of the gray level image meets predetermined luminance It is required that；

Subelement is obtained, for being based on a gray threshold, obtains the largest connected domain in the gray level image after adjusting brightness.

15. certificate identification apparatus according to claim 9, the detection pattern detection module are examined if being specifically used for hot spot It surveys result and meets preset hot spot existence condition, then the detection pattern classification device obtained based on one by deep learning network training, The detection of detection pattern is carried out to the peripheral region of the hot spot detected.

16. a kind of certificate evaluation apparatus, comprising:

Processor；And

It is arranged to the memory of storage computer executable instructions, the computer executable instructions make described when executed Processor:

Spot detection is carried out to the first image；

17. a kind of storage medium, for storing computer executable instructions, the computer executable instructions are real when executed Existing following below scheme:

Spot detection is carried out to the first image；