CN106778636A - Auth method and device - Google Patents

Auth method and device Download PDF

Info

Publication number
CN106778636A
CN106778636A CN201611201047.XA CN201611201047A CN106778636A CN 106778636 A CN106778636 A CN 106778636A CN 201611201047 A CN201611201047 A CN 201611201047A CN 106778636 A CN106778636 A CN 106778636A
Authority
CN
China
Prior art keywords
age
face characteristic
active user
mug shot
face
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201611201047.XA
Other languages
Chinese (zh)
Inventor
冯晓明
芦文龙
李阳
孙延飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Neusoft Corp
Original Assignee
Neusoft Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Neusoft Corp filed Critical Neusoft Corp
Priority to CN201611201047.XA priority Critical patent/CN106778636A/en
Publication of CN106778636A publication Critical patent/CN106778636A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • G06V40/169Holistic features and representations, i.e. based on the facial image taken as a whole
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The present invention proposes a kind of auth method and device, wherein, method includes:The first facial photo on identity card is obtained, first facial photo is processed using preset algorithm, extract the first face characteristic and the first age;Second mug shot of active user is gathered, the second mug shot is processed using preset algorithm, extract the second face characteristic data and the second age;The interval time between the first age and the second age is calculated, comparison threshold value corresponding with interval time is calculated by Principal Component Analysis Algorithm;First face characteristic is matched with the second face characteristic data, if compare knowing that matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.Whether the mug shot thereby, it is possible to the mug shot in accurate validation identity card and active user is same people, it is to avoid is not associative operation that I am carried out using identity card, improves the accuracy of face verification.

Description

Auth method and device
Technical field
The present invention relates to identity validation technology field, more particularly to a kind of auth method and device.
Background technology
Generally, identity card is used to prove unique certificate of holder's identity, used as everyone unique citizenship Proof instrument.In life, such as ride on a train, aircraft, hospital register, and are required for the checking to identity card to hold so as to verify The legitimacy of people's identity.
However, some people carry out associative operation using other people identity cards, make profit out of it.Such as, number dealer is using his person Part card has hung a large amount of numbers, and number high price being then suspended to is sold to patient in need, upsets the medical treatment order of hospital, damages patient Interests.Thus, it is desirable to a kind of mug shot that can prepare to verify mug shot and active user in identity card whether be The method of same people, so as to avoid it not being my associative operation for being carried out using identity card.
The content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the invention is to propose a kind of auth method, the method being capable of accurate validation body Whether the mug shot of mug shot and active user in part card be same people, it is to avoid is not that I is carried out using identity card Associative operation, improve the accuracy of face verification.
Second object of the present invention is to propose a kind of authentication means.
Third object of the present invention is to propose another authentication means.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
5th purpose of the invention is to propose a kind of computer program product.
It is that, up to above-mentioned purpose, first aspect present invention embodiment proposes a kind of auth method, including:
The first facial photo on identity card is obtained, the first facial photo is processed using preset algorithm, carried Take the first face characteristic and the first age;
Second mug shot of active user is gathered, second mug shot is processed using preset algorithm, carried Take the second face characteristic data and the second age;
Calculate the interval time between first age and second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value;
The first face characteristic is matched with the second face characteristic data, if compare knowing described It is more than the comparison threshold value with result, it is determined that the identity of active user has legitimacy.
The auth method of the embodiment of the present invention, by obtaining the first facial photo on identity card, using pre- imputation Method is processed first facial photo, is extracted the first face characteristic and the first age, and collection active user Second mug shot, is processed the second mug shot using preset algorithm, extracts the second face characteristic data and second At the age, the interval time between the first age and the second age is then calculated, when being calculated with interval by Principal Component Analysis Algorithm Between corresponding comparison threshold value, finally the first face characteristic is matched with the second face characteristic data, if compare knowing Matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.Thereby, it is possible in accurate validation identity card The mug shot of mug shot and active user whether be same people, it is to avoid be not correlation that I is carried out using identity card Operation, improves the accuracy of face verification.
In addition, auth method according to the above embodiment of the present invention can also have following additional technical characteristic:
In one embodiment of the invention, the application preset algorithm is processed the first facial photo, is carried The first face characteristic and the first age are taken, including:
Shape contour and position relationship according to facial image in the first facial photo are calculated by independent component analysis Method extracts the first face characteristic and the first age;
The application preset algorithm is processed second mug shot, extracts the second face characteristic data and the Two ages, including:
Shape contour and position relationship according to facial image in second mug shot are calculated by independent component analysis Method extracts the second face characteristic data and the second age.
In one embodiment of the invention, second mug shot of the collection active user, including:
If the face for detecting active user reaches predeterminable area, triggering positioning lamp is lighted, and prompting active user's is double Eye looks at the positioning lamp straight in Preset Time;
During the eyes of active user look at the positioning lamp straight, face inspection is carried out using Adaboost learning algorithms Survey, extract face rectangle feature and gather corresponding second mug shot.
In one embodiment of the invention, treatment is carried out to second mug shot in the application preset algorithm Before, also include:
Image pretreatment operation is carried out to second mug shot, wherein, described image pretreatment operation includes:Light Compensation, greyscale transformation, histogram equalization, one or more operative combinations in geometric correction.
In one embodiment of the invention, by the first face characteristic and the second face characteristic data After being matched, also include:
If compare knowing the matching result less than or equal to the comparison threshold value, the identity of alarm active user is not With legitimacy, and retain card treatment is carried out to the identity card.
It is that, up to above-mentioned purpose, second aspect present invention embodiment proposes a kind of authentication means, including:
Acquisition module, for obtaining the first facial photo on identity card;
First extraction module, is processed the first facial photo for application preset algorithm, extracts the first face Characteristic and the first age;
Acquisition module, the second mug shot for gathering active user;
Second extraction module, is processed second mug shot for application preset algorithm, extracts the second face Characteristic and the second age;
Computing module, for calculating the interval time between first age and second age, by principal component Parser calculates comparison threshold value corresponding with the interval time;
Processing module, for the first face characteristic to be matched with the second face characteristic data, Compare know the matching result be more than the comparison threshold value when, determining the identity of active user has legitimacy.
The authentication means of the embodiment of the present invention, by obtaining the first facial photo on identity card, using pre- imputation Method is processed first facial photo, is extracted the first face characteristic and the first age, and collection active user Second mug shot, is processed the second mug shot using preset algorithm, extracts the second face characteristic data and second At the age, the interval time between the first age and the second age is then calculated, when being calculated with interval by Principal Component Analysis Algorithm Between corresponding comparison threshold value, finally the first face characteristic is matched with the second face characteristic data, if compare knowing Matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.Thereby, it is possible in accurate validation identity card The mug shot of mug shot and active user whether be same people, it is to avoid be not correlation that I is carried out using identity card Operation, improves the accuracy of face verification.
In addition, authentication means according to the above embodiment of the present invention can also have following additional technical characteristic:
In one embodiment of the invention, the first extraction module is used for:According to face figure in the first facial photo The shape contour and position relationship of picture extract the first face characteristic and First Year by independent composition analysis algorithm Age;
Second extraction module is used for:Shape contour and position relationship according to facial image in second mug shot are led to Cross independent composition analysis algorithm and extract the second face characteristic data and the second age.
In one embodiment of the invention, the acquisition module is used for:If the face for detecting active user reaches pre- If during region, triggering positioning lamp is lighted, the eyes of active user are pointed out to look at the positioning lamp straight in Preset Time;
During the eyes of active user look at the positioning lamp straight, face inspection is carried out using Adaboost learning algorithms Survey, extract face rectangle feature and gather corresponding second mug shot.
In one embodiment of the invention, described device, also includes:Pretreatment module, for second face Portion's photo carries out image pretreatment operation, wherein, described image pretreatment operation includes:Light compensation, greyscale transformation, histogram Equalization, one or more operative combinations in geometric correction.
In one embodiment of the invention, the processing module is additionally operable to:Know that the matching result is less than comparing During equal to the comparison threshold value, the identity of alarm active user does not have legitimacy, and carries out retain card to the identity card Treatment.
It is that, up to above-mentioned purpose, third aspect present invention embodiment proposes another authentication means, including:Treatment Device;Memory for storing the processor-executable instruction;Wherein, the processor is configured as:
The first facial photo on identity card is obtained, the first facial photo is processed using preset algorithm, carried Take the first face characteristic and the first age;
Second mug shot of active user is gathered, second mug shot is processed using preset algorithm, carried Take the second face characteristic data and the second age;
Calculate the interval time between first age and second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value;
The first face characteristic is matched with the second face characteristic data, if compare knowing described It is more than the comparison threshold value with result, it is determined that the identity of active user has legitimacy.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of non-transitory computer-readable storage Medium, when the instruction in the storage medium is performed by the processor of server end so that server end is able to carry out one Auth method is planted, methods described includes:
The first facial photo on identity card is obtained, the first facial photo is processed using preset algorithm, carried Take the first face characteristic and the first age;
Second mug shot of active user is gathered, second mug shot is processed using preset algorithm, carried Take the second face characteristic data and the second age;
Calculate the interval time between first age and second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value;
The first face characteristic is matched with the second face characteristic data, if compare knowing described It is more than the comparison threshold value with result, it is determined that the identity of active user has legitimacy.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program product, when described When instruction processing unit in computer program product is performed, a kind of auth method is performed, methods described includes:
The first facial photo on identity card is obtained, the first facial photo is processed using preset algorithm, carried Take the first face characteristic and the first age;
Second mug shot of active user is gathered, second mug shot is processed using preset algorithm, carried Take the second face characteristic data and the second age;
Calculate the interval time between first age and second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value;
The first face characteristic is matched with the second face characteristic data, if compare knowing described It is more than the comparison threshold value with result, it is determined that the identity of active user has legitimacy.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description Obtain substantially, or recognized by practice of the invention.
Brief description of the drawings
The above-mentioned and/or additional aspect of the present invention and advantage will become from the following description of the accompanying drawings of embodiments Substantially and be readily appreciated that, wherein:
Fig. 1 is a kind of schematic flow sheet of auth method provided in an embodiment of the present invention;
Fig. 2 is the schematic flow sheet of another auth method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of authentication means provided in an embodiment of the present invention;
Fig. 4 is the structural representation of another authentication means provided in an embodiment of the present invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached It is exemplary to scheme the embodiment of description, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the auth method and device of the embodiment of the present invention described.
At present, there is number dealer in various big hospital to be registered using other people identity card reservations, number high price that then will be suspended to is sold To patient in need, the medical treatment order of hospital is upset, damage the interests of patient.
In order to control above-mentioned behavior, it is necessary to the mug shot in accurate validation identity card is with the mug shot of active user No is same people, improves the accuracy of face verification.The present invention proposes a kind of auth method.It is specific as follows:
Fig. 1 is a kind of schematic flow sheet of auth method provided in an embodiment of the present invention.
As shown in figure 1, the auth method is comprised the following steps:
Step 110, obtain identity card on first facial photo, using preset algorithm to first facial photo at Reason, extracts the first face characteristic and the first age.
Specifically, when user carries out a certain operation (buy train ticket, register) using identity card, the of identity card is obtained One mug shot.Wherein, the mode for obtaining the first facial photo of identity card has many kinds, can be selected according to actual needs Setting is selected, is illustrated below:
The first example, can obtain relevant information (name, the body of identity card by calling Ministry of Public Security's ID card information storehouse Mug shot when part demonstrate,proves number and handles identity card etc.).Thus, it is possible to obtain the mug shot of identity card as first facial Photo.
Second example, the mode such as can be directly scanned and is obtained by face recognition device to the photo on identity card The mug shot of identity card is taken as first facial photo.
Further, first facial photo is processed by preset algorithm, extract the first face characteristic and First age.In order to those skilled in the art more understand said process, illustrated by independent composition analysis algorithm of preset algorithm below It is described as follows:
Specifically, the shape contour and position relationship of facial image in first facial photo are obtained first, then by only Vertical constituent analysis algorithm estimates the first face characteristic and the first age.
Wherein, the first age estimated according to first facial photo.Wherein, the first face characteristic can be Visual signature, pixels statisticses feature, facial image conversion coefficient feature, facial image algebraic characteristic etc..
Step 120, gather active user the second mug shot, using preset algorithm to the second mug shot at Reason, extracts the second face characteristic data and the second age.
Specifically, when user carries out a certain operation (buy train ticket, register) using identity card, collection active user's Second mug shot, wherein, the mode for gathering second mug shot of active user has many kinds, can enter according to actual needs Row selection is set, and is illustrated below:
The first example, when the face for detecting active user reaches predeterminable area, triggering positioning lamp is lighted, and points out to work as The eyes of preceding user look at positioning lamp straight in Preset Time, and during the eyes direct-view positioning lamp of active user, application Adaboost learning algorithms carry out Face datection, extract face rectangle feature and gather corresponding second mug shot.
Wherein, the face entrance of predeterminable area be that what is pre-set can the be carried out region of face recognition, i.e. active user Represent that facial recognition modules can start collecting work in the predeterminable area.
Second example, by face recognition device, is directly identified to active user, searches the face of active user During portion, start collection face rectangle feature and gather corresponding mug shot as the second mug shot.
Further, the second mug shot is processed by preset algorithm, extract the second face characteristic data and Second age.In order to those skilled in the art more understand said process, illustrated by independent composition analysis algorithm of preset algorithm below It is described as follows:
Specifically, the shape contour and position relationship of facial image in the second mug shot are obtained first, then by only Vertical constituent analysis algorithm estimates the second face characteristic data and the second age.
Wherein, the second age estimated according to the second mug shot.Wherein, the second face characteristic data can be Visual signature, pixels statisticses feature, facial image conversion coefficient feature, facial image algebraic characteristic etc..
Step 130, calculates the interval time between the first age and the second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value.
Step 140, the first face characteristic is matched with the second face characteristic data, if compare knowing matching knot Fruit is more than comparison threshold value, it is determined that the identity of active user has legitimacy.
Specifically, the interval time between the first age and the second age is calculated, can subtract Second Year at the first age The absolute value of the difference in age subtracted as interval time, or the second age the absolute value of the difference at the first age as Every the time.
Further, by can dynamically adjust out the comparison threshold value of matching according to interval time.
It is understood that interval time is bigger, first facial photo is bigger with the gap of the second mug shot, corresponding Adjustment reduces comparison threshold value;Interval time is smaller, and first facial photo is smaller with the gap of the second mug shot, corresponding adjustment Improve comparison threshold value.It is illustrated below:
The first example, interval time is that A1 determines that the comparison threshold value of matching is A2 (being such as 8).Wherein, A1 is smaller It is such as 3 years, so can determine that first facial photo and the second mug shot gap are not very big, corresponding raising contrast thresholds It was 9 (being 10 to the maximum) to be worth.
Second example, interval time is that B1 determines that the comparison threshold value of matching is B2 (being such as 8).Wherein, B1 is than larger It is such as 20 years, so can determine that first facial photo with the second mug shot gap than larger, corresponding reduction contrast threshold It was 7 (being 10 to the maximum) to be worth.
It will also be appreciated that a time interval scope can be set, such as the comparison threshold value of 1 to 5 year is 9;6 to 10 The comparison threshold value in year is 8.5, and the comparison threshold value of 10 to 15 years is 8 etc..Thereby, it is possible to the face in more accurate validation identity card Whether portion's photo is same people with the mug shot of active user, further increases the accuracy of face verification.
Further, the first face characteristic is matched with the second face characteristic data, can be by default Algorithm is matched the first face characteristic with the second face characteristic data, it is also possible to by default face Matching Model First face characteristic is matched etc. with the second face characteristic data.
Further, matching result is compared with comparison threshold value, and is determined when matching result is more than comparison threshold value The identity of active user has legitimacy.
In sum, the auth method of the embodiment of the present invention, by obtaining the first facial photo on identity card, should First facial photo is processed with preset algorithm, is extracted the first face characteristic and the first age, and collection is worked as Second mug shot of preceding user, is processed the second mug shot using preset algorithm, extracts the second face characteristic data And second age, the interval time between the first age and the second age is then calculated, calculated by Principal Component Analysis Algorithm Comparison threshold value corresponding with interval time, is finally matched the first face characteristic with the second face characteristic data, if Compare and know that matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.Thereby, it is possible to accurate validation Whether mug shot in identity card is same people with the mug shot of active user, it is to avoid be not I is entered using identity card Capable associative operation, improves the accuracy of face verification.
Fig. 2 is the schematic flow sheet of another auth method provided in an embodiment of the present invention.
As shown in Fig. 2 the auth method is comprised the following steps:
Step 210, obtains the first facial photo on identity card, according to the shaped wheel of facial image in first facial photo Wide and position relationship extracts the first face characteristic and the first age by independent composition analysis algorithm.
Specifically, the mode for obtaining the first facial photo on identity card refers to the specific descriptions of step 110, herein not Describe in detail again.
Further, obtain first facial photo in facial image shape contour, and human face position relationship, By independent composition analysis algorithm process and obtain the first face characteristic and the corresponding First Year of first facial photo Age.
Step 220, if the face for detecting active user reaches predeterminable area, triggering positioning lamp is lighted, and is pointed out current The eyes of user look at positioning lamp straight in Preset Time.
Step 230, during the eyes direct-view positioning lamp of active user, pedestrian is entered using Adaboost learning algorithms Face detects, extracts face rectangle feature and gather corresponding second mug shot.
Specifically, active user is in the predeterminable area of collecting device, and collecting device can automatically be searched for and shoot current use The face-image at family.Thus, (i.e. during Face datection) can be with during the eyes direct-view locating pin of active user Accurate calibration goes out position and the size of face in the picture.The pattern feature very abundant included in face-image, such as histogram Feature, color characteristic, template characteristic, architectural feature and Haar features etc..
Further, Adaboost algorithm is a kind of method for classifying, and it can be some weaker classification sides Method is combined, and is combined into new very strong sorting technique.Picking out some using Adaboost algorithm can most represent face Face rectangle feature (Weak Classifier), a strong classifier is configured to according to the mode of Nearest Neighbor with Weighted Voting by Weak Classifier, then will instruction The some strong classifiers for getting are composed in series a cascade filtering for cascade structure, effectively improve the detection speed of grader Degree.So as to obtain the second mug shot closest to active user's time of day.
Step 240, image pretreatment operation is carried out to the second mug shot, wherein, image pretreatment operation includes:Light Compensation, greyscale transformation, histogram equalization, one or more operative combinations in geometric correction.
Specifically, it is based on above-mentioned Face datection result to carry out image pretreatment operation for the second mug shot.First The second mug shot for obtaining tends not to directly use, it is necessary to carrying due to being limited and random disturbances by various conditions Take the second face characteristic data and light compensation, greyscale transformation, histogram are carried out to the second mug shot before the second age Equalization, the medium image preprocessing of geometric correction.
Wherein it is possible to be needed to select above-mentioned light compensation, greyscale transformation, histogram equalization, geometry according to practical application One or more operative combinations in correction.
Step 250, the shape contour and position relationship according to facial image in the second mug shot are by independent element point Analysis algorithm extracts the second face characteristic data and the second age.
Specifically, the shape contour of facial image in the second mug shot carried out after pretreatment operation is obtained, and The position relationship of human face, by independent composition analysis algorithm process and obtains the second face characteristic data and the second face Portion's photo corresponding second age.
Step 260, calculates the interval time between the first age and the second age, by Principal Component Analysis Algorithm calculate with Interval time corresponding comparison threshold value.
Step 270, the first face characteristic is matched with the second face characteristic data, if compare knowing matching knot Fruit is more than comparison threshold value, it is determined that the identity of active user has legitimacy.
It should be noted that the description of step S260-S270 is corresponding with above-mentioned steps S130-S140, thus to step The description of rapid S260-S270 will not be repeated here with reference to the description of above-mentioned steps S130-S140.
Step 280, if compare knowing matching result less than or equal to comparison threshold value, the identity of alarm active user is not With legitimacy, and retain card treatment is carried out to identity card.
Specifically, matching result is compared with comparison threshold value, and the body when matching result is less than or equal to comparison threshold value Part card and its holder are not same persons, and the identity of alarm active user does not have legitimacy.Further, to identity Card carries out retain card treatment.
Wherein, the mode of alarm can have many kinds, such as by audio alert, or the end for being attached to administrative staff Vibrated in end equipment, the prompting such as voice, the user of currently used identity card is illegal, it is necessary to further confirm that treatment.
In sum, the auth method of the embodiment of the present invention, in the shape according to facial image in the second mug shot Shape profile and position relationship extract the second face characteristic data and before the second age by independent composition analysis algorithm, to the Two mug shots carry out image pretreatment operation, and compare and know matching result less than or equal to comparison threshold value, then alarm The identity of active user does not have legitimacy, and carries out retain card treatment to identity card.The accuracy of face verification is further improved, And can be to currently not conforming to judicial act carries out alarm and respective handling, more efficient avoiding be not to use identity card in person The associative operation for carrying out.
In order to realize above-described embodiment, the present invention also proposes a kind of authentication means.
Fig. 3 is a kind of structural representation of authentication means provided in an embodiment of the present invention.
As shown in figure 3, the authentication means include:Acquisition module 31, the first extraction module 32, acquisition module 33, Two extraction modules 34, computing module 35 and processing module 36.
Wherein, acquisition module 31 is used to obtain the first facial photo on identity card.
First extraction module 32 is processed first facial photo for application preset algorithm, extracts the first face characteristic Data and the first age.
Acquisition module 33 is used to gather second mug shot of active user.
Second extraction module 34 is processed the second mug shot for application preset algorithm, extracts the second face characteristic Data and the second age.
Computing module 35 is used to calculate the interval time between the first age and the second age, by Principal Component Analysis Algorithm Calculate comparison threshold value corresponding with interval time.
Processing module 36 is used to be matched the first face characteristic with the second face characteristic data, knows comparing When matching result is more than comparison threshold value, determining the identity of active user has legitimacy.
Wherein, in one embodiment of the invention, the first extraction module 32 is used for according to face in first facial photo The shape contour and position relationship of image extract the first face characteristic and the first age by independent composition analysis algorithm.
Wherein, in one embodiment of the invention, the second extraction module 34 is used for according to face in the second mug shot The shape contour and position relationship of image extract the second face characteristic data and the second age by independent composition analysis algorithm.
Wherein, in one embodiment of the invention, if acquisition module 33 is used to detect the face arrival of active user During predeterminable area, triggering positioning lamp is lighted, and points out the eyes of active user to look at positioning lamp straight in Preset Time;In active user Eyes direct-view positioning lamp during, carry out Face datection using Adaboost learning algorithms, extract face rectangle feature simultaneously Gather corresponding second mug shot.
It should be noted that the foregoing explanation to auth method embodiment is also applied for authentication means, Here is omitted.
In sum, the authentication means of the embodiment of the present invention, by obtaining the first facial photo on identity card, should First facial photo is processed with preset algorithm, is extracted the first face characteristic and the first age, and collection is worked as Second mug shot of preceding user, is processed the second mug shot using preset algorithm, extracts the second face characteristic data And second age, the interval time between the first age and the second age is then calculated, calculated by Principal Component Analysis Algorithm Comparison threshold value corresponding with interval time, is finally matched the first face characteristic with the second face characteristic data, if Compare and know that matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.Thereby, it is possible to accurate validation Whether mug shot in identity card is same people with the mug shot of active user, it is to avoid be not I is entered using identity card Capable associative operation, improves the accuracy of face verification.
For an embodiment in clear explanation, another authentication means are present embodiments provided.
The structural representation of another authentication means that Fig. 4 is provided for the present embodiment.
As shown in figure 4, on the basis of a upper embodiment, the device also includes:Pretreatment module 37.
Wherein, pretreatment module 37 is used to carry out image pretreatment operation to the second mug shot, wherein, image preprocessing Operation includes:Light compensation, greyscale transformation, histogram equalization, one or more operative combinations in geometric correction.
Wherein, in one embodiment of the invention, processing module 36 be additionally operable to compare know matching result less than etc. When comparison threshold value, the identity of alarm active user does not have legitimacy, and carries out retain card treatment to identity card.
It should be noted that the foregoing explanation to auth method embodiment is also applied for authentication means, Here is omitted.
In sum, the authentication means of the embodiment of the present invention, in the shape according to facial image in the second mug shot Shape profile and position relationship extract the second face characteristic data and before the second age by independent composition analysis algorithm, to the Two mug shots carry out image pretreatment operation, and compare and know matching result less than or equal to comparison threshold value, then alarm The identity of active user does not have legitimacy, and carries out retain card treatment to identity card.The accuracy of face verification is further improved, And can be to currently not conforming to judicial act carries out alarm and respective handling, more efficient avoiding be not to use identity card in person The associative operation for carrying out.
In order to realize above-described embodiment, the present invention also proposes another authentication means, including:Processor, Yi Jiyong In the memory for storing the processor-executable instruction.
Wherein, processor is configured as:The first facial photo on identity card is obtained, using preset algorithm to first facial Photo is processed, and extracts the first face characteristic and the first age;Gather second mug shot of active user, application Preset algorithm is processed the second mug shot, extracts the second face characteristic data and the second age;Calculated for the first age And the second interval time between the age, comparison threshold value corresponding with interval time is calculated by Principal Component Analysis Algorithm;By One face characteristic data are matched with the second face characteristic data, if compare knowing that matching result is more than comparison threshold value, really The identity for determining active user has legitimacy.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, when described When instruction in storage medium is performed by the processor of server end so that server end is able to carry out a kind of authentication side Method, methods described includes:Obtain identity card on first facial photo, using preset algorithm to first facial photo at Reason, extracts the first face characteristic and the first age;Second mug shot of active user is gathered, using preset algorithm pair Second mug shot is processed, and extracts the second face characteristic data and the second age;Calculate the first age and the second age Between interval time, corresponding with interval time comparison threshold value is calculated by Principal Component Analysis Algorithm;By the first face characteristic Data are matched with the second face characteristic data, if compare knowing that matching result is more than comparison threshold value, it is determined that active user Identity there is legitimacy.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when the computer program is produced When instruction processing unit in product is performed, a kind of auth method is performed, methods described includes:Obtain the first face on identity card Portion's photo, is processed first facial photo using preset algorithm, extracts the first face characteristic and the first age;Adopt Collect second mug shot of active user, the second mug shot is processed using preset algorithm, extract the second face characteristic Data and the second age;The interval time between the first age and the second age is calculated, is calculated by Principal Component Analysis Algorithm Comparison threshold value corresponding with interval time;First face characteristic is matched with the second face characteristic data, if comparing Know that matching result is more than comparison threshold value, it is determined that the identity of active user has legitimacy.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described Point is contained at least one embodiment of the invention or example.In this manual, to the schematic representation of above-mentioned term not Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office Combined in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area Art personnel can be tied the feature of the different embodiments or example described in this specification and different embodiments or example Close and combine.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or Implicitly include at least one this feature.In the description of the invention, " multiple " is meant that at least two, such as two, three It is individual etc., unless otherwise expressly limited specifically.
Any process described otherwise above or method description in flow chart or herein is construed as, and expression includes It is one or more for realizing custom logic function or process the step of the module of code of executable instruction, fragment or portion Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussion suitable Sequence, including function involved by basis by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention Embodiment person of ordinary skill in the field understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use In the order list of the executable instruction for realizing logic function, in may be embodied in any computer-readable medium, for Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction The system of row system, device or equipment instruction fetch and execute instruction) use, or with reference to these instruction execution systems, device or set It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass The dress that defeated program is used for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following:With the electricity that one or more are connected up Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage (ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can thereon print described program or other are suitable Medium, because optical scanner for example can be carried out by paper or other media, then enters edlin, interpretation or if necessary with it His suitable method is processed electronically to obtain described program, is then stored in computer storage.
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried The rapid hardware that can be by program to instruct correlation is completed, and described program can be stored in a kind of computer-readable storage medium In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, during each functional unit in each embodiment of the invention can be integrated in a processing module, it is also possible to It is that unit is individually physically present, it is also possible to which two or more units are integrated in a module.Above-mentioned integrated mould Block can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as Fruit is to realize in the form of software function module and as independent production marketing or when using, it is also possible to which storage is in a computer In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown above and retouching Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as to limit of the invention System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention Type.

Claims (10)

1. a kind of auth method, it is characterised in that comprise the following steps:
The first facial photo on identity card is obtained, the first facial photo is processed using preset algorithm, extract the One face characteristic data and the first age;
Second mug shot of active user is gathered, second mug shot is processed using preset algorithm, extract the Two face characteristic data and the second age;
Calculate the interval time between first age and second age, by Principal Component Analysis Algorithm calculate with it is described Interval time corresponding comparison threshold value
The first face characteristic is matched with the second face characteristic data, if compare knowing the matching knot Fruit is more than the comparison threshold value, it is determined that the identity of active user has legitimacy.
2. the method for claim 1, it is characterised in that
The application preset algorithm is processed the first facial photo, extracts the first face characteristic and First Year Age, including:
Shape contour and position relationship according to facial image in the first facial photo are carried by independent composition analysis algorithm Take the first face characteristic and the first age;
The application preset algorithm is processed second mug shot, extracts the second face characteristic data and Second Year Age, including:
Shape contour and position relationship according to facial image in second mug shot are carried by independent composition analysis algorithm Take the second face characteristic data and the second age.
3. the method for claim 1, it is characterised in that second mug shot of the collection active user, including:
If the face for detecting active user reaches predeterminable area, triggering positioning lamp is lighted, and points out the eyes of active user to exist The direct-view positioning lamp in Preset Time;
During the eyes of active user look at the positioning lamp straight, Face datection is carried out using Adaboost learning algorithms, Extract face rectangle feature and gather corresponding second mug shot.
4. the method for claim 1, it is characterised in that enter to second mug shot in the application preset algorithm Before row treatment, also include:
Image pretreatment operation is carried out to second mug shot, wherein, described image pretreatment operation includes:Light is mended Repay, greyscale transformation, histogram equalization, one or more operative combinations in geometric correction.
5. the method as described in claim any one of 1-4, it is characterised in that by the first face characteristic with it is described After second face characteristic data are matched, also include:
If compare knowing the matching result less than or equal to the comparison threshold value, the identity of alarm active user does not have Legitimacy, and retain card treatment is carried out to the identity card.
6. a kind of authentication means, it is characterised in that including:
Acquisition module, for obtaining the first facial photo on identity card;
First extraction module, is processed the first facial photo for application preset algorithm, extracts the first face characteristic Data and the first age;
Acquisition module, the second mug shot for gathering active user;
Second extraction module, is processed second mug shot for application preset algorithm, extracts the second face characteristic Data and the second age;
Computing module, for calculating the interval time between first age and second age, by principal component analysis Algorithm calculates comparison threshold value corresponding with the interval time;
Processing module, for the first face characteristic to be matched with the second face characteristic data, is comparing When knowing that the matching result is more than the comparison threshold value, determining the identity of active user has legitimacy.
7. device as claimed in claim 6, it is characterised in that
First extraction module is used for:
Shape contour and position relationship according to facial image in the first facial photo are carried by independent composition analysis algorithm Take the first face characteristic and the first age;
Second extraction module is used for:
Shape contour and position relationship according to facial image in second mug shot are carried by independent composition analysis algorithm Take the second face characteristic data and the second age.
8. device as claimed in claim 6, it is characterised in that the acquisition module is used for:
If the face for detecting active user reaches predeterminable area, triggering positioning lamp is lighted, and points out the eyes of active user to exist The direct-view positioning lamp in Preset Time;
During the eyes of active user look at the positioning lamp straight, Face datection is carried out using Adaboost learning algorithms, Extract face rectangle feature and gather corresponding second mug shot.
9. device as claimed in claim 6, it is characterised in that also include:
Pretreatment module, for carrying out image pretreatment operation to second mug shot, wherein, described image pretreatment behaviour Work includes:Light compensation, greyscale transformation, histogram equalization, one or more operative combinations in geometric correction.
10. the device as described in claim any one of 6-9, it is characterised in that the processing module is additionally operable to:
Compare know the matching result be less than or equal to the comparison threshold value when, the identity of alarm active user does not have Legitimacy, and retain card treatment is carried out to the identity card.
CN201611201047.XA 2016-12-22 2016-12-22 Auth method and device Pending CN106778636A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611201047.XA CN106778636A (en) 2016-12-22 2016-12-22 Auth method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611201047.XA CN106778636A (en) 2016-12-22 2016-12-22 Auth method and device

Publications (1)

Publication Number Publication Date
CN106778636A true CN106778636A (en) 2017-05-31

Family

ID=58897391

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611201047.XA Pending CN106778636A (en) 2016-12-22 2016-12-22 Auth method and device

Country Status (1)

Country Link
CN (1) CN106778636A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107977621A (en) * 2017-11-29 2018-05-01 淮海工学院 Shipwreck identification model construction method, device, electronic equipment and storage medium
CN109034004A (en) * 2018-07-05 2018-12-18 广东军缆信息技术有限公司 A kind of identity verification method and device based on recognition of face
CN109429519A (en) * 2017-06-30 2019-03-05 北京嘀嘀无限科技发展有限公司 System and method for verifying the authenticity of certificate photograph
CN109446772A (en) * 2018-09-03 2019-03-08 平安国际融资租赁有限公司 Accrediting amount calculation method, device, computer equipment and storage medium
CN109508705A (en) * 2018-12-29 2019-03-22 河北三川科技有限公司 The dynamic threshold face alignment setting method of identity-based card validity period
CN109670481A (en) * 2018-12-29 2019-04-23 河北三川科技有限公司 Dynamic threshold setting method is compared based on the testimony of a witness of age and gender
CN109685952A (en) * 2018-12-29 2019-04-26 河北三川科技有限公司 The face access control system and application method of identity-based information
CN111052131A (en) * 2017-09-28 2020-04-21 松下知识产权经营株式会社 Authentication device, authentication system, authentication method, and program
CN113316782A (en) * 2019-03-24 2021-08-27 苹果公司 Identity document verification

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104680131A (en) * 2015-01-29 2015-06-03 深圳云天励飞技术有限公司 Identity authentication method based on identity certificate information and human face multi-feature recognition
CN105138980A (en) * 2015-08-20 2015-12-09 深圳云天励飞技术有限公司 Identify authentication method and system based on identity card information and face identification
CN105227766A (en) * 2015-09-14 2016-01-06 惠州Tcl移动通信有限公司 A kind of anti-theft method for mobile terminal based on recognition of face, system and mobile terminal
CN105243357A (en) * 2015-09-15 2016-01-13 深圳市环阳通信息技术有限公司 Identity document-based face recognition method and face recognition device
CN106203294A (en) * 2016-06-30 2016-12-07 广东微模式软件股份有限公司 The testimony of a witness unification auth method analyzed based on face character

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104680131A (en) * 2015-01-29 2015-06-03 深圳云天励飞技术有限公司 Identity authentication method based on identity certificate information and human face multi-feature recognition
CN105138980A (en) * 2015-08-20 2015-12-09 深圳云天励飞技术有限公司 Identify authentication method and system based on identity card information and face identification
CN105227766A (en) * 2015-09-14 2016-01-06 惠州Tcl移动通信有限公司 A kind of anti-theft method for mobile terminal based on recognition of face, system and mobile terminal
CN105243357A (en) * 2015-09-15 2016-01-13 深圳市环阳通信息技术有限公司 Identity document-based face recognition method and face recognition device
CN106203294A (en) * 2016-06-30 2016-12-07 广东微模式软件股份有限公司 The testimony of a witness unification auth method analyzed based on face character

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109429519A (en) * 2017-06-30 2019-03-05 北京嘀嘀无限科技发展有限公司 System and method for verifying the authenticity of certificate photograph
CN111052131A (en) * 2017-09-28 2020-04-21 松下知识产权经营株式会社 Authentication device, authentication system, authentication method, and program
CN111052131B (en) * 2017-09-28 2024-04-09 松下知识产权经营株式会社 Authentication device, authentication system, authentication method, and storage medium
CN107977621A (en) * 2017-11-29 2018-05-01 淮海工学院 Shipwreck identification model construction method, device, electronic equipment and storage medium
CN109034004A (en) * 2018-07-05 2018-12-18 广东军缆信息技术有限公司 A kind of identity verification method and device based on recognition of face
CN109446772A (en) * 2018-09-03 2019-03-08 平安国际融资租赁有限公司 Accrediting amount calculation method, device, computer equipment and storage medium
CN109508705A (en) * 2018-12-29 2019-03-22 河北三川科技有限公司 The dynamic threshold face alignment setting method of identity-based card validity period
CN109670481A (en) * 2018-12-29 2019-04-23 河北三川科技有限公司 Dynamic threshold setting method is compared based on the testimony of a witness of age and gender
CN109685952A (en) * 2018-12-29 2019-04-26 河北三川科技有限公司 The face access control system and application method of identity-based information
CN109670481B (en) * 2018-12-29 2021-07-13 河北三川科技有限公司 Age and gender based dynamic threshold setting method for testimony comparison
CN113316782A (en) * 2019-03-24 2021-08-27 苹果公司 Identity document verification

Similar Documents

Publication Publication Date Title
CN106778636A (en) Auth method and device
CN106203294B (en) The testimony of a witness based on face character analysis unifies auth method
CN107644204B (en) Human body identification and tracking method for security system
CN105956578B (en) A kind of face verification method of identity-based certificate information
CN104732601B (en) Automatic high-recognition-rate attendance checking device and method based on face recognition technology
CN105518709B (en) The method, system and computer program product of face for identification
KR101291899B1 (en) Procedure for identifying a person by eyelash analysis and acquisition device using thereof
CN106778525A (en) Identity identifying method and device
US7881524B2 (en) Information processing apparatus and information processing method
CN106778607A (en) A kind of people based on recognition of face and identity card homogeneity authentication device and method
CN102945366B (en) A kind of method and device of recognition of face
Tayab Khan et al. Smart Real‐Time Video Surveillance Platform for Drowsiness Detection Based on Eyelid Closure
CN107992855A (en) A kind of triple verification methods of airport security based on recognition of face
CN107230267B (en) Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method
EP3680794B1 (en) Device and method for user authentication on basis of iris recognition
CN108009482A (en) One kind improves recognition of face efficiency method
CN101710383A (en) Method and device for identity authentication
CN106709450A (en) Recognition method and system for fingerprint images
CN103778409A (en) Human face identification method based on human face characteristic data mining and device
JP5955031B2 (en) Face image authentication device
CN108171138B (en) Biological characteristic information acquisition method and device
CN106650574A (en) Face identification method based on PCANet
CN106529377A (en) Age estimating method, age estimating device and age estimating system based on image
JP4992517B2 (en) Face matching device
Villariña et al. Palm vein recognition system using directional coding and back-propagation neural network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170531

RJ01 Rejection of invention patent application after publication