CN103559487B - A kind of personal identification method and system based on dermatoglyph feature - Google Patents
A kind of personal identification method and system based on dermatoglyph feature Download PDFInfo
- Publication number
- CN103559487B CN103559487B CN201310560531.1A CN201310560531A CN103559487B CN 103559487 B CN103559487 B CN 103559487B CN 201310560531 A CN201310560531 A CN 201310560531A CN 103559487 B CN103559487 B CN 103559487B
- Authority
- CN
- China
- Prior art keywords
- value
- texture images
- skin texture
- dermatoglyph
- skin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
This application discloses a kind of personal identification method and system based on dermatoglyph feature, this method include:Obtain skin texture images input by user;Determine the quality weighted value of the skin texture images;Skin texture images are compared with template image is preset, determine maximum dermatoglyph feature comparison value;The quality weighted value is multiplied with the maximum dermatoglyph feature comparison value, multiplied result is obtained, when identity information, which meets certification, passes through condition, determines that the user identity is validated user, the identity information meets certification and included at least by condition:The multiplied result is more than the first preset value.The application does not pay attention to detail excessively, but focuses on texture, focuses on big section, therefore solves in fingerprint minutiae comparison method, for few minutiae point fingerprint image, it is difficult to which zero overcome refuses publishing problem.
Description
Technical field
This application involves biometrics identification technology field, more specifically to a kind of based on dermatoglyph feature
Personal identification method and system.
Background technology
Biometrics identification technology is using terminal device acquisition physiological characteristic and behavioural characteristic, after treatment to identity
The technology differentiated.Compared with traditional identification authentication mode, living things feature recognition has antifalsification good, easy to carry, no
Easy to be lost, the advantages that being not easy to forget, therefore have better safety, reliability and validity.With the rapid development of information technology,
Living things feature recognition has become an important feature of current era, and the technology of this respect is widely used in banking and insurance business, electronics
The industries such as commercial affairs, office automatic, identity card management, social security, security, anti-fake.In this context, how to confirm human individual's
True identity, protection information have become safely the hot spot of various countries' research and application.
Existing more mature living things feature recognition has fingerprint, face, iris, hand, personal recognition etc., different biologies special
Sign identification technology is had nothing in common with each other feature, and such as on discrimination and operational efficiency, fingerprint recognition is better than face, iris, hand, palmmprint
Deng;In terms of ease of use, in safe examination system especially in public places, recognition of face is because of its contactless, clean hygiene
It is easiest to that user is allowed to receive.Although different living things feature recognitions respectively has its advantage and disadvantage, fingerprint recognition is generally acknowledged technology
One of most ripe, most widely used living things feature recognition.It is the most frequently used and most critical at present both at home and abroad in fingerprint recognition
Technology is minutiae point algorithm, and the core of minutiae point algorithm is that the extraction and comparison of minutiae point still often will appear fingerprint at present
Image in biology or identification process due to occurring interfering etc. so that will appear when identified without carefully in fingerprint image
Node or minutiae point it is less and the case where can not be identified, the phenomenon that this results in often refusing publishing, influence normal
It uses.
Invention content
In view of this, the application provides a kind of personal identification method and system based on dermatoglyph feature, for solving
Existing recognition methods is for the problem that few minutiae point or does not have the case where minutiae point, often occurs refusing publishing phenomenon.
To achieve the goals above, it is proposed that scheme it is as follows:
A kind of personal identification method based on dermatoglyph feature, including:
Obtain skin texture images input by user;
Determine the quality weighted value of the skin texture images;
The skin texture images are carried out with the template image in preset skin texture images template library respectively
Comparison obtains comparing result, and a secondary template image is included at least in the skin texture images template library;
Maximum dermatoglyph feature comparison value is determined from multiple comparing results;
The quality weighted value is multiplied with the maximum dermatoglyph feature comparison value, multiplied result is obtained, works as identity
When information meets certification and passes through condition, determine that the user identity is validated user, the identity information meets certification and passes through item
Part includes at least:The multiplied result is more than the first preset value.
Preferably, it is described by the skin texture images respectively with the mould in preset skin texture images template library
Plate image is compared to obtain comparing result process:
Fourier transformation is carried out respectively for the skin texture images and the template image, obtains corresponding two groups
Value;
Conjugation is asked to any one class value in two class values that are obtained after above-mentioned be fourier transformed;
The value obtained after value and another width after conjugation is fourier transformed carries out point multiplication operation, and by the knot after dot product
Fruit normalizes;
Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum value after absolute value, it will be described
Maximum value is determined as comparing result.
Preferably, it is described by the skin texture images respectively with the mould in preset skin texture images template library
Plate image is compared to obtain comparing result process:
For the skin texture images, different skin textural characteristics are extracted;
By the multiple different skin textural characteristics constitutive characteristic vector;
For the template image, different skin textural characteristics are extracted;
Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
The comparison value of feature based after the normalization is determined as comparing by the comparison value for normalizing the feature based
As a result.
Preferably, it is described by the skin texture images respectively with the mould in preset skin texture images template library
Plate image is compared to obtain comparing result process:
For the skin texture images, different skin textural characteristics are extracted;
By the multiple different skin textural characteristics constitutive characteristic vector;
For the template image, different skin textural characteristics are extracted;
Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
The comparison value for normalizing the feature based obtains the comparison value of feature based;
Fourier transformation is carried out respectively for the skin texture images and the template image, obtains corresponding two groups
Value;
Conjugation is asked to any one class value in two values being obtained after above-mentioned be fourier transformed;
The value obtained after value and another width after conjugation is fourier transformed carries out point multiplication operation, and by the knot after dot product
Fruit normalizes;
Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum value after absolute value, it will be described
Maximum value determination is characterized correlation;
Comparison value and the feature correlation to the feature based are weighted, and weighting coefficient selects between zero and one
It takes, and includes 0 and 1, the value after weighting is determined as comparison result.
Preferably, it is described by the skin texture images respectively in preset skin texture images template library
Template image is compared to further comprise before obtaining comparing result:
The skin texture images are pre-processed, the pretreatment is:Normalization, filtering, angle correct, displacement school
Just and stretch.
Preferably, the quality weighted value of the determination skin texture images is specially:
Dermatoglyph rule degree is calculated, dermatoglyph encircled energy is calculated, calculates the dermatoglyph degree of balance and/or calculating
The dermatoglyph uniformity;
To the dermatoglyph rule degree, the dermatoglyph encircled energy, the dermatoglyph degree of balance and/or institute
It states the dermatoglyph uniformity to be weighted, obtains weighted value.
Preferably, this method further comprises:Obtain identification code input by user and compared with the identification code that prestores;
The identity information meets certification:The multiplied result is more than the first preset value and the use
The identification code of family input is consistent with the identification code that prestores.
A kind of identification system based on dermatoglyph feature, including:
Dermatoglyph information receiving module, for receiving skin texture images input by user;
Picture quality judgment module is connected with the dermatoglyph information receiving module, for determining the dermatoglyph
The quality weighted value of image;
Dermatoglyph information identification module is connected with described image Quality estimation module, is used for the dermatoglyph figure
As being compared to obtain comparing result with the template image in preset skin texture images template library respectively, from multiple right
Than determining maximum dermatoglyph feature comparison value in result;
Identity determining module is connected with the dermatoglyph information identification module, is used for the skin texture images
Quality weighted value is multiplied to obtain multiplied result with the maximum dermatoglyph feature comparison value, passes through when identity information meets certification
When condition, determine that the user identity is validated user, the identity information meets certification and included at least by condition:The phase
Multiply result and is more than the first preset value.
Preferably, the system also includes:
Skin texture images preprocessing module, one end are connected with described image Quality estimation module, the other end and the skin
Skin texture information identification module is connected, for being pre-processed to the skin texture images.
Preferably, described image Quality estimation module includes:
Rule degree picture quality judging submodule, for being judged picture quality using rule degree;
Encircled energy picture quality judging submodule, for being judged picture quality using encircled energy;
Depth of parallelism picture quality judging submodule, for being judged picture quality using the depth of parallelism;
Uniformity picture quality judging submodule, judges picture quality for being conducive to the uniformity.
Preferably, the system also includes:
CUSTOMER ID authentication module, for receiving identification code input by user and compared with the identification code that prestores;
The identity information meets certification:The multiplied result is more than the first preset value and the use
The identification code of family input is consistent with the identification code that prestores.
It can be seen from the above technical scheme that technical solution disclosed by the invention, right by obtaining skin texture images
The quality of skin texture images is weighted, and then compares the skin texture images of acquisition and the skin line of the template image to prestore
Feature is managed, obtains maximum dermatoglyph feature comparison value, finally combines picture quality weighted value and maximum dermatoglyph aspect ratio
To value, the identity of user is confirmed.The application does not pay attention to detail excessively, but focuses on texture, focuses on big section, therefore solves finger
In line minutiae point comparison method, for few minutiae point or there is no minutiae point fingerprint image, it is difficult to which zero overcome refuses publishing problem.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of personal identification method flow chart based on dermatoglyph feature disclosed in the embodiment of the present application;
Fig. 2 compares flow chart for a kind of skin texture images disclosed in another embodiment of the application with template image;
Fig. 3 is that another skin texture images disclosed in another embodiment of the application compare flow chart with template image;
Fig. 4 is that another skin texture images disclosed in another embodiment of the application compare flow chart with template image;
Fig. 5 is another personal identification method flow based on dermatoglyph feature disclosed in another embodiment of the application
Figure;
Fig. 6 is a kind of method flow of the quality weighted value of determining skin texture images disclosed in another embodiment of the application
Figure;
Fig. 7 is another personal identification method flow based on dermatoglyph feature disclosed in another embodiment of the application
Figure;
Fig. 8 is a kind of identification system composition figure based on dermatoglyph feature disclosed in another embodiment of the application;
Fig. 9 is another disclosed identification system composition based on dermatoglyph feature of another embodiment of the application
Figure;
Figure 10 is a kind of picture quality judgment module composition figure disclosed in another embodiment of the application;
Figure 11 is the group of another identification system based on dermatoglyph feature disclosed in another embodiment of the application
Cheng Tu;
Figure 12 is a kind of CUSTOMER ID authentication module composition figure disclosed in another embodiment of the application.
Specific implementation mode
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall in the protection scope of this application.
Embodiment 1
Fig. 1 is the personal identification method flow chart based on dermatoglyph feature according to the embodiment of the present application 1.
As shown in Figure 1, this approach includes the following steps:
Step 101:Obtain skin texture images input by user;
By carrying out Image Acquisition to specific region of skin, skin texture images input by user are obtained.
Step 102:Determine the quality weighted value of the skin texture images;
Specifically, after obtaining skin texture images input by user, it can be determined that the matter of the skin texture images
Amount, and picture quality weighted value is all assigned to corresponding image, the weighted value any one number between 0-1, including 0 and 1.Certainly
In order to accelerate recognition speed, picture quality deterministic process can not also be passed through, it is 1 directly to assign picture quality weighted value.If
Picture quality is too poor, and prompt user can be selected to re-start dermatoglyph acquisition, can not also be prompted.
Step 103:By the skin texture images respectively with the template in preset skin texture images template library
Image is compared to obtain comparing result, and a width template image is included at least in the skin texture images template library;
Specifically, the skin texture images of one or more users can be prestored in skin texture images template library
Template, if prestoring the template of a user, it is only necessary to compare the skin texture images of acquisition and the template to prestore
If prestoring the template of multiple users, the skin texture images for comparing each template and acquisition successively are needed, are obtained
To multiple comparing results.
Step 104:Maximum dermatoglyph feature comparison value is determined from multiple comparing results;
Specifically, a maximum value is determined from multiple comparing results, it is special which is determined as maximum dermatoglyph
Levy comparison value.
Step 105:The quality weighted value is multiplied with the maximum dermatoglyph feature comparison value, obtains the knot that is multiplied
Fruit determines that the user identity is validated user, the identity information, which meets, to be recognized when identity information, which meets certification, passes through condition
Card is included at least by condition:The multiplied result is more than the first preset value.
Specifically, first preset value is prestored before recognition, the size of the value is by user according to multiple reality
It tests and is determined.In identification, considers the quality weighted value and dermatoglyph feature comparison value of image, judge that the two is multiplied
As a result then confirm that user identity is legal use when multiplied result is more than the first preset value with the magnitude relationship of the first preset value
Family allows user to log in, and otherwise confirms that user identity is disabled user, refusal user logs in.
Further, the technical solution of the application can either carry out 1:1 verification can also carry out 1:The matching operation of N.
In the present embodiment, due to need not excessively pay attention to detail, but focus on texture, focus on big section, thus reduce by
In lack minutiae point and caused by refuse publishing problem.
Embodiment 2
It is that a kind of skin texture images disclosed in the present application compare flow chart with template image referring to Fig. 2.
This method includes:
Step 201:Fourier transformation is carried out respectively for the skin texture images and the template image, is corresponded to
Two class values;
Step 202:Conjugation is asked to any one class value in two class values that are obtained after above-mentioned be fourier transformed;
Step 203:The value obtained after value and another width after conjugation is fourier transformed carries out point multiplication operation, and by point
Result normalization after multiplying;
Step 204:Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum after absolute value
Value, is determined as comparing result by the maximum value.
The skin texture images comparison method provided through this embodiment, selection dermatoglyph enriches, less hair interferes,
The detection and analysis region for comparing expression shape change robust, does not overemphasize the details of texture, therefore solves currently popular
In fingerprint minutiae comparison method, for few minutiae point fingerprint image or there is no minutiae point fingerprint image, it is difficult to zero overcome
According to stepping on problem, and this method is applicable not only to fingerprint front, fingerprint side image authentication and compares, and suitable articulations digitorum manus is just
The image authentications such as face, the articulations digitorum manus back side, palm, face with compare.
Embodiment 3
It is that another skin texture images disclosed in the present application compare flow chart with template image such as Fig. 3.
This method includes:
Step 301:For the skin texture images, different skin textural characteristics are extracted;
Step 302:By the multiple different skin textural characteristics constitutive characteristic vector;
Step 303:For the template image, different skin textural characteristics are extracted;
Step 304:Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
Step 305:The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
Step 306:The comparison value for normalizing the feature based, the comparison value of the feature based after the normalization is true
It is set to comparison result.
Further, the template characteristic vector in the application can also be what user pre-saved, thus be not necessarily to step
303 and step 304, directly extract template characteristic vector.In the present embodiment, according to the direction of dermatoglyph, frequency, thick
Carefully, the depth, node type, number of nodes, the quantity of texture primitive, texture based on distribution, local feature etc. carry out feature
Extraction and comparison, compare expression shape change in the detection and analysis region of robust, do not overemphasize the details of texture, therefore solve
Currently popular in fingerprint minutiae comparison method, for few minutiae point fingerprint image or there is no minutiae point fingerprint image, it is difficult
Problem is stepped on zero evidence overcome, and this method is applicable not only to fingerprint front, fingerprint side image authentication and compares, Er Qieshi
It closes the image authentications such as articulations digitorum manus front, the articulations digitorum manus back side, palm, face and compares.
Embodiment 4
It is that another skin texture images disclosed in the present application compare flow chart with template image such as Fig. 4.
This method includes:
Step 401:For the skin texture images, different skin textural characteristics are extracted;
Step 402:By the multiple different skin textural characteristics constitutive characteristic vector;
Step 403:For the template image, different skin textural characteristics are extracted;
Step 404:Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
Step 405:The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
Step 406:The comparison value for normalizing the feature based obtains the comparison value of feature based;
Step 411:Fourier transformation is carried out respectively for the skin texture images and the template image, is corresponded to
Two class values;
Step 412:Conjugation is asked to any one class value in two class values that are obtained after above-mentioned be fourier transformed;
Step 413:The value obtained after value and another width after conjugation is fourier transformed carries out point multiplication operation, and by point
Result normalization after multiplying;
Step 414:Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum after absolute value
Maximum value determination is characterized correlation by value;
Step 415:Comparison value and the feature correlation to the feature based are weighted, and weighting coefficient is in 0 and 1
Between choose, and include 0 and 1, the value after weighting be determined as comparison result.
In the present embodiment, by considering two kinds of skin texture images comparison methods, robust is compared to expression shape change
Detection and analysis region, do not overemphasize the details of texture, therefore solve fingerprint minutiae comparison method currently popular
In, for few minutiae point fingerprint image or there is no minutiae point fingerprint image, it is difficult to which zero evidence overcome steps on problem, and this method
Be applicable not only to fingerprint front, fingerprint side image authentication and compare, and suitable articulations digitorum manus front, the articulations digitorum manus back side, palm,
The image authentications such as face with compare.
Embodiment 5
It is another personal identification method flow chart based on dermatoglyph feature disclosed in the present application such as Fig. 5.
In the present embodiment, step 501,502,504,505,506 and the step 101 in embodiment one, 102,103,104,
105 is identical, and the present embodiment only increases step 503 between the step 102 and step 103 of embodiment one:To the skin
Texture image is pre-processed, and pretreated mode is:Normalization, filtering, angle correct, displacement correction and stretching.
By being pre-processed to skin texture images, the dermatoglyph feature extracted is enabled to become apparent from so that
Authentication method is more accurate.
Embodiment 6
It is a kind of method flow diagram of the quality weighted value of determining skin texture images disclosed in the present application such as Fig. 6.
This method includes:
Step 601:Dermatoglyph rule degree is calculated, dermatoglyph encircled energy is calculated, calculates the dermatoglyph degree of balance
And/or calculate the dermatoglyph uniformity;
Step 602:To the dermatoglyph rule degree, the dermatoglyph encircled energy, dermatoglyph balance
Degree and/or the dermatoglyph uniformity are weighted, and obtain weighted value.
In the present embodiment, can select it is any one or more in aforementioned four criterion, if selection multiple is sentenced
Disconnected standard, then the corresponding value obtained to each criterion be weighted processing, after finally considering total weighting
The size of value, to evaluate the quality of skin texture images.
Embodiment 7
It is the another personal identification method flow chart based on dermatoglyph feature disclosed in the present application such as Fig. 7.
On the basis of embodiment 1, step 101-104 does not change, and only further increases step 701:Obtain user
The identification code of input and compared with the identification code that prestores;
Step 105 in embodiment 1 also changes into step 702 accordingly:By the quality weighted value and the maximum skin
Skin textural characteristics comparison value is multiplied, and obtains multiplied result;When identity information, which meets certification, passes through condition, user's body is determined
Part is validated user, and the identity information meets certification and includes by condition:The multiplied result is more than the first preset value and institute
It is consistent with the identification code that prestores to state identification code input by user.
In the present embodiment, CUSTOMER ID verification step is further increased, the identification code can be specifically:User
Name, password, work number, identification card number, mobile phone, terminal serial number etc., the mode of reading can be contact with it is contactless.And
It is final to determine that certification when user identity is by condition:Judge textural characteristics recognition result and identity code as a result, if
The two is all consistent, determines user identity.
Personal identification method provided in this embodiment based on dermatoglyph feature uses multimode manner, carries out dermatoglyph
While feature recognition, code determination is also identified so that the technical solution of the application is more safe and reliable in application.
And the personal identification method of the application can be applied on existing hardware resource, also can be to hardware resource slightly
It can be applied after adding modification, there is no the problems in hardware design, making.
Embodiment 8
Disclosed herein as well is a kind of identification systems based on dermatoglyph feature, and referring to Fig. 8, which includes:
Dermatoglyph information receiving module 81, for receiving skin texture images input by user;
Picture quality judgment module 82 is connected with the dermatoglyph information receiving module, for determining the skin line
Manage the quality weighted value for the skin texture images that information receiving module 81 is sent;
Specifically, picture quality judgment module 82 assigns each image one weighting for evaluating picture quality
Value, any one number of the value between 0-1, including 0 and 1.Of course for recognition speed is accelerated, image matter can not also be passed through
Deterministic process is measured, it is 1 directly to assign picture quality weighted value.If picture quality is too poor, can select prompt user again into
Row dermatoglyph acquires, and can not also prompt.
Dermatoglyph information identification module 83 is connected with described image Quality estimation module 82, by the dermatoglyph figure
As being compared to obtain comparing result with the template image in preset skin texture images template library respectively, from multiple right
Than determining maximum dermatoglyph feature comparison value in result;
Identity determining module 84 is connected with the dermatoglyph information identification module 83, is used for the dermatoglyph figure
The quality weighted value of picture is multiplied with the maximum dermatoglyph feature comparison value, obtains multiplied result, recognizes when identity information meets
When card passes through condition, determine that the user identity is validated user, the identity information meets certification and included at least by condition:
The multiplied result is more than the first preset value.
System described in the present embodiment judges picture quality by picture quality judgment module 82, and assigns certain
Weighted value, skin texture images are compared by dermatoglyph information identification module 83, it is special to obtain maximum dermatoglyph
Levy comparison value, consider the quality weighted value of image and maximum dermatoglyph feature comparison value, both judge multiplied result with
The magnitude relationship of first preset value then confirms user identity when multiplied result is more than the first preset value, and user is allowed to log in,
Otherwise confirm that user identity is disabled user, is denied it to log in.
In the present embodiment, due to need not excessively pay attention to detail, but focus on texture, focus on big section, thus reduce by
In lack minutiae point and caused by refuse publishing problem.
Referring to Fig. 9, on the basis of the above embodiments, which can further include skin texture images pretreatment mould
Block 85,85 one end of skin texture images preprocessing module are connect with picture quality judgment module 82, and the other end is believed with dermatoglyph
It ceases identification module 83 to connect, for pre-processing the skin texture images.
Embodiment 9
Such as Figure 10, scheme for picture quality judgment module disclosed in the present application composition.
Picture quality judgment module 82 specifically includes:
Rule degree picture quality judging submodule 821, for being judged picture quality using rule degree;
Encircled energy picture quality judging submodule 822, for being judged picture quality using encircled energy;
Depth of parallelism picture quality judging submodule 823, for being judged picture quality using the depth of parallelism;
Uniformity picture quality judging submodule 824, judges picture quality for being conducive to the uniformity.
In the present embodiment, picture quality judgment module 82 can be rule degree picture quality judging submodule 821, energy quantity set
Moderate picture quality judging submodule 822, depth of parallelism picture quality judging submodule 823, uniformity picture quality judge submodule
It is any one or more in block 824, it can also be weighted and collectively form multi-modality image Quality estimation module 82.Rule degree
Picture quality judging submodule 821, encircled energy picture quality judging submodule 822, depth of parallelism picture quality judge submodule
Block 823, uniformity picture quality judging submodule 824 obtain difference respectively from the local, global of image, frequency domain, time domain
Image quality judging method.
Wherein, rule degree picture quality judging submodule 821 refers to being judged picture quality using rule degree, i.e.,
The degree of skin texture images texture order is weighed using texture rule degree, it is the general indices in time domain, rule degree
Small skin texture images texture is mixed and disorderly, and the big skin texture images of rule degree then streakline aligned orderly;Encircled energy figure
Image quality amount judging submodule 822 refers to being judged picture quality using encircled energy, i.e., extracts skin line in a frequency domain
The essential characteristic of image is managed, it is the general indices on frequency domain, embodies the deal shared by dominant frequency;Depth of parallelism picture quality judges
Submodule 823 is the index for weighing skin texture images part streakline parallel degree, it carries out skin texture images blocks is waited to draw
Point, the skin texture images in each fritter are generally alternately made of crestal line and valley line, the good dermatoglyph figure of the depth of parallelism
As all crestal line directions are similar to parallel, and the image of depth of parallelism difference is then opposite;Uniformity picture quality judging submodule 824,
Refer to being judged picture quality using the uniformity, the texture uniformity is the different journeys for characterizing dermatoglyph topography
The ratio of gray-scale pixels is spent, it is the local indexes in time domain, and the skin texture images ridge paddy of good evenness is to be alternately arranged simultaneously
And it is equally distributed, so the Black white pixel rate in each piece is stable, and the skin texture images of uniformity difference due to
Its ridge paddy streakline unobvious, crackle is more and miscellaneous, and the parameter between block and block is very big, so its ratio is non-constant.
Embodiment 10
It is the composition figure of another identification system based on dermatoglyph feature disclosed in the present application such as Figure 11.
On the basis of embodiment 8 or 9, disclosed system further includes:
CUSTOMER ID authentication module 111, for receiving identification code input by user and the certification compared with the identification code that prestores;
Correspondingly, the identity determining module 84 of embodiment 8 or 9 also changes into identity determining module 112:Judge the identity
Information meet certification by condition further comprise:The multiplied result is more than the first preset value and the knowledge input by user
Other code is consistent with the identification code that prestores.
In the present embodiment, CUSTOMER ID authentication module 111 is further increased, for receiving identification input by user
Code, and be compared with the identification code to prestore, to obtain identification code authentication result.And identity determining module 112 is final really
Certification when determining user identity is by condition:The multiplied result is more than the first preset value and the identification code input by user
It is consistent with the identification code that prestores.I.e. identity determining module 112 confirms user identity by two aspects.
Identification system provided in this embodiment based on dermatoglyph feature uses multimode manner, carries out skin characteristic
While identification, code authentication is also identified so that the technical solution of the application is more safe and reliable in practical application.
And the identification system of the application can be applied on existing hardware resource, also can be to hardware resource slightly
It can be applied after adding modification, there is no the problems in hardware design, making.
Embodiment 11
It is the composition figure of the application CUSTOMER ID authentication module 111 such as Figure 12.
The CUSTOMER ID authentication module 111 specifically includes:
Identification code authentication sub module 1111 is inputted, for code authentication to be identified according to the identification code input by user;
Contact identification code authentication sub module 1112, for being identified according to the contact terminal recognition code of the user
Code authentication;
Contactless recognition code authentication submodule 1113, for being carried out according to the contactless terminal recognition code of the user
Identify code authentication;
Based on matched identification code authentication sub module 1114, for according to the physiology input by user or behavioural characteristic into
Row identification code authentication.
Wherein, input identification code authentication sub module 1111, can be by pre-stored identification code and identification input by user
Code is compared, and obtains authentication result, which can be user name, work number, identification card number, cell-phone number, password etc.;
Pre-stored identification code can be compared with terminal recognition code for contact identification code authentication sub module 1112, obtain certification
As a result, the input of the contact identification code, can be IC card, magnetic card etc.;Contactless recognition code authentication submodule 1113 is same
Pre-stored identification code can be compared with terminal recognition code, obtains authentication result, the non contact angle measurement code it is defeated
Enter, can be Wireless IC card, also to determine certification etc. at a distance from user distance by GPS etc.;Recognized based on matched identification code
Certification can be realized by fingerprint, face, iris, hand, palmmprint etc. by demonstrate,proving submodule 1114.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only that
A little elements, but also include other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or use the application.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (11)
1. a kind of personal identification method based on dermatoglyph feature, which is characterized in that including:
Obtain skin texture images input by user;
Determine the quality weighted value of the skin texture images;
The skin texture images are compared with the template image in preset skin texture images template library respectively
Comparing result is obtained, a secondary template image is included at least in the skin texture images template library;
Maximum dermatoglyph feature comparison value is determined from multiple comparing results;
The quality weighted value is multiplied with the maximum dermatoglyph feature comparison value, multiplied result is obtained, works as identity information
When meeting certification and passing through condition, determine that the user identity is validated user, the identity information meets certification by condition extremely
Include less:The multiplied result is more than the first preset value.
2. according to the method described in claim 1, it is characterized in that, it is described by the skin texture images respectively with preset
Skin texture images template library in template image compared to obtain comparing result process be specially:
Fourier transformation is carried out respectively for the skin texture images and the template image, obtains corresponding two class value;
Conjugation is asked to any one class value in two class values that are obtained after above-mentioned be fourier transformed;
The value obtained after value after conjugation is fourier transformed with another width carries out point multiplication operation, and the result after dot product is returned
One changes;
Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum value after absolute value, by the maximum
Value is determined as comparing result.
3. according to the method described in claim 1, it is characterized in that, it is described by the skin texture images respectively with preset
Skin texture images template library in template image compared to obtain comparing result process be specially:
For the skin texture images, different skin textural characteristics are extracted;
By the multiple different skin textural characteristics constitutive characteristic vector;
For the template image, different skin textural characteristics are extracted;
Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
The comparison value of feature based after the normalization is determined as comparing knot by the comparison value for normalizing the feature based
Fruit.
4. according to the method described in claim 1, it is characterized in that, it is described by the skin texture images respectively with preset
Skin texture images template library in template image compared to obtain comparing result process be specially:
For the skin texture images, different skin textural characteristics are extracted;
By the multiple different skin textural characteristics constitutive characteristic vector;
For the template image, different skin textural characteristics are extracted;
Template characteristic vector is constituted by the corresponding multiple and different dermatoglyph features of the template image;
The characteristic vector and the template characteristic vector are compared, obtains the comparison value of feature based;
The comparison value for normalizing the feature based obtains the comparison value of feature based;
Fourier transformation is carried out respectively for the skin texture images and the template image, obtains corresponding two class value;
Conjugation is asked to any one class value in two values being obtained after above-mentioned be fourier transformed;
The value obtained after value after conjugation is fourier transformed with another width carries out point multiplication operation, and the result after dot product is returned
One changes;
Fourier inversion is asked to the dot product result after the normalization, and seeks the maximum value after absolute value, by the maximum
Value determination is characterized correlation;
Comparison value and the feature correlation to the feature based are weighted, and weighting coefficient is chosen between zero and one, and
Including 0 and 1, the value after weighting is determined as comparison result.
5. method according to claim 1,2,3 or 4, which is characterized in that distinguish the skin texture images described
It is compared to further comprise before obtaining comparing result with the template image in preset skin texture images template library:
The skin texture images are pre-processed, the pretreatment is:Normalization, filtering, angle correct, displacement correction and
It stretches.
6. according to the method described in claim 1, it is characterized in that, the quality weighted value of the determination skin texture images
Specially:
Dermatoglyph rule degree is calculated, dermatoglyph encircled energy is calculated, calculate the dermatoglyph degree of balance and/or calculates skin
The texture uniformity;
To the dermatoglyph rule degree, the dermatoglyph encircled energy, the dermatoglyph degree of balance and/or the skin
The skin texture uniformity is weighted, and obtains weighted value.
7. according to the method described in claim 1, it is characterized in that, this method further comprises:Obtain identification input by user
Code and compared with the identification code that prestores;
The identity information meets certification:The multiplied result is more than the first preset value and the user is defeated
The identification code entered is consistent with the identification code that prestores.
8. a kind of identification system based on dermatoglyph feature, which is characterized in that including:
Dermatoglyph information receiving module, for receiving skin texture images input by user;
Picture quality judgment module is connected with the dermatoglyph information receiving module, for determining the skin texture images
Quality weighted value;
Dermatoglyph information identification module is connected with described image Quality estimation module, for dividing the skin texture images
It is not compared to obtain comparing result with the template image in preset skin texture images template library, be tied from multiple comparisons
Maximum dermatoglyph feature comparison value is determined in fruit;
Identity determining module is connected with the dermatoglyph information identification module, is used for the quality of the skin texture images
Weighted value is multiplied to obtain multiplied result with the maximum dermatoglyph feature comparison value, passes through condition when identity information meets certification
When, determine that the user identity is validated user, the identity information meets certification and included at least by condition:The multiplication knot
Fruit is more than the first preset value.
9. system according to claim 8, which is characterized in that the system also includes:
Skin texture images preprocessing module, one end are connected with described image Quality estimation module, the other end and the skin line
It manages information identification module to be connected, for pre-processing the skin texture images.
10. system according to claim 8 or claim 9, which is characterized in that described image Quality estimation module includes:
Rule degree picture quality judging submodule, for being judged picture quality using rule degree;
Encircled energy picture quality judging submodule, for being judged picture quality using encircled energy;
Depth of parallelism picture quality judging submodule, for being judged picture quality using the depth of parallelism;
Uniformity picture quality judging submodule, judges picture quality for being conducive to the uniformity.
11. system according to claim 8 or claim 9, which is characterized in that the system also includes:
CUSTOMER ID authentication module, for receiving identification code input by user and compared with the identification code that prestores;
The identity information meets certification:The multiplied result is more than the first preset value and the user is defeated
The identification code entered is consistent with the identification code that prestores.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310560531.1A CN103559487B (en) | 2013-11-12 | 2013-11-12 | A kind of personal identification method and system based on dermatoglyph feature |
PCT/CN2014/073446 WO2015070549A1 (en) | 2013-11-12 | 2014-03-14 | Skin texture collection and identity recognition method and system |
US15/036,275 US20160300094A1 (en) | 2013-11-12 | 2014-03-14 | Skin texture collection and identity recognition method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310560531.1A CN103559487B (en) | 2013-11-12 | 2013-11-12 | A kind of personal identification method and system based on dermatoglyph feature |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103559487A CN103559487A (en) | 2014-02-05 |
CN103559487B true CN103559487B (en) | 2018-09-11 |
Family
ID=50013728
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310560531.1A Active CN103559487B (en) | 2013-11-12 | 2013-11-12 | A kind of personal identification method and system based on dermatoglyph feature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103559487B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015070549A1 (en) * | 2013-11-12 | 2015-05-21 | 浙江维尔科技股份有限公司 | Skin texture collection and identity recognition method and system |
CN103810410A (en) * | 2014-03-10 | 2014-05-21 | 辽宁科技大学 | Information evidence collection method for Internet of things |
CN104055521B (en) * | 2014-06-05 | 2017-10-27 | 胡宝华 | Method for identifying ID, identifying system and health instrument |
US20200245014A1 (en) * | 2017-08-29 | 2020-07-30 | Home Control Singapore Pte Ltd | Subtle user recognition |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100395770C (en) * | 2005-06-27 | 2008-06-18 | 北京交通大学 | Hand-characteristic mix-together identifying method based on characteristic relation measure |
-
2013
- 2013-11-12 CN CN201310560531.1A patent/CN103559487B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
Non-Patent Citations (3)
Title |
---|
基于形状特征的图像检索;陈宏;《中国优秀硕士学位论文全文数据库》;20101231;第38页第2段 * |
基于指纹识别与智能卡的身份认证系统设计;宁璇;《中国优秀硕士学位论文全文数据库》;20100331;第40页第2-3段 * |
基于纹理特征的自动指纹识别系统;王俊一;《中国优秀硕士学位论文全文数据库》;20060531;第10页第2段,第5段,第12页第2段,第36页第4段,第52页第1-2段 * |
Also Published As
Publication number | Publication date |
---|---|
CN103559487A (en) | 2014-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106326886B (en) | Finger vein image quality appraisal procedure based on convolutional neural networks | |
Maltoni et al. | Handbook of fingerprint recognition | |
CN104700094B (en) | A kind of face identification method for intelligent robot and system | |
CN103559487B (en) | A kind of personal identification method and system based on dermatoglyph feature | |
US20140059675A1 (en) | Biometric authentication | |
CN109766785A (en) | A kind of biopsy method and device of face | |
US20160300094A1 (en) | Skin texture collection and identity recognition method and system | |
CN103544490A (en) | Skin texture collection and identity recognition method and system | |
CN103246880A (en) | Human face recognizing method based on multi-level local obvious mode characteristic counting | |
Beton et al. | Biometric secret path for mobile user authentication: A preliminary study | |
CN101178755A (en) | Method and device for confirming safety level of biology identification systemic | |
CN105184571A (en) | Payment authentication system based on combination of hand veins and multiple fingerprints | |
JP3590285B2 (en) | Biological information recognition device and method | |
CN111723595A (en) | Personnel identity identification method and system | |
CN107615299B (en) | For assessing the method and system of fingerprint template | |
Nishiuchi et al. | Cancelable biometric identification by combining biological data with artifacts | |
JP5422326B2 (en) | Biometric authentication device | |
Wangkeeree et al. | Finding a suitable threshold value for an iris-based authentication system | |
Ameh et al. | Securing cardless automated teller machine transactions using bimodal authentication system | |
Vanthana et al. | Iris authentication using gray level co-occurrence matrix and Hausdorff dimension | |
Sharma et al. | Role of biometric technology over advanced security and protection in auto teller machine transaction | |
Betab et al. | Fingerprints in automated teller Machine-A survey | |
Cruz et al. | Lip Biometric Authentication Using Viola-Jones and Appearance Based Model (AAM) System | |
JP6032566B2 (en) | Identification data processing apparatus and identification data processing method | |
CN205788285U (en) | social security self-service terminal system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 310053 8 / F and 12 / F, building 5, No. 669, BINKANG Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: ZHEJIANG WELLCOM TECHNOLOGY Co.,Ltd. Address before: 310012, building two, Neusoft building, 99 Huaxing Road, Hangzhou, Zhejiang, Xihu District, A208 Patentee before: ZHEJIANG WELLCOM TECHNOLOGY Co.,Ltd. |