KR101802061B1 - Method and system for automatic biometric authentication based on facial spatio-temporal features - Google Patents
Method and system for automatic biometric authentication based on facial spatio-temporal features Download PDFInfo
- Publication number
- KR101802061B1 KR101802061B1 KR1020160029793A KR20160029793A KR101802061B1 KR 101802061 B1 KR101802061 B1 KR 101802061B1 KR 1020160029793 A KR1020160029793 A KR 1020160029793A KR 20160029793 A KR20160029793 A KR 20160029793A KR 101802061 B1 KR101802061 B1 KR 101802061B1
- Authority
- KR
- South Korea
- Prior art keywords
- face
- users
- space
- time
- user
- Prior art date
Links
Images
Classifications
-
- G06K9/00221—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G06K9/00268—
-
- G06K9/00288—
-
- G06K9/00302—
Abstract
An automatic biometric authentication method based on face space-time features includes obtaining a face gesture image of a user; Extracting face space-time features from the face gesture image; And matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-time feature of the user to authenticate the user.
Description
The following embodiments relate to an automatic biometric authentication system and method thereof, and more particularly to a technique for authenticating a user through automatic biometric authentication based on facial spatio-temporal features.
In recent years, a variety of biometric information has been utilized in smart devices such as smart phones and smart TVs. In particular, biometrics technology that is non-contact and easy to acquire data is required. Existing biometric authentication systems have been realized by classical biometric recognition technology such as fingerprint and iris. However, since they are acquired through contact data acquisition, user's control is required.
As an alternative, face recognition based biometric technology has emerged. Unlike conventional biometrics technology, face recognition based biometrics technology is not only useful in terms of user convenience because it does not require special contact, it is also expected to be widely used in smart devices and can be applied to various fields I am in the spotlight.
However, biometric authentication using facial biometric information is easier to acquire data than iris or fingerprint recognition, but is limited to use for user authentication due to a relatively high false acceptance rate (false acceptance rate) There is a great demand for research on this.
Recently, various studies have been conducted on feature learning and classification algorithms for high-performance face authentication, but since they depend only on the appearance information of a still-state facial image, they are present in an image (for example, video) There is a limit in that it can not utilize all facial image information. Particularly, considering that the dynamic information related to the human face motion provides not only the face shape information but also the important clues in recognition of the face characteristics of the human, the shape information of the face image existing in the image, it is necessary to study using temporal dynamic information.
Therefore, the following embodiments propose an automatic biometric authentication technique based on face space-time characteristics in an image including a user's face.
The following embodiments provide a method and system for automatic biometric authentication using facial spatio-temporal features.
Specifically, the embodiments described below can be applied to a face space-time feature including static face information extracted from a spatial analysis and dynamic face information extracted through a temporal analysis. And provides an automatic biometric authentication method and system to be used.
According to one embodiment, an automatic biometric authentication method based on face space-time features includes: obtaining a face gesture image of a user; Extracting face space-time features from the face gesture image; And matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-time feature of the user to authenticate the user.
The face space-time feature may include static face information and dynamic face information of the user.
Wherein the extracting of the face space-time feature from the face gesture image comprises: performing spatial analysis on the face gesture image to extract static face information of the user; Performing temporal analysis on the face gesture image to extract dynamic face information of the user; And extracting the face space-time feature by fusing the static face information and the dynamic face information of the user.
The step of extracting the face space-time feature from the face gesture image may include performing face analysis on the face gesture image based on a deep learning technique.
The step of matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-time feature of the user may include a nearest neighbor classifier, a sparse representation based classifier, and matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-time feature of the user using at least one of a support vector machine.
Wherein the step of matching the face space-time features of each of the plurality of users stored in the face feature database with the face space-time feature of the user comprises: matching the face space-time feature of the user among the plurality of users based on the matching result; And identifying the user having the feature.
The automatic biometric authentication method based on the face space-time feature may further include building the face feature database in advance.
The step of constructing the facial feature database in advance includes: acquiring a face gesture image of each of the plurality of users; Extracting a face space-time feature of each of the plurality of users from a face gesture image of each of the plurality of users; And storing face space-time characteristics of each of the plurality of users in the face feature database.
Wherein the step of extracting face space-time features of each of the plurality of users from the face gesture images of the plurality of users comprises the steps of extracting static face information of each of the plurality of users included in the face space- Performing a spatial analysis on a face gesture image of each of the plurality of users to extract; Performing time analysis on the face gesture images of each of the plurality of users to extract dynamic face information of each of the plurality of users included in the face space-time feature of each of the plurality of users; And extracting facial spatio-temporal features of each of the plurality of users by fusing static face information and dynamic face information of each of the plurality of users.
The step of extracting face space-time features of each of the plurality of users from the face gesture images of each of the plurality of users comprises: measuring a quality of a face gesture image of each of the plurality of users; And extracting face space-time characteristics of each of the plurality of users from the face gesture images of the plurality of users when the quality of the face gesture images of the plurality of users is equal to or greater than a reference value.
The step of measuring the quality of the face gesture image of each of the plurality of users may further include notifying each of the plurality of users when the quality of the face gesture image of each of the plurality of users is less than the reference value .
According to an embodiment, an automatic biometric authentication system based on face space-time features includes an acquiring unit for acquiring a face gesture image of a user; An extracting unit extracting a face space-time feature from the face gesture image; A face feature database storing face space-time features of each of a plurality of users; And a matching unit for matching the face space-time characteristics of each of the plurality of users stored in the face feature database with the face space-time characteristics of the user to authenticate the user.
Wherein the extractor performs a spatial analysis on the face gesture image to extract static face information of the user and performs a spatial analysis on the face gesture image to extract dynamic face information of the user, Temporal analysis for the user, and extracts the face space-time feature by fusing the static face information and the dynamic face information of the user.
Wherein the facial feature database acquires a face gesture image of each of the plurality of users in the obtaining unit and extracts a face space-time feature of each of the plurality of users from the face gesture image of each of the plurality of users in the extracting unit And the face space-time characteristics of each of the plurality of users can be stored and built in advance.
Wherein the extracting unit measures the quality of a face gesture image of each of the plurality of users in a measurement unit further included in the automatic biometric authentication system, and when the quality of a face gesture image of each of the plurality of users is equal to or greater than a reference value, Space feature of each of the plurality of users from the face gesture images of the users of the users.
The embodiments described below can provide an automatic biometric authentication method and system using face time and space features.
Specifically, the embodiments described below can be applied to a face space-time feature including static face information extracted from a spatial analysis and dynamic face information extracted through a temporal analysis. It is possible to provide an automatic biometric authentication method and system to be used.
Therefore, the following embodiments utilize the dynamic information of the face as well as the static information of the face, so that it is possible to provide an automatic biometric authentication method and system that perform effective face authentication in terms of performance.
In addition, since the following embodiments are based on non-contact data acquisition, it is possible to provide an automatic biometric authentication method and system which is useful in terms of user convenience and widely applied.
1 is a diagram for explaining a user registration process in an automatic biometric authentication system according to an embodiment.
2 is a diagram for explaining a user authentication process in an automatic biometric authentication system according to an exemplary embodiment.
FIG. 3 is a view for explaining a process of extracting face space-time features in the automatic biometric authentication system according to an embodiment.
FIG. 4 is a diagram for explaining time analysis performed in the process of extracting face space-time features according to an exemplary embodiment.
5 is a flowchart illustrating an automatic biometric authentication method according to an embodiment.
6 is a block diagram illustrating an automatic biometric authentication system according to an embodiment.
Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to or limited by the embodiments. In addition, the same reference numerals shown in the drawings denote the same members.
Also, terminologies used herein are terms used to properly represent preferred embodiments of the present invention, which may vary depending on the user, intent of the operator, or custom in the field to which the present invention belongs. Therefore, the definitions of these terms should be based on the contents throughout this specification.
1 is a diagram for explaining a user registration process in an automatic biometric authentication system according to an embodiment.
Referring to FIG. 1, an automatic biometric authentication system according to an exemplary embodiment of the present invention can perform a user registration process of previously building a
Specifically, the automatic biometric authentication system can acquire a face gesture image of each of a plurality of users through the
Then, the automatic biometric authentication system may extract the face-space-time feature of each of the plurality of users from the face gesture images of the plurality of users through the
In addition, the automatic biometric authentication system may measure the quality of the face gesture image of each of the plurality of users through the
The face space-time characteristics of each of the plurality of users extracted as described above may be matched to each of a plurality of users, and stored in the
2 is a diagram for explaining a user authentication process in an automatic biometric authentication system according to an exemplary embodiment.
2, an automatic biometric authentication system according to an exemplary embodiment of the present invention includes an acquiring
Specifically, the automatic biometric authentication system acquires a face gesture image of the user through the
Then, the automatic biometric authentication system extracts facial spatio-temporal features from the face gesture image through the
For example, the extracting
Thereafter, the automatic biometric authentication system performs a process for authenticating the user through the
At this time, the
FIG. 3 is a view for explaining a process of extracting face space-time features in the automatic biometric authentication system according to an embodiment.
Referring to FIG. 3, the extracting unit included in the automatic biometric authentication system according to an exemplary embodiment may perform a
For example, the extracting unit extracts static face information through the
In particular, the extractor may perform a
FIG. 4 is a diagram for explaining time analysis performed in the process of extracting face space-time features according to an exemplary embodiment.
Referring to FIG. 4, the extracting unit included in the automatic biometric authentication system according to an exemplary embodiment may perform time analysis on a face gesture image using a deep learning technique.
For example, the extractor may extract dynamic face information in which a user's face land marker in each of a plurality of frames included in a face gesture image changes with time, by performing time analysis based on a deep learning technique .
Such a deep running technique is described as a case where the extracting part is used in performing time analysis, but is not limited thereto and may be used in performing spatial analysis.
5 is a flowchart illustrating an automatic biometric authentication method according to an embodiment.
Referring to FIG. 5, the automatic biometric authentication method according to one embodiment is performed by the automatic biometric authentication system. Here, the automatic biometric authentication system may be implemented in the form of a separate server, or in the form of program code for executing an automatic biometric authentication method in combination with a computer, such as an application installed in a user terminal.
First, the automatic biometric authentication system obtains a user's face gesture image (510).
Next, the automatic biometric authentication system extracts face-space-time features from the face gesture image (520). Here, the face space-time feature may include static face information of the user and dynamic face information.
Specifically, in
At this time, the automatic biometric authentication system can perform facial analysis on the face gesture image based on the deep learning technique in the process of extracting the face space-time feature.
Then, in order to authenticate the user, the automatic
For example, in
Accordingly, in
Although not shown in the drawing, the automatic biometric authentication system may perform a user registration process of building a face feature database in advance before performing the user authentication process in
First, the automatic biometric authentication system acquires a face gesture image of each of a plurality of users.
Then, the automatic biometric authentication system extracts the face space-time characteristics of each of the plurality of users from the face gesture images of each of the plurality of users.
Here, the process of acquiring the face gesture image of each of the plurality of users and the process of extracting the face space-time feature of each of the plurality of users may be performed for each of the plurality of users in the same manner as the
For example, in the process of extracting the face space-time features of each of the plurality of users from the face gesture images of the plurality of users, the automatic biometric authentication system may include a plurality of users included in the face space- A spatial analysis is performed on the face gesture images of each of a plurality of users to extract respective static face information, and dynamic face information of each of a plurality of users included in the face space-time feature of each of a plurality of users is extracted The face time-space feature of each of the plurality of users can be extracted by fusing the static face information and the dynamic face information of each of the plurality of users by performing time analysis on the face gesture images of each of the plurality of users.
Particularly, the automatic biometric authentication system measures the quality of the face gesture image of each of the plurality of users before extracting the face space-time feature of each of the plurality of users from the face gesture images of each of the plurality of users, Space feature of each of the plurality of users can be extracted from the face gesture image of each of the plurality of users only when the quality of each face gesture image is equal to or greater than the reference value.
If the quality of the face gesture image of each of the plurality of users is less than the reference value, the automatic biometric authentication system can notify each of the plurality of users that the quality of the face gesture image is less than the reference value.
Then, the automatic biometric authentication system stores the face space-time characteristics of each of the plurality of users in the face feature database.
6 is a block diagram illustrating an automatic biometric authentication system according to an embodiment.
6, an automatic biometric authentication system according to an exemplary embodiment includes an
The acquiring
The
Specifically, the
At this time, the extracting
The
Specifically, the
In extracting the static face information of each of the plurality of users included in the face space-time feature of each of the plurality of users, the
The extracting
If the quality of the face gesture image of each of the plurality of users is less than the reference value, the measuring unit may notify each of the plurality of users that the quality of the face gesture image is less than the reference value.
The
For example, the
Accordingly, the
The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA) A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.
The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.
The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magnetic recording media such as floptical disks, Includes hardware devices that are specially configured to store and execute program instructions such as magneto-OTPical media and ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.
Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.
Claims (15)
Building a facial feature database in advance;
Obtaining a face gesture image of a user;
Extracting face space-time features from the face gesture image; And
Matching the face space-time features of each of the plurality of users stored in the face feature database with the face space-time feature of the user to authenticate the user;
Lt; / RTI >
The facial spatio-
The user's static face information and dynamic face information,
The step of pre-constructing the facial feature database
Obtaining a face gesture image of each of the plurality of users;
Measuring a quality of a face gesture image of each of the plurality of users;
Extracting a face space-time feature of each of the plurality of users from a face gesture image of each of the plurality of users when the quality of the face gesture image of each of the plurality of users is equal to or greater than a reference value; And
Storing face space-time features of each of the plurality of users in the face feature database
Wherein the biometrics authentication method comprises:
The step of extracting face space-time features from the face gesture image
Performing spatial analysis on the face gesture image to extract static face information of the user;
Performing temporal analysis on the face gesture image to extract dynamic face information of the user; And
Extracting the face space-time feature by fusing static face information and dynamic face information of the user
Wherein the biometrics authentication method comprises:
The step of extracting face space-time features from the face gesture image
Performing face analysis on the face gesture image based on a deep learning technique
Wherein the biometrics authentication method comprises:
Wherein the step of matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-
A face feature database, at least one of a nearest neighbor classifier, a sparse representation based classifier, and a support vector machine (SVM) Matching the spatiotemporal feature with the face space-time feature of the user
Wherein the biometrics authentication method comprises:
Wherein the step of matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-
Identifying a user having a face space-time feature matching the face space-time feature of the user among the plurality of users based on a result of matching the face space-time feature of each of the plurality of users with the face space-
Wherein the biometrics authentication method comprises:
The step of extracting face space-time features of each of the plurality of users from the face gesture images of the plurality of users
Performing spatial analysis on the face gesture images of each of the plurality of users to extract static face information of each of the plurality of users included in the face space-time feature of each of the plurality of users;
Performing time analysis on a face gesture image of each of the plurality of users to extract dynamic face information of each of the plurality of users included in the face space-time feature of each of the plurality of users; And
Extracting facial spatio-temporal features of each of the plurality of users by fusing static face information and dynamic face information of each of the plurality of users
Wherein the biometrics authentication method comprises:
Wherein measuring the quality of the face gesture image of each of the plurality of users comprises:
When the quality of the face gesture image of each of the plurality of users is less than a reference value, notifying each of the plurality of users
Further comprising the steps of:
An acquiring unit acquiring a face gesture image of a user;
An extracting unit extracting a face space-time feature from the face gesture image;
A face feature database storing face space-time features of each of a plurality of users; And
A matching unit for matching the face space-time feature of each of the plurality of users stored in the face feature database with the face space-time feature of the user,
Lt; / RTI >
The facial spatio-
The user's static face information and dynamic face information,
The facial feature database
Wherein the acquisition unit acquires a face gesture image of each of the plurality of users and measures a quality of a face gesture image of each of the plurality of users in a measurement unit further included in the automatic biometric authentication system, Wherein the extracting unit extracts the face space-time feature of each of the plurality of users from the face gesture images of the plurality of users when the quality of each face gesture image is equal to or greater than a reference value, An automatic biometric authentication system in which space-time features are stored and built in advance.
The extracting unit
Performing a spatial analysis on the face gesture image to extract static face information of the user and performing time analysis on the face gesture image to extract dynamic face information of the user, and extracts the face space-time feature by fusing static face information and dynamic face information of the user.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150144766 | 2015-10-16 | ||
KR20150144766 | 2015-10-16 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170045093A KR20170045093A (en) | 2017-04-26 |
KR101802061B1 true KR101802061B1 (en) | 2017-11-27 |
Family
ID=58705086
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160029793A KR101802061B1 (en) | 2015-10-16 | 2016-03-11 | Method and system for automatic biometric authentication based on facial spatio-temporal features |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101802061B1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10635893B2 (en) * | 2017-10-31 | 2020-04-28 | Baidu Usa Llc | Identity authentication method, terminal device, and computer-readable storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101297736B1 (en) * | 2013-05-07 | 2013-08-23 | 주식회사 파이브지티 | Face recognition method and system |
-
2016
- 2016-03-11 KR KR1020160029793A patent/KR101802061B1/en active IP Right Grant
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101297736B1 (en) * | 2013-05-07 | 2013-08-23 | 주식회사 파이브지티 | Face recognition method and system |
Also Published As
Publication number | Publication date |
---|---|
KR20170045093A (en) | 2017-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102299847B1 (en) | Face verifying method and apparatus | |
KR102415509B1 (en) | Face verifying method and apparatus | |
KR102466998B1 (en) | Method and apparatus for image fusion | |
KR102486699B1 (en) | Method and apparatus for recognizing and verifying image, and method and apparatus for learning image recognizing and verifying | |
US11908238B2 (en) | Methods and systems for facial point-of-recognition (POR) provisioning | |
WO2019071664A1 (en) | Human face recognition method and apparatus combined with depth information, and storage medium | |
US11200405B2 (en) | Facial verification method and apparatus based on three-dimensional (3D) image | |
KR102288302B1 (en) | Authentication method and authentication apparatus using infrared ray(ir) image | |
US20140169663A1 (en) | System and Method for Video Detection and Tracking | |
US20160217198A1 (en) | User management method and apparatus | |
JP2019109709A (en) | Image processing apparatus, image processing method and program | |
KR102459852B1 (en) | Method and device to select candidate fingerprint image for recognizing fingerprint | |
US10764563B2 (en) | 3D enhanced image correction | |
JP5087037B2 (en) | Image processing apparatus, method, and program | |
US20130083965A1 (en) | Apparatus and method for detecting object in image | |
KR20220076398A (en) | Object recognition processing apparatus and method for ar device | |
Bedagkar-Gala et al. | Gait-assisted person re-identification in wide area surveillance | |
KR102434574B1 (en) | Method and apparatus for recognizing a subject existed in an image based on temporal movement or spatial movement of a feature point of the image | |
CN109711287B (en) | Face acquisition method and related product | |
KR101802061B1 (en) | Method and system for automatic biometric authentication based on facial spatio-temporal features | |
Zhang et al. | A retrieval algorithm for specific face images in airport surveillance multimedia videos on cloud computing platform | |
US20240037995A1 (en) | Detecting wrapped attacks on face recognition | |
US10580145B1 (en) | Motion-based feature correspondence | |
KR102301785B1 (en) | Method and appauatus for face continuous authentication | |
KR102380426B1 (en) | Method and apparatus for verifying face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |