KR20150065529A - Method and apparatus for authenticating biometric by using face/hand recognizing - Google Patents

Abstract

The present invention relates to a biometric authentication apparatus and a method using recognition of a face and a hand. The biometric authentication apparatus includes: an image acquisition unit which acquires an image by photographing a subject; a face image analysis unit which detects a face area by analyzing the acquired image and extracts information to be used for authenticating a face; a hand image analysis unit which detects a hand area by analyzing the acquired image and extracts information to be used for authenticating a hand; a face authentication unit which authenticates the face by comparing the extracted information of a face area with pre-registered biometric information of the face; a hand authentication unit which authenticates the hand by comparing the extracted information of a hand area with pre-registered biometric information of the hand; a biometric authentication unit which executes biometric authentication with respect to the subject according to at least one from a face authentication result and a hand authentication result; and an output unit which outputs the results of biometric authentication. Therefore, costs of the biometric authentication apparatus are substantially reduced when compared to a case wherein a biometric apparatus for face recognition and a biometric apparatus for finger print recognition are independently installed in one place. A user can expect reliability of biometric authentication by a multi-modal method while executing similar processes of face authentication and hand authentication at the same time.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a biometric authentication device,

The present invention relates to a biometric authentication apparatus and method. And more particularly, to a biometric authentication apparatus and method for processing biometric authentication by combining face recognition and hand recognition results.

As is well known, features that are currently used in biometric authentication systems include face, voice, hand shape, iris, vein, and fingerprint, and research on each feature has been actively conducted.

Of these biometric authentication techniques, a face recognition apparatus (terminal) using face recognition has advantages of providing ease of use and fast authentication speed, and its occupation rate is gradually increasing.

However, the biometric authentication device for a large number of users is required to have excellent authentication performance with a low False Acceptance Rate (FAR). However, since the biometric authentication device using face recognition has a large number of users (for example, 1,000 or more) The authentication performance can not be satisfactorily satisfactory.

Therefore, research is underway to overcome the limitation of face authentication using a multi-modal method.

According to the related art, the biometric authentication technique using the multimodal method has an example of using the face recognition and the fingerprint recognition together, and the authentication performance can be greatly improved because the face and fingerprint characteristics having low correlation are used.

However, since a camera that captures an image for face recognition and a scanner for fingerprint recognition have completely different hardware characteristics, and the authentication procedure of face recognition and fingerprint recognition is very different, The bonding strength is very low. In other words, it can be said that there is no difference when compared with the case where the face recognition biometric authentication device and the fingerprint recognition biometric authentication device are respectively installed in one place.

Accordingly, there has been a problem in that cost increases significantly when a biometric authentication device using face recognition is combined with a fingerprint recognition technology and implemented in a multimodal manner.

In addition, in the aspect of the user who performs the authentication, the user has to take the inconvenience of using the facial authentication procedure and the fingerprint authentication procedure separately.

U.S. Published Patent Application 2006/0210119, published on September 21, 2006.

According to the embodiment of the present invention, a biometric authentication apparatus and method for processing biometric authentication by combining the results of face recognition and hand recognition are provided.

The problems to be solved by the present invention are not limited to those mentioned above, and another problem to be solved can be clearly understood by those skilled in the art from the following description.

A biometric authentication apparatus according to one aspect of the present invention includes an image acquiring unit that acquires an image by capturing an image of a subject; a facial image analyzing unit that grasps a face area through analysis of the acquired image, A hand image analyzing unit for recognizing a hand region through analysis of the obtained image and extracting information to be used for hand authentication; and a face authentication unit for comparing the extracted face region information with previously registered face biometric information, A hand authenticating unit for comparing the extracted hand region information with previously registered hand biometric information to process hand authentication; and a hand authentication unit for comparing at least one of the processing result of the face authentication and the processing result of the hand authentication A biometric authentication unit for processing the biometric authentication for the subject according to one or more processing results; and an output unit for outputting the biometric authentication result .

The information processing apparatus may further include a guide information generating unit for generating photographing posture information for guiding the photographing posture of the subject according to the position of the face area and the hand area or the degree of overlap between the face area and the hand area and outputting the photographing posture information through the output unit.

The face image analyzing unit may estimate the face region based on the position of the binocular after detecting the position of both eyes.

The facial image analyzing unit may extract the information of the facial region by calculating the slope of the virtual line connecting the both eyes, and then rotating the estimated facial region by an angle corresponding to the inclination.

The hand image analyzing unit may detect the hand region in the lump after detecting a lump in which the relatively bright pixels are gathered from the surroundings in the image except for the face region.

The hand image analyzing unit may extract the information of the hand region by separating the hand region and the finger region from the hand region and rotating the hand region toward a certain direction after grasping the direction of the hand.

According to another aspect of the present invention, there is provided a biometric authentication method including the steps of: analyzing a photographed image of a subject to determine a face area and a hand area; extracting information to be used for face authentication in the detected face area; Extracting information to be used for hand authentication in a hand region, processing face authentication by comparing the information of the extracted face region with previously registered face biometric information, A step of processing hand authentication by comparing hand biometric information; processing the biometric authentication with respect to the subject according to at least one process result of the face authentication process result and the hand authentication process result; And outputting the result of the processing of FIG.

The method may further include generating and outputting photographing posture information for guiding the photographing posture of the subject according to the position of the face area and the hand area or the overlapping degree between the face area and the hand area.

The step of recognizing the face area and the hand area may estimate the face area based on the position of the binocular after detecting the position of the binocular.

The step of extracting the information to be used for face authentication may include extracting information of the face area by calculating the slope of the virtual line connecting the two eyes and then rotating the estimated face area by an angle corresponding to the slope.

The step of recognizing the face area and the hand area may detect the hand area in the lump after detecting a lump in which pixels relatively bright compared to the surroundings are detected in the image except for the face area.

The step of extracting the information to be used for the hand authentication may extract the information of the hand region by separating the palm area and the finger area from the hand area and rotating the hand area toward a certain direction after grasping the direction of the hand.

According to the embodiment of the present invention, biometric authentication is performed by combining the results of face recognition and hand recognition.

Such a multimodal biometric authentication technique can share image acquiring means for acquiring images for face recognition and image acquiring means for acquiring images for hand recognition, as well as being integrally or separately installed in the biometric authentication apparatus Since the infrared light source for image capture can be also shared, the degree of coupling is very high in terms of hardware. Therefore, the cost is significantly reduced in comparison with the case where the face recognition biometric authentication device and the fingerprint recognition biometric authentication device are respectively installed in one place.

In addition, since similar image analysis procedures are used in the face authentication process and the hand authentication process, the degree of coupling is very high in the authentication process. Therefore, in the aspect of the user performing the authentication, the reliability of the biometric authentication by the multimodal method can be expected while the similar procedures of the face authentication and the hand authentication are performed at the same time. Further, in the case of hand authentication, since the intravenous vein can be used, the authentication performance is dramatically improved in comparison with the case where the face authentication is performed singly, because the internal composition is excellent.

Further, according to the embodiment, since the photographing posture information for guiding the correct photographing posture of the subject is provided according to the overlap degree of the face area and the hand area analyzed from the photographed image, and the good biometric information is extracted from the photographed image, Has an effect of providing excellent authentication performance with a low False Acceptance Rate (FAR).

1 is a block diagram of a biometric authentication device using face and hand recognition according to an embodiment of the present invention.
2 is a flowchart illustrating a biometric authentication method using face and hand recognition according to an embodiment of the present invention.
3 is an exemplary diagram illustrating a process of analyzing and authenticating an image acquired for biometric authentication according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The following terms are defined in consideration of the functions in the embodiments of the present invention, which may vary depending on the intention of the user, the intention or the custom of the operator. Therefore, the definition should be based on the contents throughout this specification.

1 is a block diagram of a biometric authentication device using face and hand recognition according to an embodiment of the present invention.

The biometric authentication apparatus 100 includes an image acquisition unit 110, a proximity sensing unit 120, an infrared ray generation unit 130, an information input unit 140, a control unit 150, An information storage unit 160, an output unit 170, an authentication interlocking unit 180, and the like. The control unit 150 includes a facial image analysis unit 151, a hand image analysis unit 152, a face authentication unit 153, a hand authentication unit 155, a biometric authentication unit 157, a guide information generation unit 159, .

1, the infrared ray generator 130 may be provided integrally with the biometric authentication device 100 or separately from the biometric authentication device 100. [ The infrared ray generator 130 serves as a light source that generates infrared light so that the image acquisition unit 110 of the biometric authentication apparatus 100 can capture images for biometric authentication.

The proximity sensing unit 120 senses that the subject is approaching the sensing effective range. For example, the proximity sensing unit 120 may sense the proximity of the subject in accordance with the received value of the infrared signal reflected by the subject after transmitting the infrared signal.

The image acquiring unit 110 acquires an image by photographing a subject. A part of the subject is absorbed and a part of the infrared light is reflected by the infrared ray generator 130. The image obtaining unit 110 receives the infrared ray reflected by the subject and acquires an image of the subject. Here, the image obtaining unit 110 may be implemented by a camera used in a general facial recognition biometric authentication device, and may be used for both face authentication and hand authentication when a hand is positioned with a face of a subject in an effective close- It is possible to obtain an image for authentication. In addition, the infrared light is used to minimize the influence of ambient light such as a fluorescent lamp, and the vein pattern formed on the hand (palm) of the subject can be recognized using the property that the vein hemoglobin does not reflect infrared light.

The information input unit 140 is an interface through which a user can input various commands and data. For example, it can be realized by a keypad integrally provided outside the biometric authentication device 100.

The facial image analyzing unit 151 analyzes the image obtained by the image obtaining unit 110, and extracts information to be used for face authentication from the detected facial region. The image analyzing unit 151 may analyze the image obtained by the image obtaining unit 110 to detect the position of one eye, which is one of the face elements, and then estimate the face area based on the positions of the two eyes. In addition, the facial image analyzing unit 151 can extract the information to be used for face authentication by calculating the slope of the virtual line connecting both eyes, and then rotating the estimated face region by an angle corresponding to the inclination.

The hand image analyzing unit 152 grasps the hand region by analyzing the image obtained by the image obtaining unit 110 and extracts information to be used for hand authentication from the hand region. The hand image analyzing unit 152 can detect a hand region within a lump after detecting a lump in which relatively bright pixels are gathered from the rest of the regions excluding the face region estimated by the facial image analyzing unit 151 . In addition, the hand image analyzing unit 152 can extract information to be used for hand authentication by separating the palm area and the finger area from the detected hand area and rotating the hand area toward a certain direction after grasping the direction of the hand. For example, the hand image analyzing unit 152 can extract a vein pattern, a hand pattern, a palm pattern, and the like as information to be used for hand authentication. In the case of the vein pattern, since the hemoglobin contained in the blood flowing through the vein formed in the palm of the hand or the palm of the hand absorbs the infrared light without reflecting it, the hand image analyzing section 152 is relatively dark It is possible to collect the pixels and extract the vein pattern.

The face authentication unit 153 compares the information of the face region extracted by the image analysis unit 151 with the previously registered face biometric information in the information storage unit 160 and processes the face authentication according to the matching or similarity .

The hand authentication unit 155 compares the hand region information extracted by the image analysis unit 151 with previously registered hand biometric information in the information storage unit 160 and processes hand authentication according to the matching or similarity .

The biometric authentication unit 159 processes the biometric authentication for the subject according to at least one of the processing results of the face authentication processing by the face authentication unit 153 and the hand authentication processing by the hand authentication unit 155 . The biometric authentication unit 159 can finally process the biometric authentication for the subject by combining the processing result of the face authentication and the processing result of the hand authentication, and only one of the face authentication and the hand authentication is normally authenticated If the authentication score proportional to the match degree is higher than the predetermined reference score, the final authentication result for the subject can be determined as normal. Alternatively, an authentication score obtained by the face authentication unit 153, an average score or a total score of the authentication score obtained by the hand authentication unit 155, and the like are compared with a predetermined reference score, and when the average score or the total score is larger than the reference score The final authentication result may be determined to be normal. On the other hand, when the authentication score by the face authentication unit 153 and the authentication score by the hand authentication unit 155 are compared with the respective reference scores, only when the two authentication scores are greater than the respective reference scores, Is determined to be normal, the FAR can be reduced.

The guide information generating unit 159 generates the photographing posture information for guiding the photographing posture of the subject according to the position of the face area and the hand area or the degree of mutual overlap between the images captured by the image analyzing unit 151, . For example, if the position of the face area and the hand area deviate from a preset area, for example, a central area, information for authentication can not be extracted properly. At this time, the photographing posture information for guiding the subject to change the position of the face and the hand is generated and provided. Alternatively, when the mutual overlap between the face area and the hand area is higher than the preset reference value, it is determined that the hand is an attitude that faces the face excessively, and the information of the face area can not be extracted properly. At this time, the photographing posture information for guiding the subject to lower the degree of overlap between the face and the hand or to separate them from each other is generated and provided.

The face biometric information required for the face authentication of the face authentication unit 153 and the hand biometric information necessary for the hand authentication of the hand authentication unit 155 are registered and stored in the information storage unit 160. [ In addition, various reference values and data necessary for the image analysis and authentication process may be stored in the information storage unit 160.

The output unit 170 outputs the processing result of the biometric authentication by the biometric authentication unit 157 and the photographing posture information by the guide information generating unit 159 to the outside through an image or voice to allow the user to recognize the image. In addition, the output unit 170 may display an image obtained in real time at the time of photographing by the image obtaining unit 110.

The authentication interlocking unit 180 can be implemented with various loads linked to each other according to the biometric authentication result by the biometric authentication unit 157. [ For example, if the biometric authentication device 100 is constructed as an access control system, it may be implemented as an actuator that opens and closes a door according to a biometric authentication result.

2 is a flowchart illustrating a biometric authentication method using face and hand recognition according to an embodiment of the present invention.

As described above, the biometric authentication method according to the embodiment includes steps (S201 to S209) of capturing and analyzing an image of a nearby subject and grasping a face area and a hand area.

The method further includes steps (S211 to S215) of generating and outputting photographing posture information for guiding the photographing posture of the subject in accordance with the detected position of the face area and the hand area or the overlapping degree of each other.

The method further includes a step (S217 to S225) of processing the face authentication by comparing the information of the detected face area with the previously registered face biometric information.

The method further includes a step (S227 to S237) of comparing the information of the hand region thus identified with the previously registered hand biometric information to process the hand authentication.

The method further includes a step (S239) of processing the biometric authentication for the subject according to at least one of the processing result of the face authentication and the processing result of the hand authentication.

Hereinafter, a biometric authentication apparatus according to an exemplary embodiment of the present invention performs biometric authentication on a subject using face and hand recognition will be described in more detail with reference to FIGS. 1 to 3. FIG.

First, the proximity sensing unit 120 senses that the subject approaches the sensing effective range according to the reception value of the infrared signal reflected by the subject after transmitting the infrared signal (S201).

When the proximity sensing unit 120 senses the proximity of the subject, the infrared ray generator 130 generates infrared light under the control of the controller 150 and the image is easily captured by the image acquisition unit 110 (S203).

Then, the image acquiring unit 110 acquires an image by photographing a subject. Here, the infrared ray generated by the infrared ray generator 130 is partially absorbed and partially reflected by the object, and the image acquisition unit 110 receives the infrared ray reflected by the object to acquire an image of the object (S205).

In this case, if the subject is a user who intends to perform biometric authentication, the image acquisition unit 110 places the hand in the vicinity of the face with the palm facing outward as exemplified in Fig. 3 based on predetermined rules, So that it is possible to acquire authentication images that can be used for authentication.

In this way, the image of the object acquired by the image acquisition unit 110 is provided to the facial image analysis unit 151 and the hand image analysis unit 152, and the facial image analysis unit 151 analyzes the acquired image The hand image analyzing unit 152 identifies the hand region through analysis of the obtained image (S207 and S209).

Here, the facial image analyzing unit 151 analyzes the image acquired by the image acquiring unit 110 and detects the position of one of the facial elements. For example, the positions of the eyes 301 and 303 can be detected using a known adaboost algorithm or the like in the image illustrated in FIG. Then, the face region is estimated based on the positions of both eyes. For example, the face region can be estimated to be a rectangular shape 305.

If the hand image analyzing unit 152 detects the hand region later after the face image analyzing unit 151 first detects the face region, it is preferable that the remaining region excluding the face region is relatively After detecting a blob in which bright pixels are gathered, it is possible to grasp the hand area more accurately and quickly by grasping the hand area in the chunk.

Here, the guide information generating unit 159 generates the photographing posture information for guiding the photographing posture of the subject in accordance with the position of the face area and the hand area or the degree of overlap between them, which is grasped by the image analyzing unit 151. [

For example, the guidance information generation unit 159 determines the position of the face area and the hand area (S211). If any of the face area and the hand area is out of a predetermined area, for example, the central area, (S213). ≪ / RTI > At this time, the photographing posture information for guiding the subject to change the position of the face and the hand is generated.

Alternatively, the guide information generation unit 159 calculates the overlap degree between the face area and the hand area (S211), compares the calculated overlap and the preset reference value, and determines whether the subject is in a positive posture for biometric authentication (S213). For example, when the overlap degree between the face area and the hand area is higher than the preset reference value, it is determined that the hand is an attitude that overshoots the face excessively, and the information of the face area can not be extracted properly. And the photographing posture information for guiding the degree of overlap of the hand to be lowered or separated from each other.

Then, the output unit 170 outputs the photographing posture information generated by the guide information generating unit 159 through a screen, a voice, or the like so that a subject, that is, a user who performs biometric authentication can recognize the subject, (Step S215).

Next, if it is determined that the subject is in a correct posture for biometric authentication, the facial image analysis unit 151 calculates the slope of the virtual line connecting the binarized face image (S217) (Step S221). The face area information is compared with the face biometric information registered in the information storage unit 160 (step S221). Here, the fact that the face authentication unit 153 rotates the face area and then extracts the information for authentication is because the accuracy of the biometric information extracted from the image photographed in a state where the head of the subject is inclined can be lowered. That is, if the information for authentication is extracted after correcting the angle of the face region, the accuracy of the biometric information is improved and the authentication reliability is improved accordingly.

In addition, the hand image analyzing unit 152 separates the palm area and the finger area from the hand area, rotates the hand area toward a predetermined direction after grasping the direction of the hand, And extracts the information of the hand region for comparison (S227 to S233).

Here, the hand image analyzing unit 152 rotates the hand image in a certain direction in order to extract only the correct information at all times since the plurality of users do not always place the hand in the same direction. That is, if the information for authentication is extracted after correcting the angle of the hand as described above, the accuracy of the biometric information is improved and the reliability of the authentication is improved accordingly.

For example, the hand image analyzing unit 152 can extract a vein pattern, a hand pattern, a palm pattern, and the like as information to be used for hand authentication. That is, it is possible to extract shape information of a hand or a palm or to extract vein pattern information formed in the human body. In the case of the vein pattern, since the hemoglobin contained in the blood flowing through the vein formed in the palm of the hand or the palm of the hand absorbs the infrared light without reflecting it, the hand image analyzing section 152 is relatively dark It is possible to collect the pixels and extract the vein pattern.

The hand image analyzing unit 152 analyzes the image obtained by the image acquiring unit 110 using a known ASM (Active Shape Model) algorithm or the like to calculate the hand image of the palm 307 and the finger 309 ). If the facial image analyzing unit 151 has already completed the detection of the facial region, the hand image analyzing unit 152 extracts a relatively bright pixel from the obtained image of the subject, excluding the face region, Once the gathered blobs are detected, the hand area can be grasped more accurately and quickly in the chunk.

Then, the face authentication unit 153 compares the information of the face region extracted by the face image analysis unit 151 with the previously registered face biometric information in the information storage unit 160 and, based on the matching or similarity, (S223 and S225).

The hand authentication unit 155 compares the information of the hand region extracted by the hand image analyzing unit 152 with previously registered hand biometric information in the information storage unit 160, (S235 and S237).

Next, the face authentication result by the face authentication unit 153 and the hand authentication unit 155 are provided to the biometrics authentication unit 157, and the biometrics authentication unit 159 receives the face authentication result from the face authentication unit 153 And processes the biometric authentication of the subject according to at least one of the processing results and the hand authentication processing result by the hand authentication unit 155. [

The biometric authentication unit 159 can finally process the biometric authentication for the subject by combining the processing result of the face authentication and the processing result of the hand authentication, and only one of the face authentication and the hand authentication is normally authenticated If the authentication score proportional to the match degree is higher than the predetermined reference score, the final authentication result for the subject can be determined as normal. Alternatively, an authentication score obtained by the face authentication unit 153, an average score or a total score of the authentication score obtained by the hand authentication unit 155, and the like are compared with a predetermined reference score, and when the average score or the total score is larger than the reference score The final authentication result may be determined to be normal.

On the other hand, when the biometric authentication unit 157 compares the authentication score by the face authentication unit 153 and the authentication score by the hand authentication unit 155 with the respective reference scores, the two authentication scores are all more than the respective reference scores If the final authentication result is determined to be normal only when it is large, the FAR can be reduced (S239).

In this way, the biometric authentication result determined by the biometric authentication unit 157 of the control unit 150 is outputted through the output unit 170 as an image or voice so that the user can recognize the biometric authentication result.

In addition, the authentication interlocking unit 180 can interlock various loads according to the biometric authentication result by the biometric authentication unit 157. [ For example, if the biometric authentication device 100 has constructed the access control system, the access door can be opened and closed by driving the actuator according to the biometric authentication result.

As described above, the multimodal biometric authentication technology that combines face recognition and hand recognition can capture an image for image recognition and hand recognition by a single image acquisition means, that is, a camera or the like, Since the IR light source for image capture, which can be installed integrally with the apparatus or can be installed separately, can also be shared, the degree of coupling is very high in terms of hardware. Therefore, the cost is significantly reduced in comparison with the case where the face recognition biometric authentication device and the fingerprint recognition biometric authentication device are respectively installed in one place.

In addition, since similar image analysis procedures are used in the face authentication process and the hand authentication process, the degree of coupling is very high in the authentication process. Therefore, in the aspect of the user performing the authentication, the reliability of the biometric authentication by the multimodal method can be expected while the similar procedures of the face authentication and the hand authentication are performed at the same time. Further, in the case of hand authentication, since the intravenous vein can be used, the authentication performance is dramatically improved in comparison with the case where the face authentication is performed singly, because the internal composition is excellent.

Combinations of the steps of each flowchart attached to the present invention may be performed by computer program instructions. These computer program instructions may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus so that the instructions, which are executed via a processor of a computer or other programmable data processing apparatus, Lt; / RTI > These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible to produce manufacturing items that contain instruction means for performing the functions described in each step of the flowchart. Computer program instructions may also be stored on a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible for the instructions to perform the processing equipment to provide steps for executing the functions described in each step of the flowchart.

In addition, each step may represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative embodiments, the functions mentioned in the steps may occur out of order. For example, the two steps shown in succession may in fact be performed substantially concurrently, or the steps may sometimes be performed in reverse order according to the corresponding function.

The foregoing description is merely illustrative of the technical idea of the present invention and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

110: image acquiring unit 120: proximity sensing unit
130: infrared ray generator 140: information input unit
150: control unit 151: facial image analysis unit
152: hand image analysis unit 153: face authentication unit
155: hand authentication unit 157: biometrics authentication unit
159: Guide information generating unit 160: Information storing unit
170: output unit 180: authentication interlocking unit

Claims (12)

An image acquiring unit that acquires an image by photographing a subject;
A face image analyzing unit for recognizing a face region through analysis of the obtained image and extracting information to be used for face authentication,
A hand image analyzing unit for recognizing a hand region through analysis of the obtained image and extracting information to be used for hand authentication;
A face authentication unit for comparing face information of the extracted face region with previously registered face biometric information to process face authentication,
A hand authentication unit for comparing the extracted hand region information with previously registered hand biometric information to process hand authentication;
A biometric authentication unit for processing the biometric authentication for the subject according to at least one result of the processing result of the face authentication and the processing result of the hand authentication;
And an output unit outputting a result of the biometric authentication process. The method according to claim 1,
Further comprising: a guide information generating unit for generating photographing posture information for guiding the photographing posture of the subject in accordance with the position of the face area and the hand area or the overlapping degree between the face area and the hand area, and outputting the photographing posture information through the output unit. The method according to claim 1,
Wherein the face image analyzing unit estimates the face region based on a position of both eyes after detecting a position of both eyes. The method of claim 3,
Wherein the face image analyzing unit calculates the slope of the virtual line connecting the two eyes and then rotates the estimated face area by an angle corresponding to the slope to extract the information of the face area. The method according to claim 1,
Wherein the hand image analyzing unit grasps the hand region in the lump after detecting a lump in which pixels relatively bright compared to the surroundings are detected in the image excluding the face region. The method according to claim 1,
Wherein the hand image analyzing unit extracts information of the hand region by separating the hand region and the finger region from the hand region and rotating the hand region toward a predetermined direction after grasping the direction of the hand. Analyzing a photographed image of a subject to grasp a face region and a hand region;
Extracting information to be used for face authentication in the identified face area;
Extracting information to be used for hand authentication in the identified hand region,
Processing the face authentication by comparing the information of the extracted face region with previously registered face biometric information,
Processing the hand authentication by comparing the extracted hand region information with previously registered hand biometric information,
Processing the biometric authentication for the subject according to at least one process result of the face authentication process result and the hand authentication process result;
And outputting the processing result of the biometric authentication. 8. The method of claim 7,
Further comprising the step of generating and outputting photographing posture information for guiding the photographing posture of the subject according to the position of the face area and the hand area or the overlapping degree of each other. 8. The method of claim 7,
Wherein the step of recognizing the face region and the hand region estimates the face region based on the position of the binocular after detecting the position of both eyes. 10. The method of claim 9,
Wherein the step of extracting the information to be used for face authentication includes a step of calculating a slope of a virtual line connecting the two eyes and then rotating the estimated face area by an angle corresponding to the slope to extract information of the face area . 8. The method of claim 7,
Wherein the step of recognizing the face region and the hand region grasps the hand region in the lump after detecting a lump in which pixels relatively bright compared to the surroundings are detected in the image excluding the face region. 8. The method of claim 7,
Wherein the step of extracting the information to be used for the hand authentication includes extracting information of the hand region by separating the palm area and the finger area from the hand area and rotating the hand area toward a certain direction after grasping the direction of the hand.

Images