JP2000215308A - Biometric information authentication device and method - Google Patents

Abstract

(57) [Summary] [Problem] The balance between the performance and comfort of personal authentication and the strength against environmental change can be adjusted according to the situation,
Improve convenience. SOLUTION: A means (1) for acquiring biometric information of a person to be authenticated, a means (2, 3) for extracting features of the person to be authenticated from input information thereof and forming biometric feature information, A plurality of identification means for comparing (4, 5) registration information prepared in advance for each category and determining a category to which the subject belongs, and at least one of the biometric information receiving means and the identification means are provided. In the biometric information authentication device, when performing biometric information authentication using an authentication logic configured by combining them, the biometric information receiving unit and the identification unit are selected by selecting one from a plurality of authentication logic modes. It has a controllable mode management means (6).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a personal authentication device and a personal authentication method using biometric information.

[0002]

2. Description of the Related Art Hitherto, an authentication technology for authenticating an individual from biological information has been studied in various fields with the aim of realizing higher security. Above all, an individual authentication system based on face image recognition using image processing technology has attracted attention because of the comfort that a target person hardly spends time and effort for inputting biometric information required for authentication. However, facial image recognition is more comfortable than other recognition methods using biometric information such as iris and fingerprint, but its recognition performance is inferior, and this has been an obstacle to its application to personal identification systems. . In order to realize high security using face image recognition, both the rate of identifying a person (passing rate of the person) and the rate of rejecting persons other than the person (rejection rate of others) do not maintain high enough. must not.

However, in the current face image recognition, an image of a person to be authenticated and registered information are compared and collated in a predetermined feature space to obtain a similarity, and the authentication is performed based on whether or not the similarity exceeds a predetermined threshold. It is common to determine whether or not the person is the person of the registration information, but if the threshold used as the criterion for determination is fixed, a sufficient height cannot be obtained at least in one of the above-mentioned rates. Inconvenience occurs.

[0004] For example, the relationship between the exclusion rate of another person and the pass rate of the person is shown in FIG.
If the threshold value is set high as in (A), the pass will be low for others to pass, but at the same time the person may be rejected. If the threshold is set low as in (B), the pass will always occur Even if you can, others may pass. That is, it has been difficult for the conventional personal authentication system using face image recognition to sufficiently achieve both high security and comfort including that a regular user is not rejected. Although the comfort in inputting biometric information is not as good as a face image, the same problem as described above also occurs in authentication for voice as biometric information.

[0005]

As described above, it is difficult to keep both the pass-through rate and the rejection rate of other persons sufficiently high by the conventional biometric information authentication using a face or voice, and furthermore, environmental conditions such as lighting and noise are difficult. It is difficult to realize a personal authentication system having sufficient authentication performance and comfort using only a single authentication logic, including the strength of the authentication.

[0006] The present invention has been made in view of such problems, and aims at adjusting the balance between the performance and the comfort of personal authentication and the strength against environmental fluctuations according to the situation. It is an object of the present invention to provide a system which is made possible and thus has improved convenience.

[0007]

According to the present invention, in order to achieve the above object, an authentication logic for identifying and authenticating a person using input information received from a person to be authenticated is applied to one input information. A plurality of built-in processing means (mode management means) are provided which can realize convenience by controlling authentication performance and comfort by managing / controlling them.

[0008]

DESCRIPTION OF THE PREFERRED EMBODIMENTS First, an embodiment of a biometric information authentication apparatus and a method thereof according to the present invention will be described with reference to the drawings. Here, an embodiment of authentication using a face image as biometric information will be described.

FIG. 1 is a block diagram showing the basic structure of the biometric information authentication device according to the present invention. The biometric information receiving unit A is a unit that acquires input biometric information necessary for authentication from a person to be authenticated. The basic components are an image input unit 1, a face detection unit 2, and a feature extraction unit 3. The image input unit 1 is a processing unit that acquires an image of a certain area including a face image of a person to be authenticated, and transmits the input image information to the face detection unit 2 as digital data. The face detection unit 2 analyzes the input image information sent from the image input unit 1 to determine whether a face image is included, and if so, extracts the face image information to extract a feature image. 3 is a processing means to send to 3. The feature extracting unit 3 is a processing unit that calculates a feature amount of the face image in the input image information by a feature extracting algorithm selected by the mode managing unit C, and sends the result to the matching unit 4 as biometric feature information.

The identification section B is means for judging whether the person to be authenticated is included in the registered persons or in which category it is classified. The identification section B comprises a collation section 4 and an authentication information storage section 5. The matching unit 4 checks the similarity by comparing the biometric feature information sent from the biometric information receiving unit A with the registered authentication information by using the identification method determined by the mode control information sent from the mode management unit C. This is processing means for determining whether the subject to be authenticated matches any of the registered persons. The authentication information storage unit 5 is a processing unit that stores authentication registration information used when the matching unit 4 obtains a similarity, and stores the authentication registration information there when the matching unit 4 performs identification. Transmit.

The mode management section C is means for managing / controlling an identification method used when the collation section 4 identifies the biometric characteristic information of the person to be authenticated by comparing it with the registered information, and performs identification based on various information. It has a processing means for determining the method and transmitting the result as mode control information to the collating unit 4, that is, a mode determining unit 6. As a result, the system controls the authentication performance and the comfort, and the convenience of the person to be authenticated can be improved.

The following five are examples of authentication logic management / control patterns by the mode management means. (1) Mode control by time. (2) Mode control based on information sensed by sensors. (3) Mode control based on environmental information included in the input image. (4) Mode control by an external operation by the administrator and the subject. (5) Control of a mode for selecting which of a plurality of different types of biometric information to acquire from a subject to be used for authentication. (6) Control of the mode for selecting which of the biometric information and the non-biometric authentication information is to be obtained from the subject for use in authentication.

(1) to (3) have some means in the biometric information authentication apparatus for automatically collecting information for controlling the mode, and the mode management unit C controls the mode based on the information. System. Such a mode control mode is called automatic mode control. (4) is characterized in that the biometric information authentication device includes an external input device for sending a command for the manager and the subject to be instructed to control the mode to the mode management unit C. . Mode management unit C
Determines the mode based on the information sent from it and transmits it to each unit. Such a mode control mode is called manual mode control. (1) to (4) are embodiments in which the mode management unit pays attention to information that is an element for determining a mode, but (5) and (6) show which of the subjects to be authenticated to use for authentication. In this embodiment, the mode management unit controls whether to acquire such input information. Examples of each of the authentication mode control mechanisms (1) to (6) will be described. (Embodiment 1) The first embodiment is the time mode control of (1). In this case, when a preset time comes, the mode management means issues an instruction (mode control information) to the identification means to switch to another predetermined identification method. That is, the identification means can perform an identification operation using an identification method that differs depending on a preset time zone.

Here, a biological information authentication apparatus incorporating the time mode control system will be described.

Changes in the pass-through rate and the rejection rate for other persons with respect to a threshold for determining authentication (FIG. 20: Osamu Yamaguchi, Kazuhiro Fukui: "Face Recognition System Using Video", PRMU)
97-50, pp. 17-24 (1997)), it is impossible to fix both high enough regardless of where the threshold is set. Therefore, two thresholds for obtaining a sufficient height for either one are set. In the present embodiment, the threshold setting 1 (personal convenience mode) “the pass rate is high but the exclusion rate is slightly low” and the threshold setting 2 (safety priority mode) that the pass rate is low but the exclusion rate is high. Prepare two.

By switching these modes depending on the time zone, a security system that emphasizes comfort during the day and security during the night is realized. (FIG. 2) In the time control mode, the mode management unit C can control the threshold value required to identify the user in two ways depending on the time zone. Threshold setting 1 is used during the day when less security is required, and threshold setting 2 is used at night when sufficient security needs to be obtained. This is the mode manager C
Is achieved by changing the threshold value without being intentionally operated by a human, and such mode control is called automatic mode control. The flow of processing of the security system realized by properly using these two threshold settings will be described with reference to the flowchart of FIG.

The image input unit 1 acquires image information using a camera installed in consideration of the face of the person to be authenticated, and transmits the image information to the face detection unit 2. The face detection unit 2 sends the detected face image information to the feature extraction unit 3 only when a face is detected in the input image (step S1). The feature extraction unit 3 analyzes the sent face image information and sends the obtained feature amount to the matching unit 4 as biometric feature information. The mode determining unit 6 issues a command to the collating unit 4 to perform identification in the personal convenience mode when the operating time period is daytime and in the safety priority mode when it is nighttime (step S2). The matching unit 4 obtains the feature similarity by comparing both the biometric feature information sent from the feature extracting unit 3 and the authentication registration information sent from the authentication information storage unit 5, and the largest one of the similarities is the mode. Identification is performed based on whether or not the threshold setting selected according to the instruction from the determination unit 6 is exceeded, and the result is output (step S).
3). In this embodiment, switching between two modes has been described. However, the number of modes is not limited to two, and a plurality of three or more modes may be used. This is explained in the following Examples (2) to
The same applies to (4). (Example 2) Face image recognition is not sufficiently robust to variations in lighting conditions, and a feature extraction algorithm created robustly to variations in lighting has lower authentication performance under reference lighting conditions than otherwise. There is a problem. Therefore, an illuminance sensor is newly provided, and the intensity of the illumination is sensed by this sensor, and a mode control example corresponding to the above (2), which switches the feature extraction algorithm to the one robust to illumination according to the intensity, is introduced. An example in which such mode control is realized is a second embodiment according to the present invention described below.

The apparatus according to the present embodiment constitutes a biometric information authentication apparatus which is robust to illumination by using a face image as an authentication item and using two feature extraction methods having different properties with respect to illumination conditions. The two feature extraction methods include an algorithm 1 "a sufficiently high recognition rate can be achieved at a reference illumination intensity, but a poor recognition rate otherwise" algorithm 1 and a "recognition algorithm 1 at a reference illumination intensity""Algorithm 2 reduces the rate but otherwise allows higher recognition rates."
It is. The authentication when each is used is assumed to be a normal mode and an illumination robust mode. (FIG. 4) Here, the algorithm 1 and the algorithm 2 will be described.

A face image obtained by photographing a person's face under certain lighting conditions is a reflection luminance image created by reflecting illumination light on a three-dimensional object called a face. The apparatus inputs such a reflection luminance image of the face, normalizes the image to a predetermined size, and further normalizes the luminance range to obtain an image pattern. The above-mentioned algorithm 1 is a feature extraction algorithm in which the image pattern based on the reflected luminance expression generated in this way is used as the biological feature information.

However, the image pattern based on the expression of reflected luminance includes deformation of an object (a change in a three-dimensional shape such as a change in facial expression), illumination change (a change in illumination spectral intensity or illumination direction due to time of day or weather), and a change in the posture of the object ( Various changes occur due to changes in the imaging direction such as a change in the orientation of the face. In particular, it is difficult to make the registration information for collation learn patterns in various illumination directions in advance, in spite of the instability difference that the shading of the image pattern changes dramatically in the illumination direction. Unlearned lighting fluctuations give unlearned lighting brightness to all input patterns.
Therefore, the algorithm 1 causes a serious decrease in recognition rate under illumination conditions different from those at the time of learning.

In order to prevent the recognition rate from being lowered due to such illumination fluctuations, biometric feature information based on feature amounts (ie, image representations) that are hardly affected by lighting and that preserve feature information unique to an object (person's face) is preserved. Must be used for recognition. Since the illumination fluctuation gives a strong fluctuation to the reflection luminance image of the object, the influence of the illumination fluctuation is inevitable as long as the reflection luminance expression is used as the biological feature information. On the other hand, it is known that a certain kind of image expression derived from the reflection luminance pattern has a constancy that is hardly influenced by the illumination condition.

For example, a reference (Yael Moses e)
t al. , "Face Recognition:
the Problem of Compensat
ion for Changes in Illumi
nation Direction ", Processe
Ding of ECCV'94, 1994)
A luminance gradient expression obtained by differentiating a reflected luminance image as a feature amount effective against illumination fluctuation (hereinafter referred to as a differential image)
Has been proposed.

The first-order differentiation of the reflected luminance image corresponds to an operation for obtaining a rate of change in luminance, and a portion (edge) where the luminance changes stepwise is extracted. On the object surface, there is a high / low pattern of reflectivity peculiar to the object, and in places with low reflectivity the reflection luminance always changes regardless of the illumination intensity, and in places with high reflectivity the reflection luminance changes depending on the illumination intensity. I do. Therefore, the first-order differential image expresses (a) a change in reflectance at a location where illumination is applied and (b) a shadow change at a location with high reflectance. (A) is an edge where there is intensity variation due to illumination variation but there is no positional variation as long as the posture of the object does not change, and (b) both intensity and position vary due to illumination variation even when the posture of the object does not change. Edge.

The slope of the edge extracted by the differentiation depends on the nature of the operator in the differentiation process. Generally, a smoother edge can be extracted as the operator is larger, and only a steep edge is extracted as the operator is smaller. Since the type of differential operator to be used depends on the intensity of illumination contrast, etc., in the present embodiment, a control for reducing the size of the differential operator to be used in accordance with the magnitude of the illumination intensity is also provided in the mode. Performed by the decision unit.

The first effect of the differential image on the illumination variation is that (a) preserves the characteristic of the reflectance pattern unique to the object according to the posture of the object. This demonstrates the validity of using differential patterns for object recognition. The second effect of the differential image on the illumination variation is that the difference in the reflectance pattern on the surface of the object is large, that is, the stronger the texture of the object, the stronger (a) appears than (b). In particular, when the object has a smooth curved surface, the shadow due to illumination shows a gradual change, so that (b) is further weakened. This means that the unlearned illumination fluctuation, which was a large-scale fluctuation in the reflection luminance expression, is suppressed to the unlearned fluctuation related to (b) in the differential image (localization and miniaturization). The differential image is considered to have illumination fluctuation constancy due to such an effect. The algorithm 2 receives a reflected luminance image of the face, differentiates the image, normalizes the image to a predetermined size, and further normalizes the luminance range to obtain an image pattern. As a result, in Algorithm 2, the effect of illumination fluctuation is localized and miniaturized, and the illumination fluctuation robustness is improved.

However, Algorithm 2 uses only texture information such as eyebrows and eyes as individuality by dropping shadow information (reflecting the three-dimensional shape characteristics of the individual's face) on the forehead and cheek of the face. The recognition rate is slightly lower than Algorithm 1 which can recognize individuality based on all of these clues. As a result, Algorithm 1 is an algorithm that "can achieve a very high recognition rate under the lighting conditions at the time of learning the registered information for collation, but the recognition rate extremely deteriorates if the lighting conditions deviate from this." The algorithm is "a reasonably high recognition rate can be achieved under the lighting conditions at the time of learning the registered information for verification, and the recognition rate is stable even if the lighting conditions fluctuate." Note that any variation in illumination intensity is absorbed by normalizing the brightness of the image pattern in any of the algorithms.

FIG. 5 shows a block configuration of this embodiment. The structure diagram is very similar to FIG. 1, but there are two different parts.
First, a device for sensing lighting conditions around the subject is installed. The illumination sensor unit 17 converts the intensity of the illumination in the target range into digital data (illumination intensity information).
Is a processing means for transmitting to the mode determination unit 16 as Second, what is controlled by the mode determining unit 16 is that the mode is changed to the feature extracting unit 13 instead of the collating unit 14. In order to create a system that is robust to lighting, the algorithm used for feature extraction must be changed to one that is robust to lighting, and it must act on the feature extraction unit 13.

Based on the above, the processing flow of the apparatus of this embodiment will be described with reference to the flowchart of FIG. First, similarly to the first embodiment, face image information is sent to the feature extraction unit 13 by the face detection unit 12 that extracts face features from the input image acquired by the image input unit 11 (step S1).
1). The illumination sensor unit 17 always senses the illumination intensity around the subject and transmits the illumination intensity information to the mode determination unit 16. When the mode determining unit 16 determines that the current illumination intensity does not change much from the illumination intensity at the time of learning the registration information for collation and is within a range that is sufficiently permissible with the algorithm 1, the normal mode is set, and the change in the illumination intensity is too large. If it is determined that a command is issued to the feature extraction unit 13 each time to adopt the illumination robust mode (step S
12). The feature extraction unit 13 selects an algorithm according to the selection and performs a feature extraction operation (step S13). This allows the system to achieve a higher overall recognition rate than using each mode alone. The biometric feature information generated by the feature extracting unit is sent to the matching unit 14, where the biometric feature information is compared with the authentication registration information sent from the authentication information storage unit 15 to perform authentication.

As a modification, by changing the mode, it is also possible to change the identification algorithm used in the matching unit 14 for each feature amount generated in the feature extraction unit 13. (FIG. 7) (Embodiment 3) Similarly to the above-described second embodiment, a biometric information authentication device that is robust to lighting conditions may be implemented using the mode control example (3) corresponding to the above (3). it can. The basic block configuration is as shown in FIG. In this device, an illumination intensity analysis unit 27 is newly provided between the face detection unit 22 and the feature extraction unit 23 instead of the illumination sensor as compared with FIG. 5 of the second embodiment. The illumination intensity analysis unit 27 analyzes the face image information input from the face detection unit 22 and sends, for example, the average luminance of the face image information to the mode determination unit 26 as illumination intensity information. Upon receiving the illumination intensity information, the mode determination unit 26 determines a feature extraction algorithm, and instructs the feature extraction algorithm to the feature extraction unit 23. The face image information acquired by the face detection unit 22 is passed through the feature extraction unit 23 and passed to the collation unit 2.
4 is identified. At this time, the feature extraction algorithms used in the feature extraction unit 23 are the same two modes as in the second embodiment: the normal mode and the illumination robust mode.

Next, the flow of processing in this apparatus will be described. Although the subject of each processing step is different, the flowchart is the same as FIG. 6 used in the second embodiment. First, the image input unit 21 acquires an image of a predetermined area and sends it to the face detection unit 22 as input image information. When detecting a face in the input image, the face detection unit 22 extracts and outputs face image information (step S11). The face image information is transferred to the illumination intensity analysis unit 27 as it is, and for example, the average luminance in the image is calculated as the illumination intensity. The illumination intensity information is sent to the mode management unit C and becomes an element for determining an optimal mode. The mode determination unit 26 in the mode management unit C determines an algorithm to be used for feature extraction based on the received illumination intensity information, and uses the result as mode control information as the feature extraction unit 2.
3 (step S12).

If the illumination intensity does not change much from the illumination intensity at the time of learning the registration information for collation, and the algorithm 1 is within a sufficiently allowable range, the normal mode is selected. If the illumination intensity changes too much, the illumination robust mode is selected. Put out. The feature extracting unit 23 extracts features from the face image information by the face detecting unit 22 using an algorithm determined according to the mode control information (step S13), and sends the acquired biometric feature information to the matching unit 24. In the identification unit B, authentication is performed in the matching unit 24 using the authentication registration information sent from the authentication information storage unit 25 and the biometric feature information sent from the feature extraction unit 23. With such a system, the person to be authenticated can receive personal authentication that is robust to lighting as in the case of the second embodiment.

In all of the three embodiments described above, the mode management unit B automatically determines the mode based on information obtained by any one of the function blocks in the apparatus. The fourth embodiment described below is different from these, and the mode adopted by the system can be controlled by sending a signal for operating the mode by the administrator or the authenticated person to the mode management unit B. . Such mode control will be referred to as manual mode control. (Embodiment 4) Here, the mode control corresponding to the above (4) is adopted, and a signal (mode selection information) for an administrator or a person to be authenticated to select a mode from the outside to the mode management unit C is adopted. A description will be given of a security system (apparatus a) and (apparatus b) using a biometric information authentication apparatus for inputting and determining a mode to be adopted according to the input. Regarding the mode control by the person to be authenticated of (apparatus b), an embodiment will be described in which, in addition to biometric information, non-biometric authentication information using a storage such as a password or an ID card or physical means is used. In the following, two identification methods (threshold setting 1, 2) used in the first embodiment as an embodiment of this device will be described.
A system (apparatus a) and an apparatus (apparatus b) provided with are described.

First, as an embodiment of the device a controlled by the administrator, a personal convenience mode with an emphasis on comfort while the administrator is at the reception, for example, near the device, and a safety priority with an emphasis on safety when leaving the reception. A system adopting the mode will be described. This is based on the premise that a sufficient fraud deterrence can be obtained even in the personal convenience mode because the administrator checks the person to be passed when the administrator is at the reception.

FIG. 9 shows the block structure. The difference from the first embodiment is that the mode determining unit 36 does not control the mode according to the time zone, but instead determines the mode according to the signal from the external input unit 39 for the manager. The administrator external input unit 39 is a processing unit that transmits a signal input by the administrator to the mode determination unit 36. By sending a signal (mode selection information) for switching the mode, the administrator can obtain the convenience of controlling the mode according to his / her own convenience.

The flow of processing when this apparatus is used will be described with reference to the flowchart of FIG. Normally, this apparatus is controlled by the mode determination unit 36 so that the personal convenience mode having a low threshold is used when the authentication is performed by the collation unit 34. When the administrator leaves the reception, the mode determining unit 3 sends a signal for switching from the personal convenience mode to the safety priority mode using the external input unit 39 for the administrator.
Input for 6. Mode decision unit 3 receiving this signal
6 issues an instruction to switch the authentication mode to the safety priority mode having a higher threshold (mode control information). The subsequent information transmission process is the same as in the first embodiment. The input image information obtained by the image input unit 31 is sent to the face detection unit 32. Therefore, when it is recognized that a face is included in the image, the face image information is sent (step S31), and the feature extracting unit 33 sends the biometric feature information obtained by analyzing the face image information to the matching unit 34. Upon receiving this, the collation unit 34 performs authentication in the safety priority mode as instructed earlier (step S32) (step S33).

When the administrator who has returned to the reception sends a signal to the mode management unit C so as to switch the authentication mode to the personal convenience mode again, it is possible to return to the original state.

Next, the device b will be described. As an example of this device, a person to be authenticated can specify his / her registered authentication information by a personal ID such as a wireless tag, an ID card, and a password, and perform one-to-one personal authentication using the registered authentication information and the input face image information. A security system using the biometric information authentication device will be described. FIG. 11 shows a basic configuration of the device b. The system normally operates in a security priority mode, and some subjects may be rejected even though they are registered. In such a case, the person to be authenticated inputs the personal identification number to the mode determining unit 46 using the externally inputting part 49 for the person to be authenticated, and verifies the authentication mode of the specific individual designated by the personal identification number with a high pass rate. The user can be authenticated again after switching to the personal identification mode. As a result, it is possible to realize a very convenient security system in which the probability that a registered person who is a registered person is finally rejected while maintaining sufficiently high security is kept low.

The difference from the configuration of the device a is that the external input device is a device for inputting the personal ID for the user to be authenticated, and the external input unit 49 for the user to be authenticated. A processing flow when this system is used will be described. The case in which the normal safety priority mode is activated has been described in the first embodiment, and therefore will be omitted. The case where the registered person is rejected (step S41) will be described with reference to FIG. I do. At this time, the person to be authenticated inputs the personal ID to the mode determining unit 46 using the external input unit 49 for the person to be authenticated. The change instruction and the input personal ID are output (mode control information). The image input unit 41, the face detection unit 42, and the feature extraction unit 43 input the biometric information of the subject again, and the acquired biometric feature information is sent to the matching unit 44. The collation unit 44 collates the biometric characteristic information with the single personal authentication information sent from the authentication information storage unit 45 in the personal identification mode, and outputs the result again (step S42).

The authentication work described in the above embodiments is
This is an identification problem for determining whether or not a person to be authenticated matches any of a large number of registered persons. Step S4
The processing steps 1 and subsequent (backup mode) result in an identification problem for determining whether or not the person to be authenticated matches one of the registered persons. By having a backup process based on the identification problem with less erroneous recognition, the security system according to the present embodiment can achieve extremely high security. Embodiment 5 Unlike the mode control examples (1) to (4) in which only one type of biometric information (face image) is used for authentication, the biometric information authentication apparatus described in Using the mode control corresponding to (5), two types of face image and iris are adopted. Further, in (1) to (4), the mechanism for changing the mode by a single means is used, whereas in this embodiment, a mechanism for controlling the mode by a plurality of means is adopted.

The biometric information authentication apparatus in this embodiment employs face image authentication in which comfort is emphasized in the daytime, and safety is emphasized in consideration of the fact that there is no manager at night and sufficient caution is required. Authentication using the iris is used. The iris authentication has to look into the camera to acquire the iris image and it is hard to say that comfort is high, but it is thought that the recognition rate has reached a level that can be applied to security by now. I have. The mode used in this embodiment will be described with reference to FIG.

As described above, the mode used in the apparatus of this embodiment is changed depending on the time zone. In the daytime, the mode control system by the administrator used in the device a of the fourth embodiment is adopted. This is a system that normally uses the personal convenience mode that emphasizes comfort when the administrator is at the reception, and switches to the safety priority mode that emphasizes safety using an external input device when the administrator leaves the reception. The details have been omitted since they have already been described in the fourth embodiment. At night, an iris authentication mode in which authentication is performed using only the iris is used. In order to perform authentication using an iris image, this biometric information authentication device has an imaging means for obtaining an iris image separately from that for obtaining a face image, and a function of detecting an iris from the image and extracting a feature amount. Have.

The structure of the biometric information authentication device according to this embodiment will be described with reference to the block diagram of FIG. The face image information receiving unit A and the face recognizing unit B having the function related to the authentication using the face image are omitted because the functions are the same as those of the biological information receiving unit A and the recognizing unit B of the third embodiment.
The iris image information receiving unit D includes an iris image acquiring unit 58, an iris detecting unit 59, and an iris feature extracting unit 60.
The iris image acquisition unit 58 is a processing unit that acquires an image by an imaging unit set so as to acquire an iris image of a person to be authenticated, and sends the image to the iris detection unit 59 as input image information. The iris detector 59 analyzes the transmitted input image information to determine whether or not the image contains an iris. If detected, sends the iris image to the iris feature extractor 60. Means. Iris feature extraction unit 6
Reference numeral 0 denotes a processing unit that analyzes the transmitted iris image, extracts a feature amount for calculating the similarity in the iris matching unit 61, and sends the extracted feature amount as iris feature information. The iris identification unit E includes an iris collation unit 61 and an iris information storage unit 62. The iris matching unit 61 calculates the similarity by comparing the iris feature information sent from the iris feature extracting unit 60 with the registered iris information sent from the iris information storage unit 62, and compares the calculated iris feature information with a set threshold to determine the identification. Processing means for outputting the result. The iris information storage unit 62 is a processing unit that stores registered iris information used when the iris matching unit 61 performs matching, and transmits the registered iris information when necessary. The mode management unit C includes a mode determination unit 56 and an external input unit 57 for manager. The mode determining unit 56 issues a command to use face authentication in the daytime and iris authentication in the nighttime depending on the time zone, and if the time belongs to daytime, the mode selection sent from the external input unit 57 for the administrator. This processing means determines whether to use the personal convenience mode or the safety priority mode according to the information, and transmits the result to the face matching unit 54. If the time zone is daytime, a command is issued to the iris information receiving unit D and the iris discriminating unit E to stop the function, and the mode is determined according to the mode selection information from the external input unit 57 for the administrator. 3
Transmit to 4. If the time zone is night, face image information receiving unit A
Is issued to the face identification unit B to stop the function, and the system shifts to a system that performs only iris authentication. The administrator's external input unit 57 outputs the signal (mode selection information) for switching to the safety priority mode when the time zone is at noon when the personal convenience mode is normally operated but the administrator leaves the reception. And has the same function as the external input unit 39 for manager described in the fourth embodiment.

The flow of processing when the present biometric information authentication device is used will be described with reference to FIG. First, it is assumed that it is used during the daytime (step S51). At this time, the functions related to iris authentication, the iris image information receiving unit D and the iris identifying unit E are stopped by the mode determining unit 56, and only authentication using a face image is possible. When a face is detected by the face detection unit 52, face image information is output to the feature extraction unit 53 (step S52), and the face feature extraction unit 53 extracts a feature amount from the face image received from the face detection unit 52 (step S52). S53). The mode determination unit 56 uses the personal convenience mode when the manager is at the reception normally, and switches the mode using the external input unit 57 to perform the identification work in the safety priority mode when leaving the reception ( Step S5
4) An instruction is issued to the face matching unit 54 as described above. The details of the face image authentication based on the mode control by the administrator have been described in the fourth embodiment, and will not be described here. Next, the case of using at night will be described (step S51). A function related to face authentication by the mode determining unit 56, a face image information receiving unit A and a face identifying unit B
Is stopped, and only authentication using an iris image is possible. When the iris detecting section 59 detects an iris in the input image, the iris feature extracting section 60 extracts a feature amount from the input iris image (step S56), and the iris matching section 60 uses the feature amount and the registered iris information. Identification (step S57). (Embodiment 6) The present invention was originally aimed at realizing security with a high level of balance between safety and comfort, and intended to overcome the problems of the conventional recognition technology. Therefore, in the present embodiment, a mode control example corresponding to the above (6) is used, biometric information authentication is combined with non-biometric authentication information such as a wireless tag and a password, and higher security without impairing the convenience of the person to be authenticated as much as possible. Describes a security system that aims for security.

In the security system of this embodiment, a face image is used as biometric information, and a wireless tag passed to all registrants and a personal ID input by a personal identification number are used as non-biometric authentication information. Next 4 which is composed by combining non-biometric information
Authentication is performed using two authentication modes. First of all, it is assumed that the manager is nearby in the daytime, so even the registered person may not be able to pass, but it is unlikely that anyone other than the person will pass. In this case, the "daytime mode" is used in which the user can be passed if the registered user is recognized by either non-biometric authentication information authentication using a wireless tag to input a personal ID. In the evening, authentication is performed in the normal safety priority mode, and if it is not passed, enter the personal ID using either the wireless tag or the password, and identify the specific person specified by it with a high pass rate The “night mode” in which the authentication can be performed again by the “personal identification mode” described in the device b of the fourth example is adopted.
(FIG. 16) By properly using the day mode and the night mode according to the time zone, authentication can be performed with emphasis on comfort at daytime and safety at night.

FIG. 17 shows a block diagram of the security system.

As in the first embodiment, the biological information receiving unit A is composed of three parts: an image input unit 71, a face detection unit 72, and a feature extraction unit 73. The roles of these parts are the same as those described in the first embodiment.

The face image identification section B comprises a face collation section 74 and a registered face image information storage section 75. The registered face image information storage unit 75 stores registered face image information necessary for collation,
Processing means for sending to the face matching unit 74 when necessary. The face matching unit 74 performs matching and identification between the biometric feature information sent from the feature extracting unit 73 and the registered face image information sent from the registered face image storage unit 75 according to the threshold setting in the mode specified by the mode determining unit 76, and passes. This is processing means that sends the information to the determination unit 83 as identification result information. In the case of performing authentication in the personal identification mode, the face information storage unit 75 includes a mode determination unit 76
With reference to the personal ID information of the person to be authenticated sent from the user, only the registered face image information of the specific individual is sent to the face matching unit 74, and the face matching unit 74 uses the biometric feature information sent from the feature extracting unit 73. Identification is performed.

The non-biometric authentication information receiving unit F includes a wireless receiving unit 77 and a wireless information matching unit 78 related to the input of the personal ID by the wireless tag, a registered wireless information storage unit 79, and a personal identification number related to the input of the personal ID by the personal identification number. An input unit 80, a password collating unit 81, and a registered password storage unit 82 are provided. The wireless receiving unit 77 is a processing unit that senses a wireless tag owned by the authentication target, acquires ID information, and sends the ID information to the wireless information matching unit 78 as personal ID information. Registered wireless information storage unit 79
Is processing means for storing registered wireless information necessary for personal ID collation by the wireless tag and sending it to the wireless information collating unit 78 when necessary. The wireless information collating unit 78 includes a wireless receiving unit 77
The personal ID information sent from the registered wireless information sent from the registered wireless information storage unit 79 is collated and identified, and whether or not the person to be authenticated matches any of the registered persons is sent to the pass determination unit 83 as identification result information. , And the individual I selected as a result of matching
D is a processing unit that sends D to the mode determination unit 76.

The password input unit 80 obtains a password input by the authenticator as personal ID information, and obtains the personal ID information.
1 is a processing means for sending to 1. The registered password storage unit 82 is a processing unit that stores a registered password required for collating the personal ID based on the password and sends it to the password matching unit 81 when necessary. The wireless information collating unit 81 includes a password input unit 80
The personal identification information sent from the personal identification information and the registered personal identification number sent from the registered personal identification number storage part 82 are collated and identified, and whether or not the authenticated person matches any of the registered persons is sent to the passage judgment part 83 as identification result information. , And the individual I selected as a result of matching
D is a processing unit that sends D to the mode determination unit 76.

The mode management section C comprises a mode determination section 76 and a passage determination section 83. The mode determining unit 76 sets a threshold setting used for identification to the face matching unit 74 as a threshold setting 1 if the time zone is daytime, and a threshold setting 2 if it is nighttime.
Is sent to the pass determination unit 83 during the day, either face image authentication in the safety priority mode or wireless tag authentication in the daytime, and face image authentication in the safety priority mode or safety priority in the nighttime. This is processing means for transmitting, as mode control information, information designating permission of passage when either one of the authentications in mode 2 is successful. The pass determination unit 83 integrates the identification result information sent from the face matching unit 74, the wireless information matching unit 78, and the personal identification number matching unit 81,
This is a processing unit that determines whether to finally permit passage according to the mode control information sent from the mode determination unit 76. If it is determined that the passage is not permitted in the safety priority mode at night, re-authentication request information for requesting authentication in the personal identification mode is sent to the mode determining unit.

The flow of processing when this security system is used will be described with reference to FIGS. When the time when the person to be authenticated visited was noon (step S
71) If a face is detected in the input image (step S7)
2) Face image authentication in the safety priority mode is performed, and if the authentication result is “passed”, the authentication ends (step S7).
3). If the result is “non-passing” or if no face is detected in step S72, non-biometric authentication in the wireless tag mode is performed after detecting that the subject has the wireless tag. (Step S7)
4). If the time zone is night, the face is detected first and face image authentication is performed in the safety priority mode (step S75), and if the result is "pass", the authentication ends there (step S7).
6). If the result is "non-passage", a personal ID is obtained from the person to be authenticated by using a wireless tag or a password, and a face image is obtained again, and then authentication in the personal identification mode is performed again (step S77).

Further, in the embodiment, in the case of the daytime mode, the judgment is first made using the biometric information, and then the final judgment is made using the biometric information. Is not limited. For example, in the case of the night mode, the wireless tag (non-biometric authentication information) as in the individual identification mode used in steps S77 to S78 in FIG.
The biometric information is checked after the determination of the above is performed in order to obtain a gain of restricting the search range of the biometric information by first acquiring the non-biometric authentication information. For example, when the face detection range is wider than the wireless detection range, the day mode in which authentication is performed by the wireless tag after authentication using the face image is performed after emphasizing quickness and if the face cannot be passed. However, in order to perform authentication with higher security, it is better to first acquire a personal ID using a wireless tag, narrow the search range, and then switch to a personal identification mode in which face image authentication is performed. Thus, the performance of the entire recognition can be controlled by the difference in the order relation. This control can be combined with other controls such as control based on time or control by an administrator in the same manner as the control described above to perform mode management such as parameter adjustment.

In the above embodiments, the authentication has been performed based on the authentication based on the face image. However, any of voice, fingerprint, palm print, iris and retina may be used as the biometric information. Further, the types of the non-biometric authentication information used in the fourth and sixth embodiments are not limited.

The present invention is not limited to the above-described embodiment, but can be implemented with various modifications within the technical scope.

[0055]

As described above in detail, according to the present invention, a security system that combines security and comfort at a high level is realized by using a conventional biometric information authentication method, which has been difficult to realize. A new system that realizes convenience by controlling the balance between comfort and comfort can be provided. Further, in the present invention, it is possible to provide a system that comprehensively prevents a reduction in recognition rate by detecting a change in the environment around a person to be authenticated and selecting an optimal authentication method according to the change.

[Brief description of the drawings]

FIG. 1 is a diagram showing a basic configuration of the present invention.

FIG. 2 is a diagram illustrating a configuration of an authentication mode according to the first embodiment.

FIG. 3 is a diagram showing a processing procedure in the first embodiment.

FIG. 4 is a diagram illustrating a configuration of an authentication mode according to a second embodiment.

FIG. 5 is a diagram illustrating a block configuration according to a second embodiment.

FIG. 6 is a diagram showing a processing procedure in the second embodiment.

FIG. 7 is a diagram illustrating a configuration of an authentication mode according to a third embodiment.

FIG. 8 is a diagram illustrating a block configuration according to a third embodiment.

FIG. 9 is a diagram illustrating a block configuration of an apparatus a according to a fourth embodiment.

FIG. 10 is a diagram showing a processing procedure in an apparatus a in the fourth embodiment.

FIG. 11 is a diagram illustrating a block configuration of a device b according to a fourth embodiment.

FIG. 12 is a diagram illustrating a processing configuration in a device b according to the fourth embodiment.

FIG. 13 is a diagram illustrating a configuration of an authentication mode according to a fifth embodiment.

FIG. 14 is a diagram illustrating a block configuration according to a fifth embodiment.

FIG. 15 is a diagram illustrating a processing configuration according to a fifth embodiment.

FIG. 16 is a diagram illustrating a configuration of an authentication mode according to a sixth embodiment.

FIG. 17 is a diagram illustrating a block configuration according to a sixth embodiment.

FIG. 18 is a diagram illustrating a processing configuration according to a sixth embodiment.

FIG. 19 is a diagram illustrating a processing configuration according to a sixth embodiment.

FIG. 20 is a diagram showing the relationship between the false exclusion rate and the pass-through rate.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Image input part 2 Face detection part 3 Feature extraction part 4 Collation part 5 Authentication information storage part 6 Mode determination part

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Kaoru Suzuki 1-1-30 Oyodonaka, Kita-ku, Osaka-shi, Osaka Toshiba Kansai branch office (72) Inventor Kazuhiro Fukui 1 Oyodonaka, Kita-ku, Osaka, Osaka No. 1-30, Toshiba Kansai Branch (72) Inventor Mayumi Yuasa 1-1-30, Oyodo, Kita-ku, Osaka-shi, Osaka F-term (reference) 5B043 AA09 BA01 GA13 GA17

Claims (11)

[Claims] 1. A biometric information receiving means for acquiring biometric information of a subject and extracting features of the subject from the input information and forming biometric feature information. The biometric information receiving means is prepared for each category in advance with the biometric feature information. A biometric information authentication device, comprising: identification means for determining the category to which the person to be authenticated belongs, wherein at least one of the biometric information reception means and the identification means is provided, and When performing biometric information authentication using authentication logic configured by combining the above, a mode management means capable of controlling the biometric information receiving means and the identification means by selecting one from a plurality of authentication logic modes A biometric information authentication device, comprising: 2. A biometric information receiving means for extracting a feature from one or a plurality of biometric information of an authentication subject to form one or a plurality of biometric feature information, and preparing a part or all of the biometric feature information in advance by category. Selecting one of a plurality of modes classified by the biometric information in a biometric information authentication device having identification means for comparing with registered information and determining a category to which a person to be authenticated belongs. A mode management unit capable of controlling a combination of authentications using a plurality of pieces of biometric information. 3. Biometric information receiving means for acquiring biometric information of a subject and extracting features of the subject from the input information to form biometric feature information, and non-biometric information possessed by the subject. Non-biometric information receiving means to be obtained, and identification means for comparing one or both of the biometric information and non-biometric information with registration information prepared in advance for each category, and determining a category to which the subject belongs. A biometric information authentication device comprising: a mode in which the combination of biometric information and non-biometric authentication information can be controlled by selecting one of a plurality of modes classified by the biometric information and non-biometric information. A biological information authentication device comprising a management unit. 4. The living body according to claim 1, wherein, when the living body information receiving unit performs feature extraction, a feature extracting method can be changed according to a mode determined by the mode managing unit. Information authentication device. 5. The biometric information authentication device according to claim 1, wherein when the identification unit performs the identification, the identification method can be changed according to a mode determined by the mode management unit. 6. The method according to claim 1, wherein when the biometric information receiving unit performs feature extraction, a feature extraction method can be changed by operating a parameter value in accordance with a mode determined by the mode management unit. , A biological information authentication device according to claim 2. 7. The identification method according to claim 1, wherein when the identification means performs the collation, the identification method can be changed by operating a parameter value according to the mode determined by the mode management means. The biometric information authentication device according to the above. 8. The biometric information authentication apparatus according to claim 1, wherein said mode management means selects one mode from a plurality of different modes according to a time zone for performing authentication. 9. An environment detecting means for detecting and acquiring surrounding environmental conditions, and said mode managing means for determining one of a plurality of modes based on environmental condition information obtained by said detecting means. Claims 1 and 2 characterized by the following:
3. The biometric information authentication device according to 3. 10. A mode can be designated to the mode management means from the outside of the apparatus, and the mode management means controls one or both operations of the biological information receiving means and the identification means according to the designated mode. The biometric information authentication device according to claim 1, wherein the biometric information authentication device is capable of being used. 11. A biometric information receiving step of obtaining biometric information of a subject and extracting features of the subject from the input information and forming biometric feature information; Identification step of determining the category to which the person to be authenticated belongs, wherein at least one of the biometric information receiving means and the identification means is provided in a plurality. When performing biometric information authentication using an authentication logic configured by combining the above, a mode management step capable of controlling the biometric information receiving means and the identification means by selecting one from a plurality of authentication logic modes A biometric information authentication method comprising: