WO2005111935A1 - Login system - Google Patents

Abstract

A login system which has a high authentication speed with reduced data amount using face authentication. A user terminal (1), a database server (3) and an authentication server (2) are connected through a communication line network (4). Face image data and identification data are acquired, the acquired face image data is subjected to DCT conversion and DCT coefficients are calculated. A DCT code at an address indicative of a DCT amplitude of a specified value or above is determined among the DCT coefficients. A binary one-dimensional template is generated from the DCT code, and a registration template consisting of the binary one-dimensional template and the acquired identification data corresponding to the binary one-dimensional template is generated. Similarly, binary one-dimensional information for authentication is generated, and login is controlled by comparing the binary one-dimensional template with the binary one-dimensional information for authentication.

Description

 Specification

 Login system

 Technical field

 The present invention relates to a login system such as a computer, and more particularly, to a login system such as a computer that requires a small amount of data for face authentication and has a high authentication speed.

 Background art

 Conventionally, as a login system such as a computer, the technologies described in Patent Documents 1 and 2 are known.

 [0003] In the technique of Patent Document 1, an authentication image is stored as an image, extracted at the time of authentication, and the image is subjected to pattern matching.

[0004] However, the technique of Patent Document 1 has a drawback in that since the pattern matching of an image image is performed at the time of authentication, the data volume is large and the authentication speed is slow.

[0005] The technique of Patent Document 2 describes that two-dimensional and three-dimensional numerical data are used for authentication for face images. The calculation method is described, and the login method is unknown at all.

 Patent Document 1: JP 2004-21332 A

 Patent Document 2: JP 2002-351838 A

 Disclosure of the invention

 Problems to be solved by the invention

[0006] Therefore, an object of the present invention is to provide a login system which requires a small data volume for face authentication, has a high authentication speed, and has a high authentication speed.

 Means for solving the problem

[0007] The above problem is solved by the following invention.

 [0008] (Claim 1) The user terminal, the database server, and the authentication server are connected to each other by a communication network,

The user terminal includes a face image data for inputting face image data for registration and authentication. Input unit, an identification data input unit for inputting identification data for registration and authentication related to the face image, and each of the face images for registration input by the face image data input unit and the identification data input unit A transmitting unit for transmitting data and identification data to the authentication server,

 The authentication server includes an authentication unit that authenticates a face image, and an authentication information generation unit. The authentication information generation unit obtains registration face image data and identification data during registration processing, The obtained face image data is subjected to DCT conversion to calculate a DCT coefficient, and an address (address) and a DCT code corresponding to the DCT coefficient in a one-to-one correspondence with a predetermined number of higher-order absolute values of the DCT coefficient are obtained. Generating a binary one-dimensional template from the DCT code, generating a registration template corresponding to the binary one-dimensional template and the acquired identification data corresponding to the binary one-dimensional template, and To the database server, the database server stores the registration template in a data table, and the authentication unit of the authentication server identifies a user at the time of login from the user terminal during authentication processing. Data and the face image data, and sends only the face image data to the authentication information generation unit.The authentication information generation unit performs DCT conversion on the face image data for authentication to calculate a DCT coefficient, and An address (address) and a DCT code corresponding to the DCT coefficient up to a predetermined number from the highest value of the absolute value of the coefficient are obtained, and binary one-dimensional information for authentication is generated from the DCT code, and the authentication is performed. For sending binary one-dimensional information to the authentication unit,

 The authentication unit calls, from the data table, a binary one-dimensional template corresponding to the identification data in the registration template, and stores the called binary one-dimensional template and the authentication binary one-dimensional information. A mouth login system characterized by comparing and controlling login.

 (Claim 2) A registration template at the time of the registration process includes the binary one-dimensional template, an address (address) corresponding to the binary one-dimensional template, and identification data. At this time, only the address (address) of the registration template corresponding to the identification data is sent to the authentication information generation unit,

The authentication information generation unit performs DCT conversion on the face image data for authentication to calculate a DCT coefficient, obtains a DCT code based on the obtained address (address), and also converts the DCT coding power into a binary value for authentication. One-dimensional information is generated, and the two-dimensional one-dimensional information for authentication is sent to the authentication part, and the two-dimensional one-dimensional template for the registration and the two-dimensional one-dimensional information for authentication are transmitted to the authentication part. The login system according to claim 1, wherein login is controlled by comparing.

[0010] (Claim 3) The login system according to claim 1 or 2, wherein the registration template includes face position data and Z or a face photographing condition.

 The invention's effect

 According to the present invention, the authentication target is a template that is not image data, that is, authentication is performed using binary one-dimensional information, and has a very small capacity as compared with image data.

 [0012] That is, the capacity of the template in the present invention is, for example, 2 bytes to 128 bytes. As an example of conventional image data, the capacity of 8 x 8 pixels in grayscale (a pattern expressing 8-bit hierarchical black and white in 0 to 255 steps) is 64 bytes, and a grayscale of 128 x 128 pixels. Is 16384 (about 16K) bytes.

 [0013] Even when compared as a binary (black and white) image, it is 16 bytes for 8 x 8 pixels, and 1448 bytes for 128 x 128 pixels.

 [0014] Accordingly, in the present invention, since authentication is performed using a template having a small capacity (for example, 16 bytes or 128 bytes), a login system such as a personal computer that requires a small amount of data for face authentication and has a high authentication speed is used. Can be provided.

 Brief Description of Drawings

FIG. 1 is a diagram showing a hardware configuration according to a first embodiment.

 [Figure 2] System flow diagram for registration processing of the above

 [Figure 3] Diagram of system flow related to binary one-dimensional template creation processing in registration processing of the above

 FIG. 4 is a diagram showing an example of an image of 8 × 8 pixels used in the registration processing of the above.

 [Figure 5] Distribution map showing DCT coefficients and addresses after DCT conversion

 [Figure 6] Distribution map showing only DCT codes among DCT coefficients

 [Figure 7] Extraction point distribution diagram of the result of extracting the feature points of the image

[Fig.8] Distribution map of Fig. 6 and Fig. 7 superimposed FIG. 9 is a diagram showing a binary one-dimensional template in the first embodiment

 [Figure 10] Diagram showing registration template in the same as above

 [FIG. 11] A diagram showing a data table in the above.

 [FIG. 12] A system flow diagram showing an authentication process in the above.

 [Figure 13] Diagram showing the login start screen of the authentication process in the same as above

 [FIG. 14] A diagram showing only DCT codes among DCT coefficients of an input image of the authentication processing in the above.

 [Figure 15] Extraction point distribution diagram of the result of extracting the feature points of the image at the time of authentication in the same

 [Figure 16] Distribution map of Fig. 14 and Fig. 15 superimposed

 [Figure 17] Diagram showing templates to be compared

 [FIG. 18] A system flow diagram relating to registration processing in the second mode

 [FIG. 19] A system flow diagram for an address template creation process in the registration process of the above.

 FIG. 20 is a system flow chart showing an authentication process in the above.

 [Fig.21] Diagram showing the addressing template in the above.

 [Figure 22] Diagram showing registration template in the same as above

 [FIG. 23] A diagram showing a data table in the above.

 [Figure 24] Diagram showing 16-byte and 128-byte binary one-dimensional template examples

 Explanation of symbols

[0016] 1: User terminal

 2: Authentication server

 3: Database Sano

 4: Communication network

 BEST MODE FOR CARRYING OUT THE INVENTION

Hereinafter, embodiments of the present invention will be described.

[0018] (First embodiment)

FIG. 1 is a functional block diagram showing an example of hardware used in the first embodiment of the present invention. In FIG. 1, 1 is a user terminal (also called a client terminal), 2 is an authentication server, 3 is a database server, and these are connected to each other by a communication network 4. In the example shown in the figure, the functions of the user terminal 1, the authentication server 2, and the database server 3 are separately described, but as hardware, the functions of the authentication server 2 and the database server 3 are provided in the user terminal 1. You may have them, or authentication server 2 and database server 3 may have two functions in one server! /, Or! /.

 The user terminal 1 includes a face image data input unit 100 for inputting face image data for registration and authentication, and an identification data input unit for inputting identification data for registration and authentication related to the face image. The system includes at least a display unit 101 such as a monitor, a transmission unit 103, and a reception unit 104. The display unit 102 may be integral with or separate from the main body of the user terminal 1.

 In the login system of the present invention, 1) a method of registering and authenticating a face image by photographing with a camera, 2) a method of reading and registering a face photograph by scanning, and 3) a method of scanning a photograph at the time of registration 4) A method that uses camera photography at the time of reading and authentication, and 4) A method that uses camera photography at the time of registration and the use of scanner reading of photos at the time of authentication.

 As the face image data input unit 100, for example, a CCD camera, a scanner, or the like can be used.

 The CCD camera 100 is provided at a position where a user who logs in to the user terminal 1 can be photographed, and may be detachably mounted on the upper part of the main body of the user terminal 1 or may be located close to the main body of the user terminal 1. May be fixed. Further, the CCD camera 100 can be provided in the authentication server 2. The direction of the taking lens may be configured to be freely changeable.

 The identification data input unit 101 plays a role of inputting identification data related to the face image, and can use, for example, a user interface. As the user interface 101, a keyboard, a mouse, a touch panel, or the like can be used.

[0025] The authentication server 2 includes an authentication unit 200 that authenticates whether or not a user who wants to log in to the user terminal 1 is permitted to log in, an authentication information generation unit 201, a transmission unit 202, and a reception unit 2 03 at least. The database server 3 includes at least a data table 300 for storing the authentication information generated by the authentication information generation unit 201, a transmission unit 301, and a reception unit 302.

 [0027] The login system for a user terminal according to the present invention includes a registration process and an authentication process. Hereinafter, each of the registration processing and the authentication processing will be described in detail.

 [0028] (1) Registration process.

 In this embodiment, an example of a registration process by camera shooting will be described with reference to FIG.

 First, a registration screen is displayed on the display unit 102 (Sl). The display unit 102 displays a registration screen (not shown) for inputting identification data relating to a user who inputs a face image.

 Next, identification data is input from the user interface 101 (S2). As the identification data, ID numbers such as an employee number, a license number, a social insurance number, and a taxpayer number are preferable as long as the personal information is unique to each user. If necessary, user attributes such as name, date of birth, company department, and post may be entered.

 Next, the camera 100 of the face image data input section is activated to input a face image (S 3). The face image input in S3 is transmitted from the transmission unit 103 of the user terminal 1 to the authentication server 2, and is transmitted to the authentication information generation unit 201 via the reception unit 204 of the authentication server. The authentication information generation unit 201 acquires face image data for registration and identification data (S4).

 Next, the authentication information generation unit 201 performs a process of creating a binary one-dimensional template (S5).

 Hereinafter, a system flow of a process of creating a binary one-dimensional template will be described with reference to FIG.

 First, a face position detection process is performed (S20). Specifically, when a face image is input, a process of detecting the image power pupil and cutting out the face image from the position of the pupil to a position within a certain range is performed.

 Next, a two-dimensional discrete cosine transform (DCT transform) of the face image is performed (S 21). In the case of input face image information (digital image information) of MXN pixels, if the image signal (pixel value) at the horizontal position m and the vertical position n is f, the horizontal position u on the frequency axis and the vertical V The DCT section mn

 The number is given by F.

 uv

 [0036] The two-dimensional DCT is defined by the following equation. Where the signal f is m = 0 '· Μ-1, η = 0

The Equation 1

 [0037]

式 2 e 0^038] [逆変換]

[conversion]

Equation 2 e 0 ^038] [Inverse transformation]

 Here, c (k) is a normalization constant as shown in the following equation.

 Equation 3

(≠ 0)

Is a real number, so the ^separable function between its amplitude and sign ( ^{Se Parable} Action)

E uv uv

[0043] However, Equation 5

 [0044]

_ ί 0: (F _uv ≥ 0)

= π: (F _UV × 0)

[0045]

A DCT coefficient is obtained by the above-described DCT transformation (S22). The DCT amplitude and the DCT sign (positive or negative) can be obtained from the DCT coefficient F.

 [0047] The DCT amplitude represents the power at each component (frequency) position. /, In other words, indicates the magnitude of the component contained in the original signal. In other words, it can be said that the DCT amplitude carries information on the energy of the original signal.

 [0048] Even with the same DCT amplitude, different signals are obviously different if the DCT code is different. The DCT code has information serving as a skeleton of the signal when the signal is configured. That is, the original signal can be identified by the positive and negative arrangement of the DCT code, and the outline drawing of the image can be obtained only from the positive and negative DCT codes. This is clearly evident in the sign-only synthesis (SOS) image, which is the inverse transform of only the code showing the characteristic properties of the DCT code. The SOS formula is shown below for reference.

 Equation 6

 [0049]

[sign-Only synthesis]

[0050] Therefore, the DCT code also clarifies the outline of the face and the outline of each of the facial parts such as the eyes, nose, mouth, eyebrows, and the like.

 For example, FIGS. 5 and 6 show examples in which the image of 8 × 8 pixels shown in FIG. 4 is subjected to DCT conversion.

(For the case ¾ ¾ »2δ) FIG. 5 shows the relationship between DCT coefficients and addresses. FIG. 6 shows a distribution diagram of only the code points when the DCT coefficient is calculated.

 Next, an address (address) and a DCT code corresponding to the DCT coefficient in a one-to-one correspondence with up to a predetermined number of higher-order absolute values of the DCT coefficient are obtained (S23). Here, the predetermined number varies depending on the number of pixels, but is a case of 128 × 128 pixels which can be preferably applied in the present invention, and is 0.1 to 1% from the higher (larger) absolute value of the DCT coefficient. (For example, about 16 points to 164 points) is a number (number of addresses) determined in the range. If it is less than 0.1%, it cannot be said that it is enough to extract the feature points of the face image, and if it exceeds 1%, the effect is not improved because only the data capacity increases. In the illustrated example, the size is 8 × 8 pixels, and the predetermined value is 14 points for convenience. That is, according to the present invention, it is possible to reduce the absolute value of the DCT coefficient without using all of the DCT codes, and to obtain a small number of addresses (addresses) and DCT codes corresponding to the DCT coefficients up to a predetermined number. The feature points of the face image can be extracted with the data capacity.

 In order to make the process of S23 easy to understand, FIG. 7 shows an extraction point distribution diagram as a result of extracting feature points of the face image. The figure shows the result of extracting 14 points in the case of an 8 × 8 pixel image.

 Next, a binary one-dimensional template represented by binary one-dimensional information “0” and “1” is created based on the sign of the feature point obtained by the processing of S23 (S24). The process of creating the binary one-dimensional template will be described with reference to FIG. That is, when the extraction point in FIG. 7 is superimposed on the code point in FIG. 6, it can be expressed as shown in FIG. In FIG. 8, two-dimensional one-dimensional information is obtained by sequentially obtaining the binary data for each row, with the upper left force also moving to the right. Based on the results, a binary one-dimensional template as shown in Fig. 9 can be created.

 After the binary one-dimensional template, which is the process of S5, is created as described above, the process returns to the process of FIG. 3, and the binary one-dimensional template created and the acquisition corresponding to the binary one-dimensional template are obtained. Create registration template with strong identification data (for example, ID) (S6)

FIG. 10 shows an example of the created registration template. In FIG. 10, 500 is identification data, 501 is a binary one-dimensional template, and 502 is a registration template including the identification data 500 and the binary one-dimensional template 501. In the above description, the case has been described where both the binary one-dimensional template and the registration template are created by the authentication information generation unit 201, but the aspect of the present invention is not limited to this, and the authentication information generation unit 201 Is composed of, for example, a binary one-dimensional template generation unit 201A and a registration template generation unit 201B, a binary one-dimensional template generation unit 201A creates a binary one-dimensional template, and a registration template generation unit 201B generates a registration template. You may try to create.

 [0059] The registration template 502 is transmitted from the transmission unit 202 of the authentication server 2 to the database server 3 as shown in Fig. 2 (S7). When the receiving unit 302 of the database server 3 receives the data, it is stored in the data table 300 (S8).

 FIG. 11 shows an example in which a plurality of registration templates are stored in data table 300.

 [0061] (2) iH processing

 Next, a user authentication process when logging in to a user terminal will be described.

 FIG. 12 shows a processing flowchart of the authentication processing. First, when the user terminal 1 is turned on (S30), a PC login screen shown in FIG. 13 is displayed on the display unit 102 (S31). The PC login screen includes a user ID input field 102A and a decision button 102B.

 [0063] By operating the user interface 101 and inputting the user ID in the input field 102A (S32), and pressing the enter button 102B (S33), the CCD camera 100 is activated (S34) and enters a shooting state.

Next, a face image of the user who is going to log in is input by the CCD camera 100 (S35).

 The input face image and user ID are transmitted from the transmitting section 103 of the user terminal 1 to the authentication section 200 of the authentication server 2 (S36).

 After acquiring the face image, authentication section 200 sends the face image to authentication information generation section 201 (S37), and authentication information generation section 201 performs face position detection processing in the same manner as the registration processing (S38). . Specifically, a process of detecting the acquired facial image force pupil and cutting out a facial image from the position of the pupil to a position within a certain range is performed.

If the face position detection at the time of authentication is the same as the face position at the time of registration, the accuracy of authentication is preferably improved. In addition, in order to improve the authentication accuracy, before detecting the face position, for example, when inputting an image, It is preferable to perform preprocessing for matching the illuminance, distance, inclination, and the like. As such preprocessing, for example, it is also preferable to perform rotation, translation, and enlargement / reduction after detecting the pupil position. To perform image transformations such as image rotation, enlargement, reduction, and translation, there is a geometric transformation that transforms coordinates. Geometric transformation includes processing such as image rotation, enlargement, reduction, parallel translation, and distortion correction. Among geometric transformations, an affine transformation is most often used for scaling, rotating, and moving an image. As a process for causing the illuminance to substantially match, a smoothing / illumination process of an image using a grayscale histogram can be performed.

 Next, the authentication information generation unit 201 performs DCT conversion in the same manner as at the time of registration (S39). Next, the DCT coefficient is calculated (S40). FIG. 14 shows a distribution diagram of only the code points when the DCT coefficient is calculated.

 Next, a DCT code corresponding to the DCT coefficient up to a predetermined number in a one-to-one correspondence is obtained (S41). This process is the same as the registration process, and the definition of the predetermined number is also the same as the registration process. The process of S41 is a process of extracting a feature point of the face image.

 [0069] In order to make the process of S41 easier to understand, FIG. 15 shows an extraction point distribution diagram of the result of extracting the feature points of the face image. The figure shows the result of extracting 14 points in the case of an 8 × 8 pixel image.

 Next, binary one-dimensional information for authentication represented by binary one-dimensional information “0” and “1” is created based on the sign of the feature point obtained by the processing of S41 (S42). . The process of creating the binary one-dimensional information for authentication will be described with reference to FIG. That is, when the extraction points in FIG. 15 are superimposed on the code points in FIG. 14, they can be expressed as in FIG. In FIG. 16, two-dimensional data is obtained for each row in order from top left to right, and binary one-dimensional information is obtained. Based on the result, binary one-dimensional information for authentication as shown in the upper part of FIG. 17 can be created.

 Next, the authentication unit 200 calls a binary one-dimensional template corresponding to the user ID (for example, GSD0001) among the registration templates from the data table 300 (S43).

Next, the called binary one-dimensional template is compared with the binary one-dimensional information for authentication (the upper part of FIG. 17) (S44). The lower part of Fig. 17 shows the binary one-dimensional template to be compared. [0073] The threshold for comparison is set to, for example, 95%. As a result of comparison, only one of the 14 points is different and the others are the same, so the matching rate is 99% or more. Therefore, since the value is equal to or larger than the threshold value, the logged-in user is permitted to log in as a result of authentication (S45).

 As a result of the comparison, if the value is less than the threshold, the login is not permitted (S46).

 The authentication result (permitted or not permitted) is sent from the authentication unit 3 to the reception unit 104 of the user terminal 1 and displayed on the display unit 102.

 If the login is not permitted in S46, it is determined whether or not to perform the login operation again (S47). If there is an instruction to perform a login operation, the process is repeated from step S31. If there is an instruction not to perform the login operation, a message indicating that the PC login process is to be terminated is displayed on the display unit 102, and the process is terminated.

 (Second Aspect)

 Hereinafter, the second embodiment of the present invention will be described. In the second aspect, the description of the first aspect is omitted for the same configuration and processing as in the first aspect, and the description is omitted.

[0078] (1) Registration process

 Basically, the hardware shown in Fig. 1 is used for the registration process. Fig. 18 shows the system flow of the registration process in the second mode.

First, as in the first embodiment, the processing flow from S1 to S4 is performed. Next, an address information template creating process is performed by the authentication information generating unit 201 (S50).

Hereinafter, a system flow of the numbered template creating process will be described with reference to FIG.

 [0081] The processes from S20 to S24 are performed in the same manner as in the first embodiment.

 [0082] In the process of the first embodiment, the process of S23 is an auxiliary means for creating a binary one-dimensional template. ,. On the other hand, the second embodiment is different from the first embodiment in that the address extracted in the process of S23 in the first embodiment is inserted into a template.

[0083] Next, a binary one-dimensional template represented by binary one-dimensional information of "0" and "1" is created based on the sign of the obtained address (feature point) (S24). Dimensional template and obtained in S23 The generated addressable template is generated (S60). One form of the numbered template is shown in FIG.

After generating the addressing template which is the process of S60 as described above, the process returns to the process of FIG. 18, and as a result of the process of S50, the created addressing template and the acquisition corresponding to the addressing template are obtained. A powerful registration template such as the identified identification data (for example, ID) is created (S51). FIG. 21 shows an example of the created registration template in the second mode.

 In FIG. 21, reference numeral 500 denotes identification data, reference numeral 501 denotes a binary one-dimensional template, reference numeral 503 denotes an address, and reference numeral 504 denotes an addressing template including a binary one-dimensional template 501 and an address 503. . Therefore, the registration template 502 in the second embodiment has a configuration including the identification data 500 and the addressing template 504.

 Next, the processing flow of S7 and S8 is performed in the same manner as in the first mode.

 FIG. 22 shows an example in which a plurality of registration templates according to the second embodiment are stored in the data table 300.

[0088] (2) Authentication iH processing

 Next, the authentication processing of the second mode will be described.

FIG. 23 shows a processing flowchart of the authentication processing according to the second mode.

As in the first embodiment, the processes from S30 to S37 in FIG. 12 are performed.

Next, the authentication unit 200 calls an addressing template corresponding to the user ID (for example, GSD001) from the data table 300 among the registration templates (S 70). The address portion of the called address-added template is sent to the authentication information generation unit (S71).

Next, the same processing is performed from S38 to S40 in FIG.

 [0093] After calculating the DCT coefficient in S40, the authentication information generation unit 201 obtains a DCT code based on the address obtained in S71, and calculates "0" and "1" based on the code of the feature point of the DCT code. The two-dimensional one-dimensional information for authentication represented by the two-dimensional one-dimensional information is created (S72), and the created two-dimensional one-dimensional information for authentication is sent to the authentication unit 200.

 Next, the same processing is performed from S44 to S47 in FIG.

[0095] (Other aspects) Hereinafter, other preferred embodiments of the present invention will be described.

 [0096] In the above embodiment, the example of the binary one-dimensional template shown in Figs.

 This is an example of X8 pixels, but the actual number of pixels is different in actual photo authentication and camera authentication where the number of pixels is large. For example, in the case of photo authentication in which a face photo is scanned and registered and then authenticated, for example, a 16-byte binary one-dimensional template can be used. In the case of authentication, for example, a 128-byte binary one-dimensional template can be used.

 [0097] Fig. 24 (A) shows an example of a 16-byte binary one-dimensional template, and Fig. 24 (B) shows an example of a 128-note addressing template. I'm ridiculed.

 [0098] Also, the above aspect corresponds to the DCT coefficient up to a predetermined number from the absolute value of the absolute value of the DCT coefficient in the authentication information generation unit at the time of registration processing. An example in which a process of extracting a feature point of a face image by obtaining an address (address) and a DCT code has been performed. In another preferred embodiment of the present invention, the authentication information generation unit performs: In this mode, an address (address) corresponding to the DCT coefficient up to a predetermined number from the absolute value of the DCT coefficient to the predetermined number is obtained and stored in a storage unit (not shown). Do not ask until

) o

 [0099] Further, as another preferred embodiment of the present invention, the registration template includes face position data and Z or a face photographing condition. Face position data and Z or face shooting conditions include pupil detection data (coordinate data, etc.), face cut-out distance data of pupil position force, image processing such as image rotation, enlargement, reduction, and translation. The conversion data at the time of the image processing, the image smoothing 'illumination processing data, etc., the camera illuminance at the time of image input, the camera power, the distance to the face (pupil), the inclination, and the like.

 [0100] Further, as another preferred embodiment of the present invention, after the user is permitted to log in, he / she temporarily leaves the personal computer to be logged in without logging in (not shown) (for example, the user interface). (For example, when the input from the user input power for a predetermined time), when the use of the personal computer is started again, the login system of the present invention is automatically activated.

, Can also improve security. At this time, it is convenient for the user to be able to omit the input of the user ID and the like. Also, when returning from the screen saver, automatic Alternatively, the login system of the present invention can be operated.

Industrial applicability

 The log-in system of the present invention is suitable for all systems, such as a computer and a computer, for example, which restrict users and enforce data confidentiality.

Claims

The scope of the claims  [1] A user terminal, a database server, and an authentication server are connected to each other via a communication network, the user terminal includes a face image data input unit for inputting face image data for registration and authentication, An identification data input unit for inputting identification data for registration and authentication related to the face image, and each of the face image data and identification data for registration input at the face image data input unit and the identification data input unit And a transmitting unit for transmitting to the authentication server  The authentication server includes an authentication unit that authenticates a face image, and an authentication information generation unit. The authentication information generation unit obtains registration face image data and identification data during registration processing, The obtained face image data is subjected to DCT conversion to calculate a DCT coefficient, and an address (address) and a DCT code corresponding to the DCT coefficient in a one-to-one correspondence with a predetermined number of higher-order absolute values of the DCT coefficient are obtained. Generating a binary one-dimensional template from the DCT code, generating a registration template corresponding to the binary one-dimensional template and the acquired identification data corresponding to the binary one-dimensional template, and To the database server, the database server stores the registration template in a data table, and the authentication unit of the authentication server identifies a user at the time of login from the user terminal during authentication processing. Data and the face image data, and sends only the face image data to the authentication information generation unit.The authentication information generation unit performs DCT conversion on the face image data for authentication to calculate a DCT coefficient, and An address (address) and a DCT code corresponding to the DCT coefficient up to a predetermined number from the highest value of the absolute value of the coefficient are obtained, and binary one-dimensional information for authentication is generated from the DCT code, and the authentication is performed. For sending binary one-dimensional information to the authentication unit,  The authentication unit calls, from the data table, a binary one-dimensional template corresponding to the identification data in the registration template, and stores the called binary one-dimensional template and the authentication binary one-dimensional information. A mouth login system characterized by comparing and controlling login.  [2] The registration template at the time of the registration process includes the binary one-dimensional template, an address (address) corresponding to the binary one-dimensional template, and identification data, The authentication unit includes, during the authentication process, the identification data of the registration template Only the corresponding address (address) is sent to the authentication information generation unit, and the authentication information generation unit performs DCT conversion on the face image data for authentication to calculate a DCT coefficient, and based on the obtained address (address). A DCT code is obtained, the DCT coding power also generates binary one-dimensional information for authentication, and sends the binary one-dimensional information for authentication to the authentication unit.  2. The login system registration template according to claim 1, wherein the authentication unit controls the login by comparing a binary one-dimensional template for the registration with the binary one-dimensional information for authentication. 3. The login system according to claim 1, further comprising face position data and Z or face photographing conditions.