Individual identification device, individual identification method, and individual identification system

The present invention relates to a personal identification device, a personal identification method, and a personal identification system, and in particular, a personal identification device, a personal identification method, and a personal identification using a vein distribution pattern on the back of the hand. Regarding the system.

PROBLEM TO BE SOLVED: To provide a personal identification system for security, personnel management, etc., a card-based system using a magnetic or high-frequency signal is the mainstream, and the card itself has an information storage ability. However, in the case of a system using a card, even if it is used by a person other than the card owner, it is identified as the card owner, so there is a problem in dealing with the theft.

[0003] Therefore, as a personal identification system that requires a high degree of security, a personal recognition system using a fingerprint and a personal recognition system using a facial image have been developed. However, in the case of a personal recognition system using fingerprints, accurate fingerprint collection may not be expected, and there is a problem that the applicable range of the system is limited. In addition, the personal recognition system using facial recognition has a problem that the recognition rate is lower than that of the system using fingerprint recognition.

[0004] In order to solve the above problems, an individual identification device using a three-dimensional shape of a hand, which is characterized by easy identification and high recognition rate, has recently been developed and filed by the applicant of the present application. .. However, in this personal identification device, the shape of the hand changes with time, so it is necessary to update the data from time to time. In addition, in the case of a person who has not used the personal identification device for a certain period of time, there is a problem that the device cannot grasp the change in the shape of the person's hand, which leads to an identification error.

[0005] Further, since the reference position for comparison cannot be set for the video data of the hand, it is necessary that the hand is always fixed at a fixed position. Further, even if the position of the hand is fixed by a certain means, it is inevitable that the position of the hand is displaced due to the elasticity of the hand, and there is a problem that it is difficult to accurately identify and compare the shape of the hand.

[0006] [Problems to be Solved by the Invention] The present invention has been made in view of the above-mentioned problems of the conventional personal identification device, personal identification method and personal identification system, and the first object of the present invention is Is new and improved so that the information for personal identification is not stolen and the personal identification rate can be increased.<u style="single">Personal identification method using vein distribution pattern</u>Is to provide.

[Means for Solving the Invention]<u style="single">According to a certain viewpoint of the present invention for solving the above problems, a step of setting a certain area from the input-converted image data of the back of the hand and the image data in the set area of the image data are filtered. Steps, a step of binarizing the filtered image data, a step of extracting a vein distribution pattern from the binarized image data, and a step of branching a vein from the extracted vein distribution pattern. A step of calculating a distribution characteristic indicating a point, the number of branches at the branch point, and a connection relationship between the branch points, and a step of comparing the calculated distribution characteristic with a pre-held distribution characteristic. The step of determining the reference position of the extracted venous distribution pattern from the calculated distribution characteristics, and the reference position of the venous distribution pattern in which the determined reference position is held in advance corresponding to the reference position. The image data corresponds to a specific individual based on the process of image comparison of both vein distribution patterns before and after the matching, the calculated distribution characteristics, and the result of the image comparison. A personal identification method utilizing a venous distribution pattern is provided, including a step of recognizing that there is. The process of setting the fixed area is a process of binarizing the input-converted image data and a process of setting a quadrangle having the maximum area inscribed in the white area of the binarized image data. And may include.</u>[0015] According to this method, it is possible to simplify the digital signal processing of data by including the largest number of vein patterns and reducing the amount of data to be calculated. Furthermore, because the calculation efficiency of the algorithm is high, it is possible to reduce the cost of hardware and produce at a low price.

【0016】<u style="single"></u>According to such a method, it is possible to eliminate the discrepancy of the pattern image caused by the sensed image being tilted to one side by slightly tilting the wrist of the input hand to the left or right.

[Embodiments of the Invention] Hereinafter, preferred embodiments of the personal identification device and the personal identification method using the vein distribution pattern according to the present invention will be described in detail with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals, so that duplicate description will be omitted.

[0020] FIG. 1 is a schematic view of the outer shape of the personal identification device 100 using the vein distribution pattern according to the present embodiment, and FIG. 1 (A) is a perspective view of the personal identification device 100. (B) is a cross-sectional view of the personal identification device 100. First, the configuration of the personal identification device 100 will be described with reference to FIGS. 1 (A) and 1 (B). The personal identification device 100 is designed to be large enough to insert a wrist, for example, as shown in FIGS. 1 (A) and 1 (B), having a width of about 13 cm and a depth of about 15 cm. ..

[0021] The inclined surface on the upper front surface of the personal identification device 100 is provided with a key input unit 1 for inputting a personal identification number or the like (hereinafter, referred to as a key code) by the user, and the input key. The code is input to microprocessor 3, which will be described later. The user places his / her wrist on the wrist splint 30b provided in front of the personal identification device 100 and inserts his / her hand. The user holds a substantially cylindrical fixing bar provided so as to cross the inside of the personal identification device 100 so that the back of the hand faces upward.

On the inner upper surface of the personal identification device 100, a CCD (Charge Coupled Device) camera 10a for photographing the back of the hand, near-infrared illuminations 10b provided on both sides of the CCD camera 10a, and a near-infrared filter that allows only near-infrared rays to pass through. 10c and, are provided. Further, an interface connector 2a for connecting to an external device is provided below the back side of the personal identification device 100. A near-infrared absorber that absorbs near-infrared rays is applied to the inner bottom surface 30, the fixed bar 30a, and the wrist splint 30b.

It is preferable to use near infrared rays to detect the image of the back of the hand as in the present embodiment, but the space inside the device into which the hand is inserted is sealed to some extent so that external light does not enter. In some cases, the vein distribution pattern on the back of the hand can be extracted by projecting using visible light and sensing the image reflected from this. Needless to say, light rays other than visible light, such as ultraviolet rays, can be used instead of near infrared rays.

[0024] Further, even if the personal identification device 100 is not provided with the fixed bar 30a, it is possible for the user to lightly hold the hand and bring it closer to the CCD camera 10a to recognize the back of the hand. In this case, a fixing means for fixing the position of the hand is required so that the back of the user's hand is included in the shooting angle of the CCD camera 10a, and the user's hand is placed in an appropriate position. A confirmation means for confirming the above, for example, a means such as providing a micro switch or the like in front of the shooting position of the CCD camera 10a is required.

FIG. 2 is a block diagram showing an internal configuration of the personal identification device 100. Inside the personal identification device 100, there is a data memory 20b in which personal vein distribution characteristic data is stored in advance, a data converter 20c that converts the video signal of the back of the hand transferred from the CCD camera 10a into still image data, and data. A vein pattern is extracted from the video memory 20a that temporarily stores the still image data generated by the converter 20c and the still image data temporarily stored in the video memory 20a, and the distribution characteristics are obtained from the extracted vein pattern. The identity is judged by comparing the function of detecting data and the venous distribution characteristics in the data memory 20b corresponding to the personal identification information input from the key input unit 1 with the above-extracted venous pattern. It is mainly composed of a microprocessor 3 that has a function to perform data. The microprocessor 3 performs data communication and control control communication with an external device via the interface connector 2a and the interface module 2b.

FIG. 3 is a flow chart of a personal identification method using the personal identification device 100 described above. First, the person receiving the personal identification inputs his / her own key code from the key input unit 1 (step S10), inserts his / her hand into the device from the front of the personal identification device 100, holds the fixed bar 30a, and holds the wrist. Support the wrist splint. The vein pattern on the back of the hand to be extracted by holding the hand appears more vividly. Next, the microprocessor 3 determines whether the input key code exists in the data memory 20b (step S11), and if the input key code does not exist in the data memory 20b, the key code input step is performed again. Return to (step S10). When the input key code exists in the data memory 20b, the image of the back of the hand inserted in the user's device is read by the following process.

[0027] Near-infrared rays are radiated downward by the near-infrared illumination 10b installed above the inside of the personal recognition device 100, and are emitted to the back of the hand through the near-infrared filter 10c located at the center. Near-infrared rays are reflected by the back of the hand, and near-infrared rays radiated to parts other than the back of the hand are absorbed by the near-infrared absorber applied to the inner bottom surface 30, the fixing bar 30a, and the wrist attachment 30b. The near-infrared rays reflected by the back of the hand will be sensed by the CCD camera 10a via the near-infrared filter 10c. At this time, the near-infrared filter 10c completely removes the image of the back of the hand due to the visible light projected from the outside, so that the influence of the disturbance is reduced and the image recognition rate of the back of the hand is increased. The video signal sensed by the CCD camera 10a is converted into still image data as shown in FIG. 4 (A) by the data converter 20c and temporarily stored in the video memory 20a (step S12). ).

[0028] The microprocessor 3 binarizes the image data while maintaining the still image data, and obtains the image data as shown in FIG. 4 (B) composed only of black and white. In Fig. 4 (B), the part corresponding to the back of the hand is shown in white, and the background is shown in black. Next, a rectangular area A that is inscribed in the white area of the image data and has the largest area is set (step S13). The reason for setting the region to be rectangular and having the maximum area is to simplify the digital signal processing of the data by reducing the amount of data to be calculated while including the most vein patterns.

[0029] When the rectangular area A is set by the above step, the microprocessor 3 sets the data in the rectangular area A from the still image data of FIG. 4 (A) temporarily stored in the video memory 20a. Only is extracted, and high-band filtering is performed on the extracted data in order to scan the part of the image where each pixel value (gray tone) changes frequently (step S14). In step S14, the image in the rectangular area A shown in FIG. 5 (A) is obtained, and in the microprocessor 3, the image data in the rectangular area shown in FIG. 5 (A) is toned by the high-band filtering process. ) Became clear, simply select the highest point of the histogram, binarize the image data in region A, and obtain the image data shown in Fig. 5 (B) (step S15). ..

[0030] Even if binarization is performed, as shown in FIG. 5 (B), many miscellaneous images will exist around the boundary line of the vein, and the microprocessor 3 has such miscellaneous images. In order to remove the image, a median filtering process is performed in which black or white pixels are substituted according to the probability of black and white pixels belonging to a certain area. Through this process, image data containing only the vein pattern shown in Fig. 5 (C) is extracted (step S15).

[0031] The microprocessor 3 detects the vein distribution characteristics from the extracted vein pattern and identifies each individual by comparing with the data stored in the data memory 20b. The process is as follows. Is. First, as the distribution characteristic of veins, the venous branching characteristic is detected by subdividing the vein pattern (step S16). The branching characteristics of a vein are composed of the branching point of the vein, the number of branches at the branching point, and the connection relationship between the branching points as detailed elements.

[0032] For example, looking at the vein distribution characteristics obtained from the vein pattern shown in FIG. 5 (C), the total number of branch points is 9 (a, b, ..., I), of which the branch points Three branches are connected to a, and one of them is connected to the branch point e. The fact that the number of branches of the branch point a is three and the number of connecting branch points is one means that the other two branches are disconnected branches, that is, they are not connected to other branch points. It shows that it is a branch. For other branch points (b, c, ..., I), check the number of branch branches and connecting branch points in the same way. Summarizing the results, the branching characteristic data shown in Fig. 6 can be obtained.

[0033] When the above-mentioned branch characteristic data is obtained, the microprocessor 3 compares it with the branch characteristic data of the person corresponding to the key code stored in the data memory 20b, and determines whether or not the person is the same person (). Step S16).

[0034] Further, in order to improve the accuracy of personal identification, two or more specific branch points (for example, the branch points a and the right in the upper left row) in the extracted branch points (a, b, ..., I) After matching the lower branch point g) with the specific branch point of the vein pattern data stored in the data memory 20b in advance, the correlation of pixels with the vein pattern data before the branch characteristic data is extracted ( correlation) will be obtained (step S17). At this time, the reason for setting two or more specific branch points to match is that the wrist of the input hand is slightly tilted to the left or right, and the image detected by the CCD camera 10a is tilted to one side. This is to eliminate the discrepancy.

[0035] It is determined whether the comparison values (correlation) by the two comparison processes (steps S16 and S17) are all equal to or higher than a certain value (step S18). It recognizes that it is a specific person specified by the key code, outputs a control signal through the interface connector 2a, and performs a predetermined process to the outside (for example, opening / closing the door, etc.) (step S20). On the other hand, if any one of the two comparison results is less than a certain value, it is determined that the microprocessor 3 is not the relevant person, and processing such as opening and closing the door is not performed (step S21).

[0036] FIG. 7 shows the configuration of the personal identification system 400 that comprehensively operates the personal identification device 100 that is configured and operates as described above. The personal identification system 400 is located between a plurality of personal identification devices 100, a data storage device 300 that intensively stores venous patterns and branching characteristics between individual individuals to be classified, and a personal identification device and a data storage device 300. It is mainly composed of a communication network 200 that performs data communication.

[0037] In the comprehensive personal identification system 400 configured as described above, the personal identification device 100 is first installed in each fixed area, and the personal identification device 100 has an individual vein pattern in which access is restricted only to that area. And the branching characteristics, and stored for everyone who is identified for the keycode, the data storage device 300 provides venous patterns and branches for individuals whose access is not restricted to areas or where access is restricted to multiple areas. Concentrate on memorizing characteristics.

[0038] In the comprehensive personal identification system 400 constructed as described above, when an individual with no area restriction inputs a key code to the personal identification device 100, the personal identification device 100 confirms the existence of the corresponding key code. At the same time as extracting the relevant vein pattern and branching characteristics, the data storage device 300 is requested to store the stored vein pattern and branching characteristics through the communication network 200.

[0039] When the requested data is received through the communication network 200, the specific individual is identified after performing the above-mentioned comparison operation. In the case of an individual who can move in this way and has a large number of restricted areas, since the data storage device 300 is centrally managed, it is easy to manage when the individual's physical changes occur, and the same data is distributed in many directions. Because it does not, the data storage space can be used effectively. Further, from the above-described embodiment, when the number of installed personal identification devices 100 is small, the data storage device 300 and the personal identification device 100 are directly connected without constructing another communication network. It is also possible to use the communication line.

[0040] The preferred embodiments of the personal identification device, the personal identification method, and the personal identification system according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is clear that a person skilled in the art can come up with various modifications or modifications within the scope of the technical idea described in the claims, and these are naturally included in the technical scope of the present invention. It is understood that it belongs.

[Effects of the Invention] As described above, according to the present invention, the following excellent effects are exhibited.

[0042] Since the personal identification device and the personal identification method using the vein distribution pattern according to the present invention and the comprehensive personal identification system have high algorithm calculation efficiency, the cost of hardware can be reduced and the production can be performed at a low price. By personally identifying the individual using the vein pattern on the back of the hand, which does not change at all, there is no risk of loss or theft when using a card key, etc., and at the same time, the hand is fixed in a fixed position. Since it is not necessary, it can be used more conveniently and has high identification characteristics.

[0043] In addition, by operating a comprehensive personal identification system, efficient identification is possible even when large-scale personnel management is required or in a field where people who move frequently and those who do not move in the area coexist. Since it can use the memory of data, it is the best invention that is economical and convenient, and is not limited to the field of application.

BRIEF DESCRIPTION OF THE DRAWINGS [FIG. 1] FIG. 1 is an explanatory view of an individual identification device using a vein distribution pattern according to the present invention, FIG. 1 (A) is a perspective view, and FIG. 1 (B) is a cross-sectional view. ..

FIG. 2 is an explanatory diagram showing an internal configuration of a personal identification device according to an embodiment of the invention.

FIG. 3 is a flow chart of an individual identification method using a vein distribution pattern according to the present invention.

FIG. 4 is an explanatory diagram for comparing a video signal and its binarized state, FIG. 4 (A) shows a video signal, and FIG. 4 (B) is a binarized image signal. It shows the state of being binarized.

FIG. 5 is an explanatory diagram showing a process of obtaining vein distribution characteristics, FIG. 5 (A) is video data in which a vein characteristic portion is set and high band filtering is performed, and FIG. 5 (B) is FIG. 5 (A). ) Is binarized video data, and Fig. 5 (C) shows the vein distribution characteristics of the data in Fig. 5 (B) as a result of median filtering to remove miscellaneous images.

FIG. 6 is an explanatory diagram showing branching characteristic data extracted and generated from a vein distribution pattern.

FIG. 7 is an explanatory diagram showing a configuration of a personal identification system that comprehensively operates the personal identification device according to the present invention.

[Code description] 1 Key input 2a Interface connector 2b Interface module 3 microprocessor 10a CCD camera 10b Near infrared illumination 10c Near infrared filter 20a Video memory 20b Data memory 20c Data converter 30 Bottom 30a Fixed bar 30b Wrist attachment 100 Personal identification Device 200 Communication network 300 Storage device