KR102333453B1 - Smartphone-based identity verification method using fingerprints and facial images - Google Patents

Abstract

The present invention performs identification by acquiring the fingerprint image and face image of the examinee from the camera built into the police smartphone, and provides a fingerprint and face image that is easy and convenient for front-line police to use and has improved identification speed and accuracy. It relates to a smartphone-based identification method used.
The smartphone-based identification method of the present invention includes: a fingerprint acquisition step in which a fingerprint acquisition assisting device having a camera, which is operated in conjunction with a police smartphone, takes a fingerprint image of the examinee and transmits it to the police smartphone; In the fingerprint image of the examinee received from the step of acquiring the examinee's fingerprint, the police smartphone detects a fingerprint feature point, and transmits the fingerprint image and the fingerprint feature point of the examinee to the matching server through the gateway server, a fingerprint feature detection step of the smartphone; an identity analysis step of the matching server, in which the matching server matches the subject's fingerprint feature points received in the fingerprint detection step with a plurality of comparison target fingerprint features pre-stored in the database unit to confirm the identity; It is characterized in that it includes. In addition, the fingerprint acquisition assisting device forms a thimble, and includes a camera in the contact portion of the bottom surface of the finger.

Description

Smartphone-based identity verification method using fingerprints and facial images}

The present invention performs identification by acquiring the fingerprint image and face image of the examinee from the camera built into the police smartphone, and provides a fingerprint and face image that is easy and convenient for front-line police to use and has improved identification speed and accuracy. It relates to a smartphone-based identification method used.

When a police officer working at the front line finds a person suspected of being a drunken person, the elderly with dementia, a lost child, a deceased person, an illegal immigrant, a wanted person, or a criminal, he/she will accompany them to the police station and then use the computer at the police station. through the identification process.

In some cases, it is inconvenient to have even unrelated people go to the police station to verify their identity.

Problems that are continuously being addressed in the current fingerprint field are the degradation of fingerprint recognition performance and too low image quality. Although there are various types of fingerprints, since all fingerprints have a certain pattern, it is possible to improve the image quality by analyzing the pattern of the image and improving the direction information.

Therefore, an identity verification system with improved fingerprint image quality is desired so that police officers can obtain fingerprints of subjects using their smartphones or mobile devices (laptops, PDFs, etc.)

In addition, fingerprint recognition technology and face recognition technology can be employed to confirm the identity of a subject using a police officer's smartphone (hereinafter referred to as a police smartphone).

Fingerprint recognition technology is a technology for recognizing a user by acquiring a digital image of a fingerprint using a dedicated sensor, and includes optical fingerprint recognition, capacitive fingerprint recognition, ultrasonic fingerprint recognition, and the like.

In the case of the national DB, since fingerprints are stored for all 10 fingers, it is necessary to match approximately 500 million fingerprints. is an element

Face recognition technology is a technology that analyzes and recognizes about 50 different parts of the facial skeleton, such as the nose, mouth, eyebrows, and chin, rather than the entire face. Facial images are sensitive to lighting, environment, and image angle, and have disadvantages in distinguishing disguise, facial changes that occur over time, plastic surgery, and similar facial features of twins.

The present invention requires an identification system that can confirm the identity more quickly and accurately in the field by acquiring an image of the subject's fingerprint and face using a smart phone or mobile device (laptop, PDF, etc.) carried by the police officer himself. do.

As a prior art, Korean Registered Utility Model Publication No. 20-0283571 relates to a portable identification device that scans an identification card or a biometric fingerprint of an identification card holder and compares it with information registered in an administrative computer network to confirm the identity of the person. In this case, since only a fingerprint is recognized, it is impossible to check if the fingerprint is erased.

As another prior art, Korean Unexamined Patent Publication No. 2003-0086527 relates to a police radio that can confirm whether the background checker is a party by comparing the fingerprint corresponding to the background checker's resident registration number with the fingerprint input by the background checker. , also in this case, since only the fingerprint is recognized, it is impossible to check if the fingerprint is erased.

As another prior art, Korean Unexamined Patent Publication No. 2002-0011577 discloses that the identity of a user on the Internet, data such as fingerprints and face photos, is stored in advance in a verification database, and then the user's fingerprints and face photos, etc. It relates to a user identification system on the Internet that is designed to compare and verify data of users.

The problem to be solved by the present invention is to obtain a fingerprint image and an image of a subject's face from a camera built in a police smartphone to perform identification, while being convenient for front-line police to use, and to increase the speed and accuracy of identification, It is to provide a smartphone-based identification method using fingerprints and face images.

In order to solve the above problem, the smart phone-based identification method of the present invention detects a fingerprint feature point in the police smart phone from the fingerprint image of the subject taken by the camera of the police smartphone, and gateways the fingerprint image and the fingerprint feature point of the examinee a step of detecting fingerprint information of a police smart phone, which is transmitted to the matching server through the server; an identity analysis step of the matching server, in which the matching server matches the subject's fingerprint feature points received in the fingerprint detection step with a plurality of comparison target fingerprint features pre-stored in the database unit to confirm the identity; It is characterized in that it includes.

In addition, the smartphone-based identification method of the present invention is operated in conjunction with a police smart phone, the fingerprint acquisition assisting device having a camera captures the subject's fingerprint image and transmits it to the police smart phone, the subject's fingerprint acquisition step; In the fingerprint image of the examinee received from the step of obtaining the examinee's fingerprint, the police smartphone detects a fingerprint feature point, and transmits the fingerprint image and the fingerprint feature point of the examinee to the matching server through the gateway server, a fingerprint information detection step of the smartphone; An identity analysis step of the matching server, in which the matching server matches the fingerprint feature points of the examinee received in the fingerprint detection step with a plurality of comparison target fingerprint features pre-stored in the database unit to verify the identity; characterized by comprising: do.

The fingerprint acquisition assisting device is in the form of a thimble, and includes a camera in the contact part of the bottom surface of the finger.

The fingerprint feature point includes an end point and a branch point of the ridge of the fingerprint.

The fingerprint information detection step of the police smartphone is a finger fingerprint image receiving step, in which the operation processing unit of the police smartphone receives the finger fingerprint image captured by the camera of the police smartphone or a fingerprint acquisition auxiliary device linked with the police smartphone. ; The police smartphone compares whether the finger fingerprint image taken in the finger fingerprint image receiving step is a finger fingerprint with the color of a pre-stored finger to determine whether it is a finger fingerprint, and if it is determined that it is not a finger fingerprint, a text message or by voice, notifying that it is not a finger print, and returning to the finger fingerprint image receiving step, a finger color comparison step; After the finger color comparison step, the operation processing unit of the police smartphone extracts the outline of the finger from the finger fingerprint image and determines whether the outline of the finger is smaller than the finger photographing guideline, and whether it is within the finger photographing guideline and limit, Deviating from the threshold or smaller than the finger photographing guideline, notifying the deviation of the finger photographing guideline by text or voice, and returning to the finger fingerprint image receiving step, determining whether a fingerprint image is input; The operation processing unit of the police smartphone, in the step of determining whether a fingerprint image is input or not, if the outline of the corresponding finger is greater than or equal to the finger photographing guideline, but is within the limit of the finger photographing guideline, the fingerprint image is centered on the fingerprint guideline by 100px × 100px , the horizontal ridges and the vertical ridges are detected in the fingerprint image by extracting the image of , indicating that it is not a finger fingerprint image, and returning to the finger fingerprint image receiving step, a ridge check step; includes.

In the fingerprint information detection step of the police smartphone, after the ridge check step, the operation processing unit of the police smartphone detects a fingerprint feature point including an endpoint and a branch point of the ridge of the fingerprint from the fingerprint image of the subject. It further includes a detection step.

The fingerprint feature detection step includes: a pre-processing step in which the operation processing unit of the police smartphone thins out the fingerprint image of the examinee; The operation processing unit of the police smartphone detects a candidate fingerprint feature point in the fingerprint image thinned in the pre-processing step, a candidate fingerprint feature point detection step; The arithmetic processing unit of the police smart phone includes a post-processing step of removing the pseudo feature point from the feature point detected in the candidate fingerprint feature point detection step.

In the identity analysis step of the matching server, the matching server calculates the rotation and transition amount in which the feature points of the fingerprint image of the subject and the feature points of the comparison target stored in the database pre-stored in the database overlap the most, and the rotation and transition amount of the image is calculated. an alignment step of selecting an alignment reference point, transforming the coordinates of the characteristic point to fit the alignment reference point, and determining a corresponding characteristic point pair; A matching step of calculating the degree of similarity by the matching server using the coordinates, types, and angle information of the corresponding feature point pairs determined in the alignment step; The matching server comprises: a score acquisition step of outputting, according to preset rule data, the degree of matching between the fingerprint feature point of the examinee and the fingerprint feature point of the comparison object stored in advance in the database from the degree of similarity of the corresponding feature point pair as a score; .

In the identity analysis step of the matching server, before the alignment step, the matching server obtains the ridge spacing for the fingerprint image of the examinee received from the operation processing unit of the police smartphone, and normalizes the ridge spacing using the maximum and minimum values of the ridge spacing By doing, standardizing, ridge interval standardization step; After the ridge interval standardization step, the matching server detects the ridge direction information from the fingerprint image of the examinee, and determines that the ridge direction information is incorrect when there are no two or more identical ridge directions in any one of the front, rear, left, and right and a correction step of correcting the fingerprint feature points of the subject by correcting the wrong ridge direction information in the direction of the ridge before, after, left, or right of the ridge with the wrong ridge direction information. include

It features a recording medium storing a smartphone program source for the smartphone-based identification method of the present invention.

The smartphone-based identification method of the present invention performs identification by acquiring the fingerprint image and face image of the examinee from a camera built into the police smartphone, and it is convenient for front-line police to use, and the identification speed and accuracy are improved. made to be raised. That is, according to the present invention, a police officer himself can use a smartphone or a mobile device (laptop, PDF, etc.) carried to obtain an image of the subject's fingerprint and face, and confirm the identity more quickly and accurately in the field.

In particular, it is possible to establish a database for drunk people, lost children or elderly people with dementia, and to check the identity of the subject in one-stop in connection with the database.

1A is a schematic diagram for schematically explaining the configuration of an identification system to which a smartphone-based identification method using a fingerprint and face image of the present invention is applied.
1B is a flowchart schematically illustrating a smartphone-based identification method using a fingerprint and face image of the present invention.
FIG. 2 is an example of an auxiliary device for acquiring a fingerprint applied to the smartphone of FIG. 1 .
3 is an explanatory diagram for explaining image improvement according to direction information.
4 is an explanatory diagram for explaining distortion of a general fingerprint image.
5 is an explanatory diagram for explaining the change of the coordinates of the characteristic information according to the determination of the rotation angle.
6 is an example of outputting matching feature points between comparison target fingerprints and connection information between key points.
7 is an explanatory diagram for explaining the use of the feature information similarity around the corresponding feature information when checking the feature information similarity.
8 is an explanatory diagram schematically illustrating a fingerprint recognition process in a matching server.
9 is an example in which the index finger of the right hand is photographed on the fingerprint photographing screen of the police smartphone of the present invention.
FIG. 10 is a view for explaining whether a finger selected on the fingerprint photographing screen of FIG. 9 matches a finger photographing guideline.
11 is a flowchart schematically illustrating a driving process of a police smartphone in the smartphone-based identification method of the present invention.
12 is a flowchart for explaining the feature information detection step of FIG. 11 .
13 is a flowchart for schematically explaining the identification process in the matching server 300 in the smartphone-based identification method of the present invention.

Hereinafter, an identification system using a smartphone of the present invention will be described in detail with reference to the accompanying drawings.

In the present invention, the smart phone or mobile device (laptop, PDF, etc.) carried by the police officer himself is broadly classified as a 'police smartphone'.

1A is a schematic diagram for schematically explaining the configuration of an identification system to which a smartphone-based identification method using a fingerprint and face image of the present invention is applied, and FIG. 1B is a smartphone-based diagram using a fingerprint and face image of the present invention It is a flowchart schematically explaining the identification method.

Police smartphone (police officer's smartphone) 100 is a smartphone in which a predetermined application is installed through a specific registration process such as authentication, and takes a fingerprint or face image of the examinee on the police smartphone 100 ( S10), detecting the feature point of the fingerprint or face from the image of the fingerprint or face (S20), selecting the identification group, and selecting the identity confirmation request, detects the feature point from the fingerprint image or the image of the face of the subject, and the identity The confirmation request signal, the identification group signal, the fingerprint feature points, and the facial feature points are transmitted to the gateway (G/W) server 200 (S30).

Here, the identification group can be entered by selecting the age group, gender, etc., and can also be set as a drunken person, an elderly person with dementia, a lost child, a deceased person, a foreigner, a wanted person, a criminal, and the like.

In the present invention, fingerprint acquisition is possible without a fingerprint acquisition aid device, but in some cases, a fingerprint acquisition aid device may be used.

In the case of fingerprint recognition, in the case of contact technology, the resolution is fixed at 500 dpi, but in general, in the case of smartphones, the resolution is different depending on the distance at which the object is photographed, so the misrecognition rate may be high during matching.

In general, when acquiring a fingerprint on a fingerprint sensor, the fingerprint shape is deformed according to the pressure of the position where the finger is applied. resolution compatibility can be ensured.

In some cases, the police smartphone 100 may receive and use a fingerprint image acquired using a live scanner, which is an existing fingerprint input device, instead of the police smartphone 100 and the fingerprint acquisition auxiliary device. .

The gateway (G/W) server 200 receives the identity confirmation request signal, the identity confirmation group signal, the fingerprint feature points, and the facial feature points received from the police smartphone 100, and transmits them to the matching server 300 (S35) ).

The matching server 300 matches and compares the fingerprint feature points of the identity verification group previously stored in the database unit 370 and the fingerprint feature points of the examinee received through the gateway server 200 to verify the identity, and also , the facial feature points of the identification group previously stored in the database unit 370 and the facial feature points of the examinee received through the gateway server 200 are matched and compared to perform identification (S50), and the result is converted into a gateway It is transmitted to the police smart phone 100 through the server 200 (S60).

FIG. 2 is an example of an auxiliary device for acquiring a fingerprint applied to the smartphone of FIG. 1 .

The fingerprint acquisition assisting device 170 of FIG. 2 is made in the form of a finger clip, that is, a thimble, and includes a fingerprint detection sensor 177 at the part where the bottom of the finger is closed.

The housing portion of the fingerprint acquisition auxiliary device 170 surrounds the front and rear surfaces of the finger of the examinee and is made in the form of a finger clip, that is, a thimble that applies horizontal pressure to the finger, and when the corresponding finger is inserted into the acquisition auxiliary device, the fingerprint detection sensor A finger fingerprint is formed by (177).

The fingerprint detection sensor 177 is a means for acquiring image information of a finger fingerprint, and the fingerprint detection sensor 177 detects a fingerprint image and transmits it to an operation processing unit (not shown) of the police smartphone 100. The fingerprint detection sensor 177 is It may be a camera or an image sensor.

3 is an explanatory diagram for explaining image improvement according to direction information, FIG. 4 is an explanatory diagram for explaining distortion of a general fingerprint image, and FIG. 6 is an example of outputting matching feature points between the comparison target fingerprints and connection information between the feature points, and FIG. 7 is an explanatory diagram for explaining the use of the feature information similarity around the feature information when checking the feature information similarity. .

Fig. 3 (a) shows an example of low image quality, the green line in Fig. 3 (a) is direction information that should be actually displayed (that is, direction information indicated by an expert), and (b) of Fig. 3 (b) is As an example of analyzing the direction information in the fingerprint image of Fig. 3 (a) by a conventional analysis method, it can be seen that the direction information is properly incorrect in the part within the rectangle of Fig. 3 (a). That is, there is a problem in the direction information. Figure 3 (c) is an example of correcting the fingerprint image to improve the direction information in the fingerprint image of Figure 3 (a).

That is, the present invention improves the image quality by improving the direction information by analyzing the pattern of the image.

Fig. 4(a) is an example of twisting downwards, Fig. 4(b) is an example of twisting upwards, Fig. 4(c) is an example of twisting right, and Fig. 4(d) is an example of twisting left. am.

That is, when the subject takes a fingerprint, image distortion occurs according to the pressure of the finger, that is, the direction in which the finger is applied. Accordingly, the matching server 300 detects the distortion direction of the image during fingerprint comparison and corrects the image to fit the square.

In the present invention, the matching server 300 multiplexes rotation and displacement selection to improve the transformed image matching performance.

Fig. 5 (a) shows an example of setting the angle change of the input fingerprint image, and Fig. 5 (b) shows the coordinate changed fingerprint image according to the angle change of Fig. 5 (a).

The matching server 300 attempts matching using a plurality of rotation values because the rotation angle may have a different rotation angle depending on the image position when the image deformation is large and the influence of the rotation angle determination on the coordinates of the characteristic information is large.

Figure 6 (a) is an example of a fingerprint stored in the database unit, Figure 6 (b) is an example of the subject fingerprint, the matching feature point between the two fingerprints is indicated by a red line, and the connection information between the feature points is indicated in blue color. indicated by a line.

Visual fingerprint recognition result expression information is obtained from the police smartphone 100, and the matching server 300 receives it and uses it as an assistant when determining whether the fingerprint is the same. That is, when it is difficult to determine whether the matching server 300 is the same fingerprint, the matching server 300 may determine it using the visual fingerprint recognition result expression information.

As shown in FIG. 6 , it is possible to determine whether the fingerprint is the same or not by outputting matching feature points between the comparison target fingerprints and connection information between the feature points. Even when the distance between the feature information or the value of the feature point direction is changed due to the fingerprint deformation, the inspection feature point and the information around it move together, so there is little deviation. Therefore, as in FIG. 7 , when checking the similarity of the feature information, the similarity of the feature information around the feature information is considered.

Figure 7 (a) is a feature point (M1 ~ M5) surrounding the feature point (Mr) in the fingerprint stored in the database unit, Figure 7 (b) is a feature point (M1 ~) surrounding the feature point (Ms) of the subject's fingerprint to be matched. In M5), the similarity of the feature points around the feature point to be compared is examined, and the similarity of feature information is detected using the similarity review result.

In the present invention, since index information is used for 1:N comparison in order to improve the fingerprint recognition speed in the matching server 300, the speed is faster than when other algorithms are applied (eg, analysis of about 100,000 people per second). Since the static classification fingerprint type has a limited type, the present invention dynamically selects an object and performs a high-speed search.

8 is an explanatory diagram schematically illustrating a fingerprint recognition process in a matching server.

In the fingerprint characteristic information processing step (S200), the fingerprint characteristic information is processed for high-speed search.

In the similarity test and preliminary target selection step (S300), the similarity is checked in the feature information processed in the fingerprint feature information processing step (S200), the fingerprint feature information stored in the database unit is sorted according to the similarity score, and the sorted database unit Among the fingerprint characteristic information stored in the , a preliminary target determined to be similar to the examinee's fingerprint characteristic information is selected. In the similarity test and preliminary target selection step (S300), the number (size) of preliminary targets (candidates) is determined in consideration of the DB size of the target group stored in the database unit.

FIG. 9 is an example of the right index finger being photographed on the fingerprint photographing screen of the police smartphone of the present invention, and FIG. 10 is a diagram explaining whether a finger selected on the fingerprint photographing screen of FIG. 9 matches the finger photographing guidelines.

FIG. 9(a) shows an example of selecting the right index finger on the fingerprint photographing screen, and clicking the right index finger selection button in the right and left hand pictures at the bottom of the fingerprint photographing screen. Finger shooting guidelines are displayed in the middle of the fingerprint shooting screen, fingerprint guidelines (blue circles in the case of FIG. The limits (triangles) of the range that may deviate from these guidelines are marked. In addition, at the top of the fingerprint photographing screen, a message is output to proceed with photographing by placing a predetermined finger selected in the finger photographing guideline.

Figure 9 (b) is an example of a fingerprint photographing screen by contacting the index finger of the right hand to the screen.

Fig. 10 (a) is an example of a case where the index finger of the right hand, which is a selected finger on the fingerprint photographing screen, deviates from the finger photographing guideline, and (b) is a case where the right index finger is smaller than the finger photographing guideline on the fingerprint photographing screen This is an example, and (c) of FIG. 10 is an example of a case in which the index finger of the right hand coincides with the finger photographing guideline on the fingerprint photographing screen.

As shown in (c) of FIG. 10 , when the boundary line of the finger is positioned between the finger photographing guideline and the limit point, the fingerprint to be photographed is properly located within the fingerprint guideline.

In the present invention, a mobile-only app was developed to acquire a fingerprint image from the camera of the police smart phone 100 or the fingerprint acquisition auxiliary device 177 . When acquiring a fingerprint image through the mobile app, the app presents a guideline for finger shooting for the fingerprint image input part, and checks three items for the finger input in the guideline, that is, the finger fingerprint image through color comparison. It is possible to obtain a high-quality finger fingerprint image by checking whether the fingerprint image is properly entered in the guideline, checking whether the fingerprint image is properly entered, and checking the ridgeline.

11 is a flowchart schematically illustrating a driving process of a police smartphone in the smartphone-based identification method of the present invention, and FIG. 12 is a flowchart for explaining the feature information detection step of FIG. 11 . Here, it can be said that FIG. 11 shows the fingerprinting and feature point detection process in the police smartphone.

In the finger fingerprint image receiving step, the operation processing unit of the police smartphone 100 receives the fingerprint image captured by the camera of the police smartphone or the fingerprint acquisition auxiliary device 170 linked with the police smartphone (S110) ).

In the finger color comparison step, the operation processing unit of the police smartphone 100 compares whether the finger fingerprint image photographed in the finger fingerprint image receiving step is a finger fingerprint or not, with the color of a pre-stored finger, whether it is a finger fingerprint or not. is primarily determined (S120), and if it is determined that the fingerprint is not a finger, it is notified by text or voice that it is not a finger (S125), and the flow returns to the finger fingerprint image reception step (S110).

In the fingerprint image input determination step, after the finger color comparison step, the operation processing unit of the police smartphone 100 extracts the outline of the finger from the finger fingerprint image to determine whether the outline of the finger is smaller than the guideline for photographing the finger, and It is determined whether it is within the shooting guideline and limit (S130), and if it is outside the limit or smaller than the finger shooting guideline, it is notified by text or voice (S135), and returns to the finger fingerprint image receiving step (S110). At this time, the operation processing unit of the police smartphone 100 determines that an appropriate fingerprint image is input in the fingerprint guideline if the outline of the corresponding finger is greater than or equal to the finger photographing guideline, but is within the finger photographing guideline and the threshold. If it is out of , or smaller than the finger photographing guideline, it is determined that an appropriate fingerprint image is not input in the fingerprint guideline.

In the ridge check step, in the step of determining whether a fingerprint image is input, if it is determined that an appropriate fingerprint image is input within the fingerprint guide The operation processing unit of the smartphone 100 extracts the fingerprint image as an image of 100px × 100px based on the fingerprint guideline, detects horizontal ridges and vertical ridges in the fingerprint image (S140), and horizontal ridges and vertical ridges It is determined whether the directional ridges form a pattern by repeating a certain portion of each (S150), and if the horizontal ridges and the vertical ridges each repeat a certain portion to form a pattern, it is determined as a fingerprint image of the finger, and if the pattern is not formed, the finger It is determined that it is not a fingerprint image, and it is notified that it is not a finger image by text or voice (S155), and the flow returns to the finger fingerprint image receiving step (S110).

In the feature information detection step (S160), the operation processing unit of the police smartphone 100 extracts feature information from the finger fingerprint image, and the feature information detection step includes a pre-processing step (S161), a feature point extraction step (S163) and the post-processing (post-processing) proceeds to three steps (S167).

The pre-processing step S161 is a step of thinning the fingerprint image, and image enhancement is performed, and the image-enhanced fingerprint image is binarized and thinned. That is, in the pre-processing step, a conversion process into a block directional image, a binarized image, and a thinned image is performed. The fingerprint image is divided into blocks of a certain size, and the direction representing the flow of the ridge is determined for each block and converted into a direction image for each block. The ridge direction information for each block obtained in this way is used in the binarization and smoothing process. In the binarization process, the fingerprint image is changed to a binary image that is expressed only in black and white, and the binary image again goes through smoothing processing that removes noise and emphasizes fusion to improve the connectivity of fusion and convert fusion into a line with a thickness of 1 pixel. It is expressed and converted into a thinning image,

The feature point extraction step ( S163 ) is a step of extracting candidate (preliminary target) feature points from the fingerprint image thinned in the pre-processing step. Here, the minutiae refers to points where changes occur in the flow of the ridge called a disadvantage (a point where the flow of the ridge is cut off) and a bifurcation (a point where one ridge splits into two). The feature quantity (T = {m1, m2, , mm}) consists of information on the feature point (mi) that exists in the fingerprint image. , the location in the fingerprint image, and the direction of the ridge where the feature point is located.

That is, the key point extraction step is a candidate key point extraction process, and information about the shortcomings and junctions in which the flow of the ridge is changed from the thinned image is stored. Candidate feature points including pseudo feature points are extracted from the ridge information of the thinned image. In this case, pseudo feature points may be generated due to an incorrect ridge portion of the thinned image. The pseudo feature point refers to a fake feature point generated during the thinning process due to noise during fingerprint acquisition. The pseudo feature point increases the amount of meaningless computation and increases the error, which is a factor that degrades the system performance.

The post-processing step S167 is a step of removing fake key points from the key points extracted in the key point extraction step. That is, in the post-processing step, a final feature point is extracted by correcting the ridge portion that is the cause of the pseudo feature point, removing the pseudo feature point, and adding the missing feature point.

In the feature information transmission step, the operation processing unit of the police smartphone 100 transmits the feature information and the fingerprint image composed of the candidate feature points detected in the feature information detection step to the matching server 300 through the gateway server 200 ( S170).

13 is a flowchart schematically illustrating an identity verification process in the matching server 300 .

In the ridge spacing standardization step (S210), the ridge spacing is obtained for the fingerprint image received from the operation processing unit of the police smartphone 100, and the ridge spacing is normalized using the maximum and minimum values of the ridge spacing. to have

In the correction step (S220), the part where the direction information is wrong by analyzing the ridge direction information in the fingerprint image received from the operation processing unit of the police smart phone 100 (for example, two or more identical When there is no direction information, correct the direction information (eg, correct the direction of the previous ridge of the wrong part).

In the fingerprint matching step (S310), the matching server 300 uses the matching algorithm of the fingerprint recognition method using the feature point, using the feature amount defined from the feature point information extracted from the operation processing unit of the police smartphone 100. This is a step of determining the similarity between two fingerprint images, and includes three steps: an Image Alignment step (S320), a Mnutiae Matching step (S330), and a scoring step (S350).

In the alignment step (S320), an alignment reference point of the image is selected by calculating the amount of rotation and transition in which the feature points of the two fingerprint images overlap the most. Then, after transforming the coordinates of the feature points to fit the alignment reference point, a corresponding feature point pair is determined. In this case, in order to find the ideal rotation shift amount, as many candidate alignments as possible should be performed.

In the matching step (S330), a similarity (Measure Vector) is calculated using the coordinates, types, and angle information of the corresponding feature point pairs determined in the alignment step. In order to realistically reflect the similarity of the corresponding feature point pair, it can be considered from various angles with various statistical techniques in the similarity determination method.

In the scoring (Scoring) step ( S350 ), the degree of matching between the two fingerprint images from the similarity (Measure Vector) of the corresponding feature point pair is expressed as a score according to preset rule data. Rule data is data determined in advance by using statistical basis and mathematical modeling for score calculation rule selection (decision making) to accurately reflect the degree of matching of images as in the matching step.

In the preliminary target selection step (S360), when the score obtained according to the similarity of the corresponding characteristic point pair in the scoring step exceeds a predetermined threshold, the fingerprint characteristic information of the database unit is selected as a preliminary target, or the database with the highest score The negative fingerprint characteristic information is selected as a preliminary target, and it is transmitted to the police smartphone through the gateway server.

The conventional device for acquiring a fingerprint image was acquired using a live scanner, but in the present invention, the fingerprint image acquired from the camera of the existing live scanner or the camera of the police smartphone 100 or the camera of the fingerprint acquisition auxiliary device 177 is compared. Verify your identity.

However, in general, when a fingerprint image is acquired with a camera, compatibility with a fingerprint image acquired with an existing device cannot be guaranteed if the distance from the camera to the finger is not constant. Therefore, the present invention obtains the interval of ridges for the acquired fingerprint image in order to standardize the fingerprint image obtained differently according to the live scanner, the camera of the police smart phone 100, etc., and improves the image based on the standardized interval A fingerprint template is created from the image.

Matching server 300 is MCU (matching controller units, matching control unit) (not shown), MPU (matching process units, matching processing unit) (not shown), MMU (Matching Monitoring Uni, matching monitoring unit) (not shown) includes

The MCU is a means for controlling the matching server 300 as a whole, and its main functions are two types of fingerprint matching task management and MPU management.

The fingerprint matching task management function of the MCU fetches the fingerprint identification request information received from the G/W server 200, pre-stored data from the DB unit 370, requests the matching operation to the MPU connected to the MCU, and requests the MPU The matching results are collected to determine the candidates, and the results are delivered to the G/W server.

The MPU management function of the MCU monitors the status of the MPU through the MMU and manages the start and stop of the MPU. When a process of a specific MPU is stopped or a deadlock occurs, the MCU can determine the status through MPU monitoring and restart the process of the corresponding MPU.

The MPU analyzes the fingerprint matching task requested from the MCU to determine the matching target, compares the characteristic points of the requested fingerprint with the characteristic points of the target fingerprint, and transmits target fingerprint information with a high degree of similarity to the MCU.

The MMU monitors the status of the MPU linked with the MCU and inquires the MPU's operation log. The MMU transmits a status check message to the MPU, and the received MPU checks its own status and sends a status check message to the MMU. When the MMU does not normally receive a message from the MPU or receives a received message in an abnormal state, the MMU transmits the operation status of the corresponding MPU to the MCU, and the MCU sends a message for restarting the process to the MPU to restart the MPU function. .

In the present invention, the matching server and the database unit may be referred to as a fingerprint matching system.

The fingerprint data of the fingerprint matching system is managed in a distributed environment to optimize the performance of the MPU. Distributed processing of fingerprint data is performed in two ways: real-time distributed processing and batch distributed processing.

In real-time distributed processing, the fingerprint data changed during operation of the fingerprint matching system is distributed to each MPU. When a change is detected, the changed fingerprint data is distributed and audited to ensure the consistency of the data.

Batch distributed processing can be performed when an initial fingerprint matching system is established or when fingerprint data in the main database is batch distributed with the MPU when there are many changes in fingerprint data. It distributes basic data and conducts auditing to ensure the consistency of fingerprint data.

As described above, although the present invention has been described with reference to the limited examples and drawings, the present invention is not limited to the above examples, which are various modifications and Transformation is possible. Accordingly, the spirit of the present invention should be understood only by the claims described below, and all equivalents or equivalent modifications thereof will fall within the scope of the spirit of the present invention.

100: police smartphone 170: fingerprint acquisition auxiliary device 177: fingerprint detection sensor
200: gateway server 300: matching server 370: database unit

Claims (10)

In the fingerprint image of the subject taken by the police smartphone camera, the police smartphone detects a fingerprint feature point and transmits the fingerprint image and the fingerprint feature point of the examinee to the matching server through the gateway server, a fingerprint information detection step of the police smartphone;
an identity analysis step of the matching server, in which the matching server matches the subject's fingerprint feature points received in the fingerprint detection step with a plurality of comparison target fingerprint features pre-stored in the database unit to confirm the identity;
In a smartphone-based identification method comprising a,
The identity analysis step of the matching server is,
The matching server selects the alignment reference point of the image by calculating the rotation and transition amount in which the fingerprint characteristic point of the examinee and the fingerprint characteristic point of the comparison target stored in the database unit overlap the characteristic points of the two fingerprint images the most, and the alignment reference point is selected. an alignment step of transforming the coordinates of the feature points to fit in and determining a corresponding feature point pair;
A matching step of calculating the degree of similarity by the matching server using the coordinates, types, and angle information of the corresponding feature point pairs determined in the alignment step;
A score acquisition step of the matching server outputting, according to preset rule data, the degree of matching between the fingerprint feature point of the examinee and the fingerprint feature point pre-stored in the database, as a score, from the degree of similarity of the corresponding feature point pair;
A smartphone-based identification method, characterized in that it comprises a. A fingerprint acquisition step of acquiring the fingerprint of the examinee by photographing the fingerprint image of the examinee and transmitting the photographed fingerprint image to the police smartphone by an auxiliary device for obtaining a fingerprint that is operated in conjunction with a police smartphone;
In the fingerprint image of the examinee received from the step of obtaining the examinee's fingerprint, the police smartphone detects a fingerprint feature point, and transmits the fingerprint image and the fingerprint feature point of the examinee to the matching server through the gateway server, a fingerprint information detection step of the smartphone;
an identity analysis step of the matching server, in which the matching server matches the subject's fingerprint feature points received in the fingerprint detection step with a plurality of comparison target fingerprint features pre-stored in the database unit to confirm the identity;
In a smartphone-based identification method comprising a,
The identity analysis step of the matching server is,
The matching server selects the alignment reference point of the image by calculating the rotation and transition amount in which the fingerprint characteristic point of the examinee and the fingerprint characteristic point of the comparison target stored in the database unit overlap the characteristic points of the two fingerprint images the most, and the alignment reference point is selected. an alignment step of transforming the coordinates of the feature points to fit in and determining a corresponding feature point pair;
A matching step of calculating the degree of similarity by the matching server using the coordinates, types, and angle information of the corresponding feature point pairs determined in the alignment step;
A score acquisition step of the matching server outputting, according to preset rule data, the degree of matching between the fingerprint feature point of the examinee and the fingerprint feature point pre-stored in the database, as a score, from the degree of similarity of the corresponding feature point pair;
A smartphone-based identification method, characterized in that it comprises a. 3. The method of claim 2,
The fingerprint acquisition assisting device is in the form of a thimble, and a camera is provided in the contact part of the bottom of the finger, a smartphone-based identification method. 3. The method of any one of claims 1 or 2,
The fingerprint feature point is a smart phone-based identification method, characterized in that it includes an end point and a bifurcation point of the ridge of the fingerprint. According to any one of claims 1 to 2, wherein the fingerprint information detection step of the police smartphone,
a finger fingerprint image receiving step of receiving, by the operation processing unit of the police smart phone, a finger fingerprint image captured by a camera of a police smartphone or a fingerprint acquisition auxiliary device interlocked with a police smartphone;
The police smartphone compares whether the finger fingerprint image taken in the finger fingerprint image receiving step is a finger fingerprint with the color of a pre-stored finger to determine whether it is a finger fingerprint, and if it is determined that it is not a finger fingerprint, a text message or a voice, notifying that the finger is not a fingerprint, and returning to the finger fingerprint image receiving step, a finger color comparison step;
After the finger color comparison step, the operation processing unit of the police smartphone extracts the outline of the finger from the finger fingerprint image and determines whether the outline of the finger is smaller than the finger photographing guideline, and whether it is within the finger photographing guideline and limit, Deviating from the threshold or smaller than the finger photographing guideline, notifying the deviation from the finger photographing guideline by text or voice, and returning to the finger fingerprint image receiving step, determining whether a fingerprint image is input;
The operation processing unit of the police smartphone, in the step of determining whether a fingerprint image is input or not, if the outline of the corresponding finger is greater than or equal to the finger photographing guideline, but is within the limit of the finger photographing guideline, the fingerprint image is centered on the fingerprint guideline by 100px × 100px , the horizontal and vertical ridges are detected in the corresponding fingerprint image by extracting the image of Informing that it is not a finger fingerprint image, and returning to the finger fingerprint image receiving step, a ridge check step;
A smartphone-based identification method comprising a. The method of claim 5, wherein the step of detecting fingerprint information of the police smart phone comprises:
After the ridge check step, the operation processing unit of the police smart phone, a fingerprint feature detection step of detecting a fingerprint feature point including an edge point and a branch point of the ridge of the fingerprint from the fingerprint image of the examinee;
Which further comprises, a smartphone-based identification method. The method of claim 6, wherein the fingerprint feature detection step comprises:
The operation processing unit of the police smartphone thinning the fingerprint image of the examinee, a pre-processing step;
The operation processing unit of the police smartphone detects a candidate fingerprint feature point in the fingerprint image thinned in the pre-processing step, a candidate fingerprint feature point detection step;
The post-processing step of the operation processing unit of the police smart phone removing the pseudo feature point from the feature point detected in the candidate fingerprint feature point detection step;
A smartphone-based identification method, characterized in that it comprises a. delete The method of claim 7, wherein the identity analysis step of the matching server comprises:
Before the alignment step, the matching server obtains the interval of the ridge for the fingerprint image of the subject received from the operation processing unit of the police smartphone and normalizes the ridge intervals using the maximum and minimum values of the ridge interval. standardization stage;
After the ridge interval standardization step, the matching server detects the ridge direction information from the fingerprint image of the examinee, and determines that the ridge direction information is incorrect when there are no two or more identical ridge directions in any one of the front, rear, left, and right and correcting the fingerprint feature points of the subject by correcting the wrong ridge direction information in the direction of the ridge before, after, left, or right of the ridge with the wrong ridge direction information;
Which further comprises, a smartphone-based identification method. [Claim 3] The computer-readable recording medium storing a smartphone program for performing the smartphone-based identification method according to any one of claims 1 to 2.

Images