KR102105669B1 - System and Method for Judging Biometric Recognition and Fake Biometric Detection of Mobile Device - Google Patents

Abstract

Disclosed is a system and method for analyzing biometric performance and counterfeit defense capabilities of a mobile terminal. The forgery defense analysis system according to the present invention may be connected to a mobile terminal having a biorecognition sensor, to evaluate the biorecognition performance of the biorecognition sensor and the counterfeit defense ability to distinguish the forged living body. To this end, the mobile terminal acquires a sample image from a test sample during the test mode, and then provides a sample image to the analysis system only when the test sample is a living body.

Description

System and method for bio-aware performance and counterfeit defense analysis of mobile terminal and its method

The present invention relates to an analysis system and a method for analyzing the forgery defense ability to evaluate the biometric performance of a biometric sensor mounted on a mobile device, such as fingerprint, face, and iris, and to detect a forged biometric.

As society has all the functional elements mechanized and networked, an authentication system has been developed to limit people's access. Since conventionally widely used passwords or magnetic cards have security vulnerabilities and risks of loss, biometrics using biometric features have been developed.

Biometric authentication is unique to each individual, and is not only an excellent means of authentication, but also does not cause a problem of portability or loss, and is relatively secure. To date, fingerprints are widely used as biometric authentication, but face recognition and iris recognition have also been developed in recent years.

Fingerprints remain the same from birth to death, and the probability of having the same fingerprint as another person is almost zero. In addition, the fingerprint recognition sensor has a feature that can be produced in a smaller size than other biometric sensors. Face recognition is a very convenient usability because the user only needs to stare at the sensor, that is, the camera without any other action, and no other physical contact is required. However, there is a weakness in that the face is susceptible to surrounding conditions such as lighting and the face itself can change over time. Iris recognition is known to be the most accurate method of authentication since it is not only changed for a lifetime after completion after approximately 18 months, and is almost impossible to reproduce. However, since the iris needs to be close to the camera and the light, the user may feel a sense of rejection, and there is a disadvantage that the product size is large.

Personal authentication based on recent biometrics goes beyond just access control to open doors, accessing data online, personal authentication such as banking, online payment, and data security on personal mobile devices such as cell phones or tablets. The scope of use is expanding. Due to this trend, a personal mobile device is equipped with a biometric recognition means. However, since the mobile device has a size limitation, the biometric means for the mobile device is also limited in size, and thus, it is a new task to improve recognition performance with miniaturization.

Meanwhile, one of the weaknesses of biometric authentication is related to counterfeit biometrics. Normal personal authentication is mainly used in areas where security is important, such as access control, e-commerce, financial transactions, personal computer (PC) security, and office payment systems. Above all, it is important to effectively distinguish living organisms (hereinafter referred to as 'false living organisms'). For example, when attempting fingerprint authentication using paper or silicon on which a pattern of a fingerprint is printed, it should be possible to distinguish whether the fingerprint is a fake fingerprint. The ability of the bio-recognition sensor to distinguish counterfeit organisms is referred to as 'counterfeiting defense'.

Therefore, when evaluating the quality of the biometric sensor, it is most important to evaluate the forgery defense along with the biometric recognition rate.

Since the detection algorithm for the biometric authentication capability or counterfeit defense is not standardized, it is a field to be developed for each manufacturer. Not all manufacturers are superior in technology and are especially compact for mobile use, and some manufacturers produce certified sensors that do not have basic counterfeit defenses.

Therefore, it is necessary to check whether the biometric device has a basic counterfeit defense as a national institution that performs approval in accordance with various laws regarding the biometric device.

[Related prior art]

Republic of Korea Patent Publication No. 10-2008-0062217 (Name of the invention: a method for measuring the quality of a fingerprint image using a block level quality measurement value and its recording medium)

The present invention uses a method of confirming the quality of the fingerprint area (ridge) itself obtained by the fingerprint image using pixel values. To this end, this invention measures the quality of a fingerprint image by dividing the fingerprint image into a plurality of blocks and obtaining an average of pixel values of each block, and is different from the present invention. Above all, this invention relates to the quality measurement of the fingerprint image itself, and not to a method for determining the quality of the fingerprint sensor.

An object of the present invention is to evaluate a biometric performance in a biometric sensor mounted on a mobile device, such as a fingerprint, a face, or an iris, and to analyze the counterfeit defense ability to detect the forged biometrics and an analysis system for analyzing the counterfeit defense. In the provision.

The analysis system according to the present invention for achieving the above object can analyze the biometric performance and counterfeit defense capabilities of the mobile device. The analysis system of the present invention includes a terminal connection unit, a feature point extraction unit, and a counterfeit defense analysis unit. The terminal connection unit is connected to the mobile terminal to be inspected, and receives a sample image from the mobile terminal. At this time, the mobile terminal obtains a sample image from a test sample to perform bio-authentication, and when it is determined that the test sample is a living body, provides the sample image to the terminal connection unit.

The feature point extraction unit extracts the feature point data from the sample image received by the terminal connection unit, and the counterfeit defense analysis unit searches the feature point data extracted by the feature point extraction unit in a database to determine whether the sample image is an image of a living body or a fake living body. Analyze the counterfeit defense of mobile terminals.

According to an embodiment, the mobile terminal may perform bio-recognition based on a bio-recognition sensor that acquires a sample image from the test sample through a fingerprint recognition, face recognition, or iris recognition method, and a sample image obtained by the bio-recognition sensor. It includes a recognition control unit that performs and determines whether to falsify, and a system connection unit that proceeds to an inspection mode when connected to the terminal access unit. The system connection unit provides the sample image to the terminal connection unit when the recognition control unit determines that the test sample is not a forgery during the test mode, and the sample is obtained when the recognition control unit determines that the test sample is forged. An image is not provided to the terminal connection unit.

According to another embodiment, the database registers and manages a sample image for the test sample. The registered sample image includes a sample image obtained from a living body and a sample image obtained from a counterfeit organism. .

According to another embodiment, the analysis system of the present invention finally outputs a quality measurement unit that evaluates the quality of a sample image received by the terminal access unit, a quality score of the quality measurement unit, and a counterfeit defense score of the counterfeit defense analysis unit. It may further include a reporting unit.

The present invention also extends to an analysis method of an analysis system. The analysis method of the present invention comprises the steps of connecting to a mobile terminal to be inspected through a terminal connection unit; Receiving a sample image from the mobile terminal; Extracting feature point data from a sample image received from the mobile terminal; And analyzing the counterfeit defense power of the mobile terminal by checking the extracted feature point data in a database to determine whether the sample image is a living body image or a fake living body image.

The bio-recognition sensor analysis system according to the present invention can determine the bio-recognition ability and counterfeit defense in a mobile device equipped with a bio-recognition sensor to be inspected.

Basically, the present invention analyzes and determines the performance of the mobile device unit's bio-recognition sensor and, at the same time, provides a software module capable of distinguishing the basic counterfeit organisms when there is no defense capable of distinguishing the counterfeit organisms, thereby passing the inspection. The bio-recognition sensor installed in one mobile device has basic counterfeit defense.

1 is a conceptual diagram of a bio-recognition sensor analysis system for a mobile device of the present invention,
2 is a block diagram of a mobile terminal to which the present invention is applied,
3 is a block diagram of the analysis system of the present invention, and
4 is a flow chart provided to explain the method for analyzing the biometric performance and counterfeit defense capabilities of the mobile device of the analysis system of the present invention.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

1 to 3, the bio-recognition sensor analysis system 110 for a mobile device of the present invention is connected to a mobile terminal 130 equipped with a bio-recognition sensor module, and is equipped with a bio-recognition mounted on the mobile terminal 130. The sensor module's recognition ability and counterfeit defense are analyzed. In the database 111 of the bio-recognition sensor analysis system 110, information on various test samples (X) is recorded and managed, and an inspection sample (x) is input to the bio-recognition sensor of the mobile terminal for inspection. Perform.

Mobile devices

Referring to FIG. 2, the mobile terminal 130 is a device that can be carried by an individual and is relatively small in size. For example, a mobile phone, a tablet, a personal digital appliance (PDA), or the like corresponds to the mobile terminal 130 of the present invention.

However, the mobile terminal 130 connected to the analysis system 110 of the present invention includes a biometric sensor 201, a recognition control unit 203, a system connection unit 205, and a communication interface 207. The bio-recognition sensor 201 and the recognition control unit 203 perform a unique bio-recognition process of the mobile terminal 130, and are practical targets for analysis by the analysis system 110 of the present invention.

The biometric sensor 201 is for fingerprint recognition, iris recognition, or face recognition, and generates a sample image (biometric image or forged biometric image) from an input test sample (biometric or forged biometric). The sensor 201 for fingerprint recognition is a fingerprint sensor for acquiring a fingerprint image, and the sensor 201 for iris or face recognition is a camera for photographing an iris or face. In the case of the mobile terminal 130, it is difficult to provide a separate camera for photographing an iris or face, and it is common to use a built-in camera mounted as a basic specification in a mobile device.

The test sample may be a living body or a counterfeit living body. For example, counterfeit fingerprints are made by molding or printing a fingerprint pattern on silicone, gelatin, rubber, film, paper, and the like. For face recognition. As a counterfeit sample, color, black and white or infrared (IR) -printed face photographs can be used, and face photographs are input to the camera. For iris recognition. As a counterfeit sample, a model made of a material for making a fake eye (bill) can be used, and an iris model is input to the camera.

The recognition control unit 203 performs bio-recognition (fingerprint recognition, face recognition, or iris recognition) from the sample image acquired by the bio-recognition sensor 201 and determines whether it is a counterfeit biometric. Therefore, the recognition control unit 203 is implemented as 'bio-recognition software' for bio-recognition and 'counterfeiting software' for counterfeiting, and may be mounted in an operating system program of the mobile terminal 130. In some cases, the forgery determination may be performed by the forgery determination software of the recognition control unit 203 and the hardware configuration of the biometric sensor 201.

On the other hand, when the recognition control unit 203 does not have a 'counterfeit defense', the basic 'counterfeiting software' possessed by the inspector is provided in advance and installed before the test, so that the mobile terminal 130, which has been finally inspected, has the basic counterfeit defense. You can.

The biometric sensor 201 and the recognition control unit 203 perform a unique biometric process of the mobile terminal 130. However, when connected to the analysis system 110 and proceeds to the inspection mode, the recognition control unit 203 receives a sample for inspection according to a bio-recognition algorithm, generates a sample image, and inspects the quality of the input sample and forgeries It is determined whether or not the recognition result is provided to the system connection unit 205. Recognition results include (1) 'recognition success', which is judged to be non-counterfeiting, and (2) 'failure recognition by forgery', which is judged to be counterfeit.

The system connection unit 205 processes a software protocol for accessing the analysis system 110, and is usually implemented with an application programming interface (API) provided by the analysis system 110. Therefore, when the API provided by the analysis system 110 of the present invention is mounted on a conventional mobile device, the system connection unit 205 is installed.

The system connection unit 205 does not participate in the unique bio-recognition process of the mobile terminal 130 and operates when it is connected to the analysis system 110. When connected to the analysis system 110 and proceeding to the 'inspection mode' controlled by the analysis system 110, the system connection unit 205 receives a biometric result from the recognition control unit 203. When the recognition result provided from the recognition control unit 203 is 'successful recognition', the system connection unit 205 provides the sample image of the inspection object to the analysis system 110 through the communication interface 207. When the sample image is provided to the analysis system 110, the system connection unit 205 provides the sample image in the form of a stream, and is typically high-speed (for example, 16 frames per second) to smoothly inspect the inspection mode. It is desirable to send.

If the recognition result provided from the recognition control unit 203 is 'recognition failure due to forgery', the system connection unit 205 does not provide the sample image to the analysis system 110, and then notifies the recognition failure only, and then checks the next test sample. Wait for the recognition result.

The communication interface 207 includes a physical interface that can connect to the analysis system 110. As a physical interface, for example, a wireless interface capable of connecting to a wireless network such as a wireless LAN or a 4G / 5G mobile communication network is possible, and a wired interface such as USB (USB) is also possible, and a mobile device ( The communication interface built in 130) can be used as it is. The system connection unit 205 provides the image and / or recognition result obtained by the bio-recognition sensor 201 to the analysis system 110 using the communication interface 207.

Analysis system

The analysis system 110 of the present invention analyzes the biometric capability and counterfeit defense capability of the connected mobile terminal 130 for inspection. Referring to FIG. 3, the analysis system 110 includes a database 111, a network interface 301, a terminal connection unit 303, a quality measurement unit 305, a feature point extraction unit 307, and a counterfeit defense analysis unit 309. And a reporting unit 311.

In the database 111, information about the test sample is registered. Here, the information on the test sample includes those obtained from living organisms and those obtained from counterfeit organisms. The sample information includes a sample image, feature point data extracted from the sample image, and registration code of each sample image, and the feature point data is the same algorithm as the algorithm in which the feature point extracting unit 307 described below extracts the feature points from the sample image. It is extracted.

In the database 111, it is advantageous to improve the quality of inspection by registering sample images extracted from various counterfeit samples. On the other hand, the database 111 does not register the biometric image and the counterfeit biometric image from which the same feature point is extracted.

The network interface 301 is a configuration for connecting the mobile terminal 130 to be inspected to the analysis system 110 of the present invention, and connects to the communication interface 207 of the mobile terminal 130. Accordingly, the network interface 301 may be a wired interface such as USB or a wireless interface capable of accessing a wireless LAN or a mobile communication network.

The terminal access unit 303 receives the recognition result from the system access unit 205 of the mobile terminal 130. If the recognition result is 'successful' as the mobile terminal 130 determines that the sample is not a forged sample, the recognition result provided by the mobile terminal 130 includes a sample image of the corresponding test sample. The terminal connection unit 303 provides the sample image received from the mobile terminal 130 to the quality measurement unit 305 and the feature point extraction unit 307.

The quality measurement unit 305 calculates a quality score by measuring the quality of the sample image provided by the terminal connection unit 303. The quality measurement unit 305 may not be necessary in the analysis system 110 or analysis method of the present invention.

The quality measurement method of the sample image of the quality measurement unit 305 is evaluated using a sample image quality evaluation algorithm. The sample image quality evaluation algorithm may use a conventionally known method for evaluating the quality of a fingerprint image, a face image, or an iris image. Grade), Good (3rd grade), Fair (4th grade), Poor (5th grade).

Even if the biometric sensor 201 of the mobile terminal 130 determines that the recognition is successful, it is preferable to perform the quality evaluation of the quality measurement unit 305 because the quality of the sample image may not reach a certain level.

The feature point extraction unit 307 extracts the feature points from a sample image provided by the terminal connection unit 303. As described above, the algorithm used by the feature point extraction unit 307 to extract the feature points is the same as the algorithm used to register the sample in the database 111, and a conventionally known algorithm for fingerprint recognition, face recognition, or iris recognition. Can be used.

At this time, the feature point extracting unit 307 does not extract the feature points for all sample images provided by the terminal connection unit 303, but the quality points measured by the quality measuring unit 305 are more than a predetermined reference value. By extracting, the accuracy of 'forgery defense evaluation' can be improved.

The feature point extraction unit 307 provides the feature point data extracted from the sample image to the counterfeit defense analysis unit 309.

The counterfeit defense analysis unit 309 determines whether the sample image provided by the terminal access unit 303 is obtained from a living body or a counterfeit living body using sample information for inspection registered in the database 111. Perform 'Forgery Defense Evaluation'. The counterfeit defense analysis unit 309 provides the analysis results to the reporting unit 311.

For the evaluation of counterfeit defense, the counterfeit defense analysis unit 309 compares the feature points extracted by the feature point extraction unit 307 with the feature points of samples registered in the database 111, and the samples registered in the database 111 Among them, the same sample is searched. If, as a result of querying the database 111, it is determined that the feature point extracted by the feature point extraction unit 307 is a counterfeit living body, the mobile terminal 130 incorrectly determines the counterfeit sample for inspection as a living body to the analysis system 110. It is provided.

Since the counterfeit defense analysis is usually performed in a series of continuous processes using a plurality of preset test samples (both living and counterfeit living organisms) as a set, the tester sequentially performs a set of test samples to the mobile terminal 130 ) Is input to the bio-recognition sensor 201, and the counterfeit defense analysis unit 309 comprehensively analyzes the counterfeit defense against a set of samples for inspection. If the mobile terminal 130 performs accurate and complete forgery discrimination, the sample image for the forged sample should not be classified and provided to the analysis system 110, and the sample image for the biological sample is provided to the analysis system 110 Should be. Therefore, the analysis of the counterfeit defense analysis unit 309 includes the following.

(1) Counterfeit detection rate or forgery acceptance rate determined by how many counterfeit living bodies are among the sample images provided by the mobile terminal 130.

(2) As the mobile terminal 130 determines that the biological sample included in the sample set for inspection is a forgery, it is comprehensively determined whether or not the sample image is not provided.

The reporting unit 311 stores the quality measurement result of the quality measurement unit 305 and the analysis result of the counterfeit defense analysis unit 309 together with the sample image in the database 111 and outputs it to the inspector.

Hereinafter, a mobile-based recognition performance and counterfeit defense analysis method of the present invention will be described with reference to FIG. 4.

<Enter inspection mode: S401>

For inspection, when the mobile terminal 130 to be inspected and the analysis system 110 are communicatively connected, and the terminal connection unit 303 is connected to the system connection unit 205 of the mobile terminal 130 according to a predetermined protocol, the system connection unit 205 enters the inspection mode.

<Input of test sample: S403>

During the test mode, the tester sequentially inputs a set of test samples to the biometric sensor 201 of the mobile terminal 130 under the control of the analysis system 110. As described above, a set of test samples includes biological samples and counterfeit samples.

According to an embodiment, the terminal connection unit 303 may confirm that the system connection unit 205 has entered the inspection mode, and then guide the tester to input a sample for inspection through a display unit or a speaker.

<Receive a sample image: S405>

According to the input of the test sample, the bio-recognition sensor 201 of the mobile terminal 130 acquires a sample image from the test sample, and the recognition control unit 203 essentially determines whether the sample is a living body or a counterfeit biological object. . If, when the recognition control unit 203 determines the input test sample as a living body, not a counterfeit sample, the system connection unit 205 provides a recognition success message together with the sample image to the terminal connection unit 303 of the analysis system 110 do. Therefore, only a sample image of a sample determined as a living body among a set of test samples is provided to the analysis system 110.

The terminal access unit 303 provides the sample image received from the mobile terminal 130 to the quality measurement unit 305 and the feature point extraction unit 307.

<Sample image quality measurement: S407>

The quality measurement unit 305 performs quality inspection on the sample image provided from the terminal connection unit 303 to calculate a quality score or grade.

<Feature point extraction of sample image: S409>

The feature point extraction unit 307 extracts the feature points from the sample image provided from the terminal connection unit 303.

Depending on the embodiment, the feature point may not be extracted for the sample image whose quality score is calculated in step S407 below the reference value, but this processing is not essential. Meanwhile, step S409 may be performed in parallel with step S407.

<Forgery judgment: S411>

The counterfeit defense analysis unit 309 compares the feature points extracted by the feature point extraction unit 307 with the feature points of samples registered in the database 111 and searches for the same sample among the samples registered in the database 111. If, as a result of querying the database 111, it is determined that the feature point extracted by the feature point extraction unit 307 is a counterfeit living body, the mobile terminal 130 incorrectly determines the counterfeit sample for inspection as a living body to the analysis system 110. It is provided.

<Forgery Defense Analysis and Reporting: S413 to S417>

Steps S403 to S411 are sequentially performed on a set of test samples (S413).

When input to a set of test samples is completed, the counterfeit defense analysis unit 309 performs counterfeit defense analysis of the mobile terminal 130. If the mobile terminal 130 performs accurate and complete forgery discrimination, the sample image for the forged sample should not be classified and provided to the analysis system 110, and the sample image for the biological sample is provided to the analysis system 110 It should be (S415).

The reporting unit 311 ends the analysis by finally outputting the counterfeit defense performance of the mobile terminal 130 unit analyzed by the counterfeit defense analysis unit 309 to the tester. When the analysis is completed, the terminal access unit 303 ends the inspection mode, and the connection between the system connection unit 205 of the mobile terminal 130 is terminated (S417).

The analysis method of the analysis system 110 of the present invention is performed by the above method.

Although the preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and is usually not limited to the technical field to which the present invention pertains without departing from the gist of the present invention claimed in the claims. It is of course possible to perform various modifications by a person having knowledge of, and these modifications should not be individually understood from the technical idea or prospect of the present invention.

Claims (8)

In the biometric performance and counterfeit defense analysis system of a mobile device,
A database for registering and managing a sample image for a biological test sample or a forged test sample and feature point data extracted from the sample image;
A terminal connection unit connected to a mobile terminal to be inspected and receiving a sample image from the mobile terminal. The mobile terminal acquires a sample image from one of the test samples registered in the database to perform bio-authentication, and when the test sample is determined to be a living body, provides the sample image to the terminal connection unit;
A feature point extraction unit for extracting feature point data from the sample image received by the terminal connection unit; And
Counterfeit defense analysis that analyzes counterfeit defense power of the mobile terminal by checking the feature point data extracted by the feature point extraction unit in the database to determine whether the sample image received from the mobile device is a biological sample image or a forged sample image Bio-recognition performance and counterfeit defense analysis system of a mobile device comprising a wealth.
According to claim 1,
The mobile terminal,
A biometric sensor that acquires a sample image from the test sample by fingerprint recognition, face recognition, or iris recognition;
A recognition control unit for performing biometric recognition based on the sample image acquired by the bio-recognition sensor and determining whether it is counterfeit; And
When connected to the terminal connection unit, proceeds to an inspection mode, and when the recognition control unit determines that the sample for inspection is a living body instead of a counterfeit during the inspection mode, provides the sample image to the terminal connection unit, and the recognition control unit performs the inspection A system for analyzing biometric performance and counterfeit defense of a mobile device, comprising a system connection unit that does not provide the sample image to the terminal connection unit when it is determined that the sample is forged.
delete According to claim 1,
A quality measurement unit that evaluates the quality of the sample image received by the terminal connection unit; And
A system for bio-recognition performance and counterfeit defense analysis of a mobile device, further comprising a reporting unit for finally outputting the quality score of the quality measurement unit and the counterfeit defense score of the counterfeit defense analysis unit.
In the analysis method of the analysis system for the biometric performance and counterfeit defense capabilities of the mobile device,
Registering and managing a sample image for a biological test sample or a forged test sample and feature point data extracted from the sample image in a database;
Connecting to a mobile terminal to be inspected through a terminal connection unit;
Receiving a sample image from the mobile terminal. The mobile terminal acquires a sample image from one of the test samples registered in the database to perform bio-authentication, and when the test sample is determined to be a living body, provides the sample image to the terminal connection unit;
Extracting feature point data from a sample image received from the mobile terminal; And
And analyzing the counterfeit defense power of the mobile terminal by checking the extracted feature point data in the database to determine whether the sample image received from the mobile device is a biological sample or a forged sample. Analysis method of the analysis system to be.
The method of claim 5,
The mobile terminal,
If the system connection unit is connected to the terminal connection unit, proceeding to an inspection mode, and then obtaining a sample image from the sample for inspection by a fingerprint recognition, face recognition, or iris recognition method;
Performing bio-recognition based on the sample image obtained by the bio-recognition sensor and determining whether it is counterfeit; And
When it is determined that the test sample is a living body, not a counterfeit, in the test mode, the system connection unit provides the sample image to the terminal connection unit, and when the test sample is determined to be forged, the sample image is sent to the terminal connection unit. Analysis method of the analysis system characterized in that it comprises a step not provided.
delete The method of claim 5,
Evaluating the quality of the sample image received by the terminal access unit; And
And finally outputting a quality score according to the quality evaluation and a counterfeit defense score according to the counterfeit defense analysis.

Images