• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.6
• /
• pp.39-46
• /
• 2003

Biometric technologies using biometric information like fingerprints features are in wide use for the secure user authentication in many services including log-in of computer systems, entrance ID and E-commercial security. Nowadays, biometric technologies are ported into small embedded systems like security tokens or smart cards due to the merit of being secure and automatic in comparison with the previous method in user authentication such as using a PIN. In this paper, the security token developed as an embedded system and tile user authentication system implemented and tested using fingerprints information are described. Communications between the security token and tile host are tested and verified with USB. And, execution time and runtime memory on tile security token board was measured and performance improvement was described. In addition, requisites for the transit from the security token to the match-on-card was mentioned.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.659-662
• /
• 2021

국내에서는 매년 많은 수의 자격시험이 치러지고 있다. 현재 대부분의 시험장에서 응시자 본인 확인 절차는 감독관이 응시자의 얼굴과 신분증 사진을 비교하는 방식으로 이루어진다. 하지만 이 방식은 사람에 따라 오차가 클 수 있으며, 사진과 눈에 띄는 차이가 없으면 동일인물로 판단하기 쉽다. 최근까지도 대리응시 이슈가 발생하고 있어 근절을 위한 보다 강력한 조치가 필요하다. 본 논문에서는 지문과 오토인코더, SGAN을 이용하여 대리응시방지를 강화할 수 있는 본인 확인 시스템을 제안한다. 이때 응시자의 지문정보가 그대로 인증 서버에 저장되면 응시자의 생체정보가 노출될 수 있다는 문제점이 존재한다. 따라서 오토인코더를 통해 지문의 특징점만 추출하여 인증용 이미지를 생성하고 이 이미지를 서버에 저장하여 학습시키도록 한다. 적은 학습데이터 환경에서 분류기로써 좋은 성능을 갖는 SGAN을 통해 인증 이미지와 응시자가 동일인물인지 확인할 수 있다. 서버가 공격을 받더라도 응시자의 지문데이터가 그대로 노출되지 않게 되어 보안 취약점을 극복할 수 있다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.6
• /
• pp.95-105
• /
• 2003

A novel reference point detection method is proposed by exploiting tile gradient probabilistic model that captures the curvature information of fingerprint. The detection of reference point is accomplished through searching and locating the points of occurrence of the most evenly distributed gradient in a probabilistic sense. The uniformly distributed gradient texture represents either the core point itself or those of similar points that can be used to establish the rigid reference from which to map the features for recognition. Key benefits are reductions in preprocessing and consistency of locating the same points as the reference points even when processing arch type fingerprints. Moreover, the new feature extraction method is proposed by improving the existing feature extraction using filterbank method. Experimental results indicate the superiority of tile proposed scheme in terms of computational time in feature extraction and verification rate in various noisy environments. In particular, the proposed gradient probabilistic model achieved 49% improvement under ambient noise, 39.2% under brightness noise and 15.7% under a salt and pepper noise environment, respectively, in FAR for the arch type fingerprints. Moreover, a reduction of 0.07sec in reference point detection time of the GPM is shown possible compared to using the leading the poincare index method and a reduction of 0.06sec in code extraction time of the new filterbank mettled is shown possible compared to using the leading the existing filterbank method.

• Journal of Korea Multimedia Society
• /
• v.11 no.4
• /
• pp.492-503
• /
• 2008

With the recent development and increasing importance of personal identification systems, biometric technologies with less risk of loss or unauthorized use are being popularized rapidly. In particular, because of their high identification rate and convenience, fingerprint identification systems are being used much more commonly than other biometric systems such as iris recognition, face recognition and vein pattern recognition. However, a fingerprint identification system has the problem that artificially forged finger-prints can be used as input data. Thus, in order to solve this problem, the present study proposed a method for detecting forged fingerprints by measuring the degree of attenuation when the light from an optical fingerprint sensor passes through the finger and analyzing changes in the transmission of light over stages at fixed intervals. In order to prove improvement in the performance of the proposed system, we conducted an experiment that compared the system with an existing multi-sensor recognition system that measures also the temperature of fingerprint. According to the results of the experiment, the proposed system improved the forged fingerprint detection rate by around 32.6% and this suggests the possibility of solving the security problem in fingerprint identification systems.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1775-1784
• /
• 2002

Fingerprint recognition technology is used in many biometrics field accordingly essential feature of fingerprint image and the study is progressing. However development is not perfect in performance of the fingerprint recognition and application of the usual life. In the paper, we study various necessity of preprocessing according to algorithm and circumstances of authentication system in automatic information machine. We prove that system circumstance and optation of fingerprints image effectively is the important factor by using optical fingerprint input device and scanning the fingerprint in ID card. And then we present correct and fast computation method for improving image and feature extraction of fingerprint. Also we study effective algorithm implementation of total system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.173-176
• /
• 2003

지문은 종생불변성, 만인부동성, 그리고 사용상의 편리함 때문에 신원인증을 위한 생체인식에 많이 사용되고 있다. 최근에는 기하학구조에 기반한 특이점 매칭방식이 제안되어 인식성능이 매우 높고 잡음에 강한 특성이 있으나 매칭 회수가 많아 인식속도가 느린 단점이 있다. 따라서 기존의 방식은 소수의 지문에 대한 1:다 매칭이나 1:1매칭에 주로 사용된다. 본 논문에서는 기존의 문제점들을 개선하기 위하여 생체 면역계의 자기-비자기 인식 능력에 주목하였다. 생체 면역계는 자기-비자기의 구별 능력을 바탕으로 바이러스나병원균 등의 낮선 외부침입자로부터 자신을 보호하고 침입자를 식별, 제거하는 시스템이다. 본 논문에서는 생체 면역계를 이루는 면역세포 중의 하나인 세포독성 T세포의 생성과정에서 자기, 비자기를 구별하기 위한 MHC 인식부를 형성하는 과정에 착안한 빠르고 신뢰성 있는 지문 인식 알고리즘을 제안한다. 제안한 방식은 지문에 존재하는 특이점(minutiae)인식을 통해 1단계로 global 패턴을 생성하고 2단계로 기하학적인 구조를 만들며, 인식시 global 패턴을 인식한 MHC 인식부에 대해서만 2차 local 매칭을 수행함으로써 매칭 속도가 매우 빠르며 지문의 비틀림이나 회전 등에 대하여 강인하게 인식된다.

• Journal of IKEEE
• /
• v.9 no.1 s.16
• /
• pp.31-39
• /
• 2005

This paper presented new biometrics data transfer model, and use MD5 (Message Digest5) and RSA (Ron Rivest, Adi Shamir, Len Adleman) algorithm to improve biometrics data's security. So, did so that can run user authentication more safely. That is, do so that may input fingerprint among biometrics through client, and transmit processed fingerprint to server. When fingerprint information is transmitted, it uses MD5 algorithm to solve problem that get seized unlawful living body information from outside and information does Digest. And did to pass through process that transmit again this by RSA method. Also, experimented general text data and living body data that is not encoded, transmission speed and security of living body data that encoding and transmit each comparison. By running user authentication through such improved method, is expected to be applied in several. fields by method to simplify certification procedure and is little more correct and stable.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.1
• /
• pp.125-133
• /
• 2009

Security of biometric data is particularly important as the compromise of the data will be permanent. To protect the biometric data, we need to store it in a non.invertible transformed version. Thus, even if the transformed version is compromised, its valid biometric data are securely remained. Fuzzy vault mechanism was proposed to provide cryptographic secure protection of critical data(e.g., encryption key) with the fingerprint data in a way that only the authorized user can access the critical data by providing the valid fingerprint. However, all the previous results cannot operate on the fingerprint image with a few minutiae, because they use fixed degree of the polynomial without considering the number of fingerprint minutiae. To solve this problem, we use adaptive degree of polynomial considering the number of minutiae. Also, we apply multiple polynomials to operate the fingerprint with a few minutiae. Based on the experimental results, we confirm that the proposed approach can enhance the security level and verification accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.249-252
• /
• 2003

This paper propose an advanced circuit for fingerprint sensor signal processing. We increased the voltage between ridge and valley by modifying the parasitic capacitance eliminating circuit of sensor plate. The analog to comparator was designed for comparing the sensor signal voltage with the reference signal voltage. We also propose an exective isolation strategy for removing noise and signal coupling of each sensor pixel. The 128$\times$144 pixel fingerprint sensor circuit was designed and simulated, and the layout was performed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.237-240
• /
• 2002

지문 인식분야는 분류와 인증단계로 나뉜다. 이 논문에서는 방향성 이미지의 통계적 접근방법을 이용한 새로운 지문분류 알고리즘을 제안한다. 알고리즘은 세 단계로 이루어져 있으며, 첫째, 융선의 방향성 계산 단계, 둘째, 방향성 이미지 분포의 분산을 이용한 특이점 추출단계, 셋째 지문의 분류 단계이다. 실험은 1000개의 NIST-4 DB를 이용하였으며 정확도는 5분류(궁상문, 텐트형 궁상문, 우제상문, 좌제상문, 와상문)에 대해 87.8%이다.