• Title/Summary/Keyword: Fingerprint scheme

Search Result 78, Processing Time 0.023 seconds

Effective Fingerprint Classification using Subsumed One-Vs-All Support Vector Machines and Naive Bayes Classifiers (포섭구조 일대다 지지벡터기계와 Naive Bayes 분류기를 이용한 효과적인 지문분류)

  • Hong, Jin-Hyuk;Min, Jun-Ki;Cho, Ung-Keun;Cho, Sung-Bae
    • Journal of KIISE:Software and Applications
    • /
    • v.33 no.10
    • /
    • pp.886-895
    • /
    • 2006
  • Fingerprint classification reduces the number of matches required in automated fingerprint identification systems by categorizing fingerprints into a predefined class. Support vector machines (SVMs), widely used in pattern classification, have produced a high accuracy rate when performing fingerprint classification. In order to effectively apply SVMs to multi-class fingerprint classification systems, we propose a novel method in which SVMs are generated with the one-vs-all (OVA) scheme and dynamically ordered with $na{\ddot{i}}ve$ Bayes classifiers. More specifically, it uses representative fingerprint features such as the FingerCode, singularities and pseudo ridges to train the OVA SVMs and $na{\ddot{i}}ve$ Bayes classifiers. The proposed method has been validated on the NIST-4 database and produced a classification accuracy of 90.8% for 5-class classification. Especially, it has effectively managed tie problems usually occurred in applying OVA SVMs to multi-class classification.

Robust Fuzzy Fingerprint Vault System against Correlation Attack (상관관계 공격에 강인한 지문퍼지볼트 시스템)

  • Moon, Dae-Sung;Chae, Seung-Hoon;Chung, Yong-Wha;Kim, Sung-Young;Kim, Jeong-Nyeo
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.21 no.2
    • /
    • pp.13-25
    • /
    • 2011
  • Biometric-based authentication can provide strong security guarantee about the identity of users. However, security of biometric data is particularly important as the compromise of the data will be permanent. The fuzzy fingerprint vault system is one of the most popular solutions for protecting the fingerprint template stored in the database. Recently, however, this system is very susceptible to a correlation attack that finds the real minutiae using multiple fingerprint vaults enrolled for different applications. To solve this problem, we propose a robust fuzzy fingerprint vault system against the correlation attack. In this paper, we add chaff minutiae based on the relative information of minutiae such as direction, coordinate instead of adding randomly. Also, our proposed approach allow to add multiple chaff minutiae within tolerance box for enhanced security level. Experimental results show that the proposed approach can protect the correlation attack and achieve enhanced verification accuracy.

High Speed and Low Power Scheme for a Fingerprint Identification Algorithm (고속 저전력 지문인식 알고리즘 처리용 회로)

  • Yoo, Min-Hee;Jung, Seung-Min
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2008.05a
    • /
    • pp.111-114
    • /
    • 2008
  • This paper proposes an effective hardware scheme for gabor filter and thinning stage processing of a fingerprint identification algorithm based on minutiae with 80% cycle occupation of 32-bit RISC microprocessor. The algorithm was developed based on minutiae with bifurcation and ending point. The analysis of an algorithm source rode was performed using ARM emulator.

  • PDF

Design and implementation of Image Content Tracking System using Fingerprinting (핑거프린팅을 이용한 이미지 콘텐츠 추적시스템 설계 및 구현)

  • 서영호;김원겸;이선화;황치정
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.41 no.5
    • /
    • pp.99-109
    • /
    • 2004
  • This paper proposes a new method for tracking image contents, which are re-distributed on the Internet using a web-robot and fingerprinting scheme. The fingerprinting is an extended technique of watermarking and embeds identity of the customer into the content as a fingerprint in a way that is very difficult to erase. The fingerprint in the content can be used widely in the field of the copyright protection technique because it identifies the content itself and includes the information about the original customer. In this paper we discuss an active image tracking system using a web-robot and fingerprinting scheme. In the proposed system the information of the original customer is embedded as a fingerprint into the image content before distribution and also stored into DB. The distributed contents are collected by the web-robot and fingerprinting information is extracted from the contents. Finally the identifying of contents is done by comparing the extracted fingerprint with the selling history of the content.

Cost Effective Mobility Anchor Point Selection Scheme for F-HMIPv6 Networks (F-HMIPv6 환경에서의 비용 효율적인 MAP 선택 기법)

  • Roh Myoung-Hwa;Jeong Choong-Kyo
    • KSCI Review
    • /
    • v.14 no.1
    • /
    • pp.265-271
    • /
    • 2006
  • In this paper, we propose a new automatic fingerprint identification system that identifies individuals in large databases. The algorithm consists of three steps: preprocessing, classification, and matching, in the classification, we present a new classification technique based on the statistical approach for directional image distribution. In matching, we also describe improved minutiae candidate pair extraction algorithm that is faster and more accurate than existing algorithm. In matching stage, we extract fingerprint minutiaes from its thinned image for accuracy, and introduce matching process using minutiae linking information. Introduction of linking information into the minutiae matching process is a simple but accurate way, which solves the problem of reference minutiae pair selection in comparison stage of two fingerprints quickly. This algorithm is invariant to translation and rotation of fingerprint. The proposed system was tested on 1000 fingerprint images from the semiconductor chip style scanner. Experimental results reveal false acceptance rate is decreased and genuine acceptance rate is increased than existing method.

  • PDF

Dictionary Attack on Functional Transform-Based Cancelable Fingerprint Templates

  • Shin, Sang-Wook;Lee, Mun-Kyu;Moon, Dae-Sung;Moon, Ki-Young
    • ETRI Journal
    • /
    • v.31 no.5
    • /
    • pp.628-630
    • /
    • 2009
  • Recently, Ratha and others proposed a cancelable biometrics scheme which transforms an original fingerprint template into a new one using a noninvertible transformation. However, we show that the original template is recovered by a dictionary attack if two transformed templates originating from it are revealed. In our attack, we simulate the transformation and construct a set of possible pre-images for each transformed template. Then, we find the correct pre-image by computing the intersection of these sets. We present an algorithm implementing this idea as well as successful experimental results.

Security Analysis to an Biometric Authentication Protocol for Wireless Sensor Networks (WSN 환경에서 Biometric 정보를 이용한 사용자 인증 스킴의 안전성 분석)

  • Lee, Youngsook
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.11 no.1
    • /
    • pp.59-67
    • /
    • 2015
  • A novel authentication mechanism is biometric authentication where users are identified by their measurable human characteristics, such as fingerprint, voiceprint, and iris scan. The technology of biometrics is becoming a popular method for engineers to design a more secure user authentication scheme. In terms of physiological and behavioral human characteristics, biometrics is used as a form of identity access management and access control, and it services to identity individuals in groups that are under surveillance. In this article, we review the biometric-based authentication protocol by Althobati et al. and provide a security analysis on the scheme. Our analysis shows that Althobati et al.'s scheme does not guarantee server-to-user authentication. The contribution of the current work is to demonstrate this by mounting threat of data integrity and bypassing the gateway node on Althobati et al.'s scheme. In addition, we analysis the security vulnerabilities of Althobati et al.'s protocol.

Biometric technology comparison analysis for the security reinforcement of the ATM (ATM 보안 강화를 위한 생체인식기술 분석)

  • Kwon, Yong-Kwan;Cha, Jae-Sang
    • Journal of Satellite, Information and Communications
    • /
    • v.11 no.1
    • /
    • pp.16-20
    • /
    • 2016
  • In this paper, we analyze the characteristics and ATM applications for fingerprint, iris, vein recognition technology that can be applied to the ATM to reinforce security. Describe the important requirements to be considered when introducing a biometric authentication in the ATM, and were compared to each biometric authentication scheme based on these requirements. Fingerprint authentication has limitations in accuracy, iris recognition is a big weakness in user convenience, whereas vein recognition has the advantage of being hygienic, yet excellent accuracy and secrecy. Vein authentication approach is expected to be expanded to apply to ATM due to the many advantages.

A Location Estimation Method Using TDOA Scheme in Vessel Environment (선박 환경에서 TDOA 기법에 의한 위치 추정 방법)

  • Kim, Beom-mu;Jeong, Min A;Lee, Seong Ro
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.19 no.8
    • /
    • pp.1934-1942
    • /
    • 2015
  • An estimation problem in the environment which GPS signals do not reach, should be solved by employing an indoor location estimation scheme. Location estimation schemes for indoor environments generally include the AOA, TOA, RSS, Fingerprint, and TDOA. For a ship environment where there exist many spaces enclosed by iron plates, the TDOA scheme is appropriate because location estimation is usually performed at a closed range. In this paper, we address the problem of estimating the location of a terminal under the ship environment. The problem of location estimation by using the TDOA is presented in detail, and then an algorithm for applying the estimation to the ship environment is proposed. Finally, the proposed algorithm of location estimation in a ship by the TDOA scheme is verified through simulations from three viewpoints.

Security Analysis and Improvement of an Anonymous Asymmetric Fingerprinting Scheme with Trusted Third Party (익명적 비대칭 핑거프린팅 기법의 보안 취약성 분석 및 개선 방안)

  • Kwon, Sae-Ran
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.36 no.5
    • /
    • pp.396-403
    • /
    • 2009
  • An anonymous asymmetric fingerprinting protocol combined with watermarking techniques, is one of the copyright protection technologies keeping both right of a seller and that of a buyer, where a seller and an anonymous buyer perform such a protocol that employs various cryptographic tools in order that the seller does not know the exact watermarked copy that the buyer receives, while inserting an invisible non-removable fingerprint i.e., each different unique watermark, into each copy of the digital content to be sold. In such a protocol innocent buyers are kept anonymous during transactions, however, the unlawful reseller is unambiguously identified with a real identity as a copyright violator. In 2007, Yong and Lee proposed an anonymous asymmetric fingerprinting scheme with trusted third party. In this paper we point out the weakness of their scheme such as: the buyer with intention can remove the fingerprint in the watermarked content, because he/she can decrypt the encrypted fingerprint with a symmetric key using man-in-the-middle-attack; a real identity of a buyer can be revealed to the seller through the identification process even though he/she is honest. Furthermore, we propose an improved secure and efficient anonymous asymmetric fingerprinting scheme which enables to reduce the number of communication between the participants.