• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.969-970
• /
• 2008

This paper proposes illumination-efficient iris image capturing method. face capture method for extraction of iris pattern with one high resolution camera needs a large scale near infrared illumination. we replace high-resolution camera with co-optic-axial combination between wide view camera and narrow view camera. because this method needs small scale illumination that illuminate only narrow camera viewing angle, we can capture iris pattern image with small scale near infrared illumination.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.961-962
• /
• 2008

This paper proposes a touchless fingerprint acquisition device for five fingerprints. In conventional devices, they are focused for taking 1 touchless fingerprint image. But this device is taking 5 fingerprint image at a time. Also, it considers problems for focus and rolling in touchless fingerprint recognition for using camera. They affects fingerprint recognition, so this research is performed to measure and analyze these problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.6133-6151
• /
• 2017

The field of periocular biometrics has gained wide attention as an alternative or supplemental means to conventional biometric traits such as the iris or the face. Periocular biometrics provide intermediate resolution between the iris and the face, which enables it to support both. We have developed a periocular recognition system by using uniform Multiscale Local Binary Pattern (uMLBP) and attribute features. The proposed system has been evaluated in terms of major factors that need to be considered on a mobile platform (e.g., distance and facial pose) to assess the feasibility of the use of periocular biometrics on mobile devices. Experimental results showed 98.7% of rank-1 identification accuracy on a subset of the Face Recognition Grand Challenge (FRGC) database, which is the best performance among similar studies.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.749-753
• /
• 2007

In this paper, a generalized version of the Motion Silhouette Image(MSI) called the Generic Motion Silhouette Image (GMSI) is proposed for gait recognition. The GMSI is a gray-level image and involves the spatiotemporal information of individual motion. The GMSI not only generalizes the MSI but also reflects a flexible feature of a gait sequence. Along with the GMSI, we use the Principal Component Analysis(PCA) to reduce the dimensionality of the GMSI and the Nearest Neighbor(NN) for classification. We apply the proposed feature to NLPR database and compare it with the conventional MSI. Experimental results show the effectiveness of the GMSI.

• Information and Communications Magazine
• /
• v.32 no.6
• /
• pp.39-49
• /
• 2015

In cryptographic applications, the key protection is either knowledge-based (passwords) or possession-based (tamper-proof device). Unfortunately, both approaches are easily forgotten or stolen, thus introducing various key management issues. By incorporating biometrics technologies which utilize the uniqueness of personal characteristics, the security of cryptosystems could be strengthened as authentication now requires the presence of the user. Biometric Cryptosystem (BC) encompasses the design of cryptographic keys protection methods by incorporating biometrics. BC involves either key-biometrics binding or direct key generation from biometrics. However, the wide acceptance and deployment of BC solutions are constrained by the fuzziness related with biometric data. Hence, error correction codes (ECCs) should be adopted to ensure that fuzziness of biometric data can be alleviated. In this overview paper, we present such ECC solutions used in various BCs. We also delineate on the important facts to be considered when choosing appropriate ECCs for a particular biometric based solution from accuracy performance and security perspectives.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.321-322
• /
• 2006

In this paper, we propose a method that extracts invariant iris codes from user's iris pattern in order to apply these codes to a new cryptographic construct called fuzzy vault. The fuzzy vault, proposed by Juels and Sudan, has been used to manage cryptographic key safely by merging with biometrics. Generally, iris data has intra-variation of iris pattern according to sensed environmental changes, but cryptography requires correctness. Therefore, to combine iris data and fuzzy vault, we have to extract an invariant iris feature from iris pattern. In this paper, we obtain invariant iris codes by clustering iris features extracted by independent component analysis(ICA) transform. From experimental results, we proved that the iris codes extracted by our method are invariant to sensed environmental changes and can be used in fuzzy vault.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.15-25
• /
• 2017

The security and privacy issues derived from unsecurely storing biometrics templates in biometric authentication/ recognition systems have opened a new research area about how to secure the stored biometric templates. Biometrics-based key generation is the newest approach that provides not only a mechanism to protect stored biometric templates in authentication/ recognition systems, but also a method to integrate biometric systems with cryptosystems. Therefore, this approach has attracted much attention from researchers worldwide. A review of current research state to summarize the achievements and remaining works is necessary for further works. In this study, we first outlined the requirements and the primary challenges when implementing these systems. We then summarize the proposed techniques and achievements in representative studies on biometrics-based key generation. From that, we give a discussion about the accomplishments and remaining works with the corresponding challenges in order to provide a direction for further researches in this area.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3204-3209
• /
• 2010

This paper suggested the future technologies of biometrics system by using Delphi method. The level of technology were also evaluated. The group for the Delphi analysis consisted of 30 experts involved in biometrics. This study also suggested the 10 future core technologies of biometrics system including Body-signal DB technology and Bio-signal analysis technology, etc. From the technological importance point of view, several technologies were suggested as critical ones including the manufacturing technology of semiconductor micro-sensor and bio-sensor, etc. This research also forecasted the realization time of each technology and gave shape the detail goal performances. This research will be able to contribute to deciding the priority order and setting the direction of biometrics R&D planning.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.1
• /
• pp.1-7
• /
• 2012

In general, currently developed ECG(electrocardiogram) based biometrics approaches are not suitable for real market applications since they require high cost ECG monitoring device and their measurement methods showed poor usability. In this paper, we developed lead I signal based biometrics system using special purpose ECG measurement hardware. To guarantee signal quality for biometrics from various signal measurement environment in our ordinary life, several filters are applied. In addition, to enhance usability, only two skin on electrodes without reference point are used for measurement. Lead I signals of seventeen candidates are measured from developed hardware and features are extracted. Extracted features are applied to support vector machine (SVM) pattern classifier for biometrics, and the experimental results showed 98.59% of sensitivity (SN) and 97.21% of accuracy (ACC). Compare to conventional ECG biometrics approaches, proposed system showed enhanced usability with low-cost measurement hardware.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.159-166
• /
• 2012

Many biometrics-based user authentication schemes using smart cards have been proposed to improve the security weaknesses in user authentication system. In 2010, Chang et al. proposed an improved biometrics-based user authentication scheme without concurrency system which can withstand forgery attack, off-line password guessing attack, replay attack, etc. In this paper, we analyze the security weaknesses of Chang et al.'s scheme and we have shown that Chang et al.'s scheme is still insecure against man-in-the-middle attack, off-line biometrics guessing attack, and does not provide mutual authentication between the user and the server. And we proposed the improved scheme to overcome these security weaknesses, even if the secret information stored in the smart card is revealed. As a result, the proposed scheme is secure for the user authentication attack, the server masquerading attack, the man-in-the-middle attack, and the off-line biometrics guessing attack, does provide the mutual authentication between the user and the remote server. And, in terms of computational complexities, the proposed scheme is more effective than Chang et al.'s scheme.