Alignment-Free Cancelable Fingerprint Templates Based on Local Minutiae Information

Chulhan Lee,Jeung-Yoon Choi,Kar-Ann Toh,Sangyoun Lee IEEE 2007 part B Vol.37 No.4

<P>To replace compromised biometric templates, cancelable biometrics has recently been introduced. The concept is to transform a biometric signal or feature into a new one for enrollment and matching. For making cancelable fingerprint templates, previous approaches used either the relative position of a minutia to a core point or the absolute position of a minutia in a given fingerprint image. Thus, a query fingerprint is required to be accurately aligned to the enrolled fingerprint in order to obtain identically transformed minutiae. In this paper, we propose a new method for making cancelable fingerprint templates that do not require alignment. For each minutia, a rotation and translation invariant value is computed from the orientation information of neighboring local regions around the minutia. The invariant value is used as the input to two changing functions that output two values for the translational and rotational movements of the original minutia, respectively, in the cancelable template. When a template is compromised, it is replaced by a new one generated by different changing functions. Our approach preserves the original geometric relationships (translation and rotation) between the enrolled and query templates after they are transformed. Therefore, the transformed templates can be used to verify a person without requiring alignment of the input fingerprint images. In our experiments, we evaluated the proposed method in terms of two criteria: performance and changeability. When evaluating the performance, we examined how verification accuracy varied as the transformed templates were used for matching. When evaluating the changeability, we measured the dissimilarities between the original and transformed templates, and between two differently transformed templates, which were obtained from the same original fingerprint. The experimental results show that the two criteria mutually affect each other and can be controlled by varying the control parameters of the changing functions.</P>

Adaptive Mode Switching in Correlated Multiple Antenna Cellular Networks

Chulhan Lee,채찬병,Sriram Vishwanath,Robert W. Heath, Jr. 한국통신학회 2009 Journal of communications and networks Vol.11 No.3

This paper proposes an adaptive mode switching algorit- hm between two strategies in multiple antenna cellular networks: A single-user mode and a multi-user mode for the broadcast chan- nel. If full channel state information is available at the base-station, it is known that a multi-user transmission strategy would outper- form all single-user transmission strategies. In the absence of full side information, it is unclear what the capacity achieving method is, and thus there are few criteria to decide which of the myriad possible methods performs best given a system conguration. We compare a single-user transmission and a multi-user transmission with linear receivers in this paper where the transmitter and the re- ceivers have multiple antennas, and nd that neither strategy dom- inates the other. There is instead a transition point between the two strategies. Then, the mode switching point is determined both ana- lytically and numerically for a multiple antenna cellular downlink with correlation between transmit antennas.

A Study of Changeable Biometrics for Fingerprint Recognition

Chulhan Lee,Hyunggu Lee,Jeung-Yoon Choi,Jaihie Kim 대한전자공학회 2007 ITC-CSCC :International Technical Conference on Ci Vol.2007 No.7

To enhance security and privacy in biometric systems, changeable (or cancelable) biometric systems have been developed. These systems can revoke and re-issue biometric data when it is compromised. The proposed method generates changeable fingerprint templates by using a single reference point. In our experiments, performance the proposed method were evaluated and the experimental results showed that the proposed method is a useful way of constructing changeable biometric systems.

The Method of Iris Region Extraction for Iris Recognition

ChulHan Lee,SeungIn No,Jaihie Kim 대한전자공학회 2003 ITC-CSCC :International Technical Conference on Ci Vol.2003 No.7

Subspace based face synthesis method for cancelable face biometrics

Chulhan Lee,Hyunggu Lee,Jeung-Yoon Choi,Jongsun Kim,Jaihie Kim 대한전자공학회 2007 ITC-CSCC :International Technical Conference on Ci Vol.2007 No.7

가변 얼굴 영상의 합성 방법에 관한 연구

이형구(Hyunggu Lee),이철한(Chulhan Lee),최정윤(Jeung-Yoon Choi),김재희(Jaihie Kim) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.11

Cancelable biometrics has been introduced for secure usage of biometric data in biometric recognition system. Cancelable template is a revocably and non-invertibly transformed version of original biometric data. Normally, the face biometric data can be interpreted by machine and human. However, due to non-invertible transform, cancelable template cannot be understood by human. In this paper, we propose a method about human interpretable face image synthesis. Because, face image is synthesized using revocable cancelable template, synthesized face image is also revocable. In other words, we can simply regenerate face image with newly issued cancelable template.

노이즈에 강인한 지문 융선의 방향 추출 알고리즘

이상훈(Sanghoon Lee),이철한(Chulhan Lee),최경택(Kyoungtaek Choi),김재희(Jaihie Kim) 대한전자공학회 2008 電子工學會論文誌-SP (Signal processing) Vol.45 No.1

지문의 방향 정보는 융선 강화, 정합, 분류기 등과 같이 전반적인 지문 인식 알고리즘의 기반 정보로 사용하므로 방향 정보의 오차는 지문 인식 성능에 직접적인 영향을 준다. 지문의 방향은 대부분의 영역에서는 융선의 흐름이 완만하게 변하는 전역적인 특성과 중심점(core point)이나 삼각주(delta point)와 같은 특이점(singular point) 부근에서 융선의 흐름이 급격히 변하는 지역적인 특성을 모두 갖고 있다. 따라서 융선의 방향 추출 시에 지역적인 특성만 강조하면 특이점 부근에서의 방향 변화를 민감하게 표현해 줄 수 있지만 노이즈에 취약한 단점이 발생하고 전역적인 특성만 강조하면 노이즈에 강인한 특성을 보이지만 특이점 부근에서 방향 변화에 둔감해진다. 본 논문에서는 지역적인 특성에 민감하면서도 노이즈에 강인한 적응적 지문 방향 추출 방법에 대하여 제안하였다. 또한, 상처에 의해 발생되는 방향성 노이즈는 반복 회귀 진단으로 이상치(outlier)들을 선별하여 제거함으로써 이에 대한 영향을 최소화하였다. 그리고 영역별로 측정 사이즈를 다르게 하여 노이즈에 강인하면서 특이점 부근에서는 융선 변화에 민감하게 방향을 추정하였다. 제안 방법의 평가를 위해 인조 지문(synthetic fingerprint)과 지문 인식의 성능 평가용으로 많이 사용되는 FVC 2002 데이터베이스를 사용하였다. 융선 방향 추출의 정확성은 융선의 방향 값을 사전에 알고 있는 인조 지문 데이터를 생성하여 평가하였고 최종 지문 인식 성능의 평가는 FVC 2002 데이터베이스를 사용하였다. Ridge orientations of fingerprint image are crucial informations in many parts of fingerprint recognition such as enhancement, matching and classification. Therefore it is essential to extract the ridge orientations of image accurately because it directly affects the performance of the system. The two main properties of ridge orientation are 1) global characteristic (gradual change in whole part of fingerprint) and 2) local characteristic (abrupt change around core and delta points). When we only consider the local characteristic, estimated ridge orientations are well around singular points but not robust to noise. When the global characteristic is only considered, to estimate ridge orientation is robust to noise but cannot represent the orientation around singular points. In this paper, we propose a novel method for estimating ridge orientation which represents local characteristic specifically as well as be robust to noise. We reduce the noise caused by scar using iterative outlier rejection. We apply adaptive measurement resolution in each fingerprint area to estimate the ridge orientation around singular points accurately. We evaluate the performance of proposed method using synthetic fingerprint and FVC 2002 DB. We compare the accuracy of ridge orientation. The performance of fingerprint authentication system is evaluated using FVC 2002 DB.

The effects of low-dose radiation therapy in patients with mild-to-moderate Alzheimer’s dementia: an interim analysis of a pilot study

Aryun Kim(Aryun Kim),Jeonghwan Lee(Jeonghwan Lee),Hansol Moon(Hansol Moon),Chulhan Kim(Chulhan Kim),Min Young Yoo(Min Young Yoo),Woo Yoon Park(Woo Yoon Park),Won Dong Kim(Won Dong Kim),Young-Seok Seo( 대한방사선종양학회 2023 Radiation Oncology Journal Vol.41 No.2

Purpose: We aimed to determine whether low-dose radiotherapy (LDRT) is effective in patients with Alzheimer disease (AD). Materials and Methods: We included patients according to the following criteria: probable Alzheimer's dementia according to the New Diagnostic Criteria for Alzheimer’s Disease; confirmation of amyloid plaque deposits on baseline amyloid positron emission tomography (PET); a Korean Mini-Mental State Examination 2nd edition (K-MMSE-2) score of 13–26; and a Global Clinical Dementia Rating (CDR) score of 0.5–2 points. LDRT was performed six times at 0.5 Gy each. Post-treatment cognitive function tests and PET-CT examinations were performed to evaluate efficacy. The medication for AD treatment was maintained throughout the study period. Results: At 6 months after LDRT, neurological improvement was seen in 20% of patients. Patient #2 showed improvement in all domains of the Seoul Neuropsychological Screening Battery II (SNSB-II). Moreover, the K-MMSE-2 and Geriatric Depression Score-Short Form scores improved from 20 to 23 and from 8 to 2, respectively. For patient #3, the CDR score (sum of box score) improved from 1 (4.0) to 1 (3.5) at 3 months follow-up. Moreover, the Z scores for language and related functions, memory, and frontal executive function improved to -2.56, -1.86, and -1.32, respectively at the 6-month follow-up. Two patients complained of mild nausea and mild hair loss during LDRT, which improved after treatment. Conclusion: One of the five patients with AD treated with LDRT experienced a temporary improvement in SNSB-II. LDRT is tolerable in patients with AD. We are currently under follow-up and will conduct cognitive function tests after 12 months after LDRT. A large-scale randomized controlled trial with a longer follow-up period is warranted to determine the effect of LDRT on patients with AD.

Online signature verification using temporal shift estimated by the phase of Gabor filter

Yi, Jonghyon,Lee, Chulhan,Kim, Jaihie Institute of Electrical and Electronics Engineers 2005 IEEE transactions on signal processing Vol.55 No.1

A new online signature-verification method using temporal shift estimation is presented. Local temporal shifts existing in signatures are estimated by the differences of the phase outputs of Gabor filter applied to signature signals. In the proposed signature-verification algorithm, an input signature signal undergoes preprocessing procedures including smoothing, size normalization and skew correction, and then its feature profile is extracted from the signature signal. A Gabor filter with the predetermined center frequency ω is applied on a feature profile, and a phase profile is computed from the phase output. The feature profile and the phase profile are length normalized and quantized so that a signature code of fixed size is generated. The temporal shifts existing between two signatures are computed by using the differences between the phase profiles. The information about the temporal shifts is used as offsets for comparing the two feature profiles. Therefore, two kinds of dissimilarities are proposed. Temporal dissimilarity is a measure reflecting the amount of total temporal disturbance between the two signatures. The difference between the two signature profiles is computed at each corresponding point pair and is accumulated into temporally arranged feature profile dissimilarity. The decision boundary is represented as a straight line in the dissimilarity space whose two axes are the two dissimilarity measures. The slope and the position of the decision boundary are computed using the distribution of the dissimilarities among the sample signatures involved in the enrollment procedure. The experimental results show that through the compact and fixed size of signature data representation and relatively simple comparison methods, the proposed method can compare signatures 400 times faster than the conventional DP matching based signature-verification method.

모바일 카메라를 이용한 지문인식을 위한 지문영역 추출 및 융선방향 추출 알고리즘

이철한,이상훈,김재희,김성재,Lee Chulhan,Lee Sanghoon,Kim Jaihie,Kim Sung-Jae 대한전자공학회 2005 電子工學會論文誌-SP (Signal processing) Vol.42 No.6

본 논문에서는 모바일 카메라를 이용한 지문인식 시스템 개발에서 지문영역 추출 및 융선 방향 정보 추출 방법에 대해 제안한다. 모바일 카메라로 획득한 지문영상은 기존의 지문센서(접촉식 센서)로 획득한 영상과 여러 가지 다른 특성을 나타낸다. 우선 모바일 카메라로 획득한 지문영상은 칼라영상이며, 배경영역이 획득 장소와 시간에 따라 변화가 심하고, 지문 융선과 골의 조도차가 접촉식 센서에서 획득한 영상보다 작아 노이즈에 대한 영향이 크다는 특징이 있다. 이러한 환경에서 지문영역을 추출하고자 손가락의 색 정보와 지문의 주파수 정보를 이용하여 초기영역을 설정하고 설정된 초기영역을 이용하여 영역확장 방법으로 지문영역을 추출하였다. 손가락의 색 정보는 학습과정을 통해 손가락 색의 확률 분포를 LUT (Look Up Table)기법을 이용해 모델하였고, 주파수 정보는 초점이 맞는 손가락 영역과 초점이 맞지 않는 배경영역의 영상 주파수 특성 차이를 이용하였다. 지문 방향 정보 추출에서는 카메라로부터 발생하는 노이즈나 극단치 (outlier)의 영향을 줄이기 위해 그래디언트 필드에서 초기 방향을 기준으로 노이즈와 극단치를 제거한 후 방향을 구하는 방법을 사용하였다. 실험에서는 모바일 카메라를 이용하여 획득한 지문영상으로 지문영역 추출 및 융선방향 정보 추출에 대한 평가를 했다. 지문영역 추출 알고리즘 평가를 위해 600장의 수동 구분된 지문영상을 사용하였고 융선방향 정보 추출은 지문 인식성능으로 비교 평가 하였다. Fingerprint segmentation and ridge orientation estimation algorithms with images from a mobile camera are proposed. The fingerprint images from a mobile camera are quite different from those from conventional sensor, called touch based sensor such as optical, capacitive, and thermal. For example, the images from a mobile camera are colored and the backgrounds or non-finger regions are very erratic depending on how the image capture time and place. Also the contrast between ridge and valley of a mobile camera image are lower than that of touch based sensor image. To segment fingerprint region, we first detect the initial region using color information and texture information. The LUT (Look Up Table) is used to model the color distribution of fingerprint images using manually segmented images and frequency information is extracted to discriminate between in focused fingerprint regions and out of focused background regions. With the detected initial region, the region growing algerian is executed to segment final fingerprint region. In fingerprint orientation estimation, the problem of gradient based method is very sensitive to outlier that occurred by scar and camera noise. To solve this problem, we propose a robust regression method that removes the outlier iteratively and effectively. In the experiments, we evaluated the result of the proposed fingerprint segmentation algerian using 600 manually segmented images and compared the orientation algorithms in terms of recognition accuracy.