http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Equal Error Rate Minimization for Biometrics Fusion
Kar-Ann Toh,Jaihie Kim,Sangyoun Lee 대한전자공학회 2008 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
This paper presents a formulation for minimizing the equal error rate (EER) in multimodal biometrics fusion. By utilizing a linear parametric model and a constrained optimization framework, the solution to the EER minimization problem can be translated into a tuning task for the Lagrange multiplier. The formulation is experimented on a fusion task, combining the scores of an infrared face system and that of a visual face system. Our preliminary result shows stability of fusion which is very encouraging.
Stretchy binary classification
Toh, Kar-Ann,Lin, Zhiping,Sun, Lei,Li, Zhengguo Elsevier 2018 Neural networks Vol.97 No.-
<P><B>Abstract</B></P> <P>In this article, we introduce an analytic formulation for compressive binary classification. The formulation seeks to solve the least <SUP> ℓ p </SUP> -norm of the parameter vector subject to a classification error constraint. An analytic and stretchable estimation is conjectured where the estimation can be viewed as an extension of the pseudoinverse with left and right constructions. Our variance analysis indicates that the estimation based on the left pseudoinverse is unbiased and the estimation based on the right pseudoinverse is biased. Sparseness can be obtained for the biased estimation under certain mild conditions. The proposed estimation is investigated numerically using both synthetic and real-world data.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Proposed a novel cost function for counting the samples that are misclassified. </LI> <LI> Conjectured an analytic solution to a constrained p -norm minimization problem. </LI> <LI> Linkage of the proposed formulation to two existing classifiers. </LI> <LI> Provided variance analysis for the proposed analytic solution. </LI> <LI> Extensive experiments with comparison to state-of-the-arts. </LI> </UL> </P>
An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition
Oh, Beom-Seok,Toh, Kar-Ann,Teoh, Andrew Beng Jin,Lin, Zhiping IEEE 2018 IEEE TRANSACTIONS ON IMAGE PROCESSING - Vol.27 No.6
<P>Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.</P>
Optimizing between data transformation and parametric weighting for stable binary classification
Oh, Kangrok,Li, Zhengguo,Oh, Beom-Seok,Toh, Kar-Ann Elsevier 2018 Journal of the Franklin Institute Vol.355 No.4
<P><B>Abstract</B></P> <P>In this paper, an optimization problem is formulated for stable binary classification. Essentially, the objective function seeks to optimize a full data transformation matrix along with the learning of a linear parametric model. The data transformation matrix and the weight parameter vector are alternatingly optimized based on the area above the receiver operating characteristic curve criterion. The proposed method improves the existing means via an optimal data transformation rather than that based on the diagonal, random and ad-hoc settings. This optimal transformation stretches beyond the fixed settings of known optimization methods. Extensive experiments using 34 binary classification data sets show that the proposed method can be more stable than competing classifiers. Specifically, the proposed method shows robustness to imbalanced and small training data sizes in terms of classification accuracy with statistical evidence.</P> <P><B>Highlights</B></P> <P> <UL> <LI> An optimizing data transformation is proposed based on the area above the ROC curve. </LI> <LI> The proposed method is effective when a low number of training samples is available. </LI> <LI> The proposed method is robust to imbalance data class distribution. </LI> <LI> The proposed method is stable with respect to classier model complexity. </LI> </UL> </P>
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>