Search

Abstract: The receiver operating characteristics (ROC) curve has been extensively used for performance evaluation in multimodal biometrics fusion. However, the processes of fusion classifier design and the final ROC performance evaluation are usually conducted separately. This has been inevitable because the ROC, when taken from the error counting point of view, does not have a well-posed structure linking to the fusion classifier of interest. In this work, we propose to optimize the ROC performance directly according to the fusion classifier design. The area under the ROC curve (AUC) will be used as the optimization objective since it provides a good representation of the ROC performance. Due to the piecewise cumulative structure of the AUC, a smooth approximate formulation is proposed. This enables a direct optimization of the AUC with respect to the classifier parameters. When a fusion classifier has linear parameters, computation of the solution to optimize a quadratic AUC approximation is surprisingly simple and yet effective. Our empirical experiments on biometrics fusion show strong evidences regarding the potential of the proposed method. [Copyright &y& Elsevier]

Abstract: Lately, the once powerful one-factor authentication which is based solely on either password, token or biometric approach, appears to be insufficient in addressing the challenges of identity frauds. For example, the sole biometric approach suffers from the privacy invasion and non-revocable issues. Passwords and tokens are easily forgotten and lost. To address these issues, the notion of cancellable biometrics was introduced to denote biometric templates that can be cancelled and replaced with the inclusion of another independent authentication factor. BioHash is a form of cancellable biometrics which mixes a set of user-specific random vectors with biometric features. In verification setting, BioHash is able to deliver extremely low error rates as compared to the sole biometric approach when a genuine token is used. However, this raises the possibility of two identity theft scenarios: (i) stolen-biometrics, in which an impostor possesses intercepted biometric data of sufficient high quality to be considered genuine and (ii) stolen-token, in which an impostor has access to the genuine token and used by the impostor to claim as the genuine user. We found that the recognition rate for the latter case is poorer. In this paper, the quantised random projection ensemble based on the Johnson–Lindenstrauss Lemma is used to establish the mathematical foundation of BioHash. Based on this model, we elucidate the characteristics of BioHash in pattern recognition as well as security view points and propose new methods to rectify the stolen-token problem. [Copyright &y& Elsevier]

Abstract: This paper addresses the biometric scores fusion problem from the error rate minimization point of view. Comparing to the conventional approach which treats fusion classifier design and performance evaluation as a two-stage process, this work directly optimizes the target performance with respect to fusion classifier design. Based on a smooth approximation to the total error rate of identity verification, a deterministic solution is proposed to solve the fusion optimization problem. The proposed method is applied to a face and iris verification fusion problem addressing the demand for high security in the modern networked society. Our empirical evaluations show promising potential in terms of decision accuracy and computing efficiency. [Copyright &y& Elsevier]

• This paper explores the potential of spatial feature dimensions to seek an effective feature representation for point clouds. • The dimension expansion of MKConv enables spatially correlated feature representation and discrete convolutions for point cloud data without information loss. • For stable and effective learning, kernel weight normalization and multidimensional attention are proposed. • The effectiveness of multidimensional feature representation is demonstrated by the superior performance on three different point cloud processing tasks including object classification, object part segmentation, and scene semantic segmentation. Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function that can handle an arbitrary point in continuous space. Various approaches exhibiting high performance have been proposed, but we observe that the standard pointwise feature is represented by 1D channels and can become more informative when its representation involves additional spatial feature dimensions. In this paper, we present Multidimensional Kernel Convolution (MKConv), a novel convolution operator that learns to transform the point feature representation from a vector to a multidimensional matrix. Unlike standard point convolution, MKConv proceeds via two steps. (i) It first activates the spatial dimensions of local feature representation by exploiting multidimensional kernel weights. These spatially expanded features can represent their embedded information through spatial correlation as well as channel correlation in feature space, carrying more detailed local structure information. (ii) Then, discrete convolutions are applied to the multidimensional features which can be regarded as a grid-structured matrix. In this way, we can utilize the discrete convolutions for point cloud data without voxelization that suffers from information loss. Furthermore, we propose a spatial attention module, Multidimensional Local Attention (MLA), to provide comprehensive structure awareness within the local point set by reweighting the spatial feature dimensions. We demonstrate that MKConv has excellent applicability to point cloud processing tasks including object classification, object part segmentation, and scene semantic segmentation with superior results. [ABSTRACT FROM AUTHOR]

Ever since the availability of real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor, the performance of gesture recognition can be largely enhanced. However, since conventional two-dimensional (2D) image based feature extraction methods such as local binary pattern (LBP) generally use texture information, they cannot be applied to depth or range image which does not contain texture information. In this paper, we propose an adaptive local binary pattern (ALBP) for effective depth images based applications. Contrasting to the conventional LBP which is only rotation invariant, the proposed ALBP is invariant to both rotation and the depth distance in range images. Using ALBP, we can extract object features without using texture or color information. We further apply the proposed ALBP for hand tracking using depth images to show its effectiveness and its usefulness. Our experimental results validate the proposal. [ABSTRACT FROM AUTHOR]

• Surveillance anomaly detection is critical in our daily life that replaces inefficient human monitoring with an automated system and provides various pattern recognition applications. • In this paper, novel architecture ITAE learns normal appearance and motion patterns by implicitly capturing static and dynamic features. • By utilizing normalizing flow generative model, we are the first to estimate the distribution of appearance and motion surveillance video features. • The proposed approach achieves superior performance on six surveillance anomaly detection benchmarks and demonstrates its effectiveness of generalization ability which is crucial issue in real-world scenarios. In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos without anomalous events, which makes the task challenging. Most existing methods use an autoencoder (AE) to learn to reconstruct normal videos; they then detect anomalies based on their failure to reconstruct the appearance of abnormal scenes. However, because anomalies are distinguished by appearance as well as motion, many previous approaches have explicitly separated appearance and motion informationfor example, using a pre-trained optical flow model. This explicit separation restricts reciprocal representation capabilities between two types of information. In contrast, we propose an implicit two-path AE (ITAE), a structure in which two encoders implicitly model appearance and motion features, along with a single decoder that combines them to learn normal video patterns. For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features through normalizing flow (NF)-based generative models to learn the tractable likelihoods and identify anomalies using out-of-distribution detection. NF models intensify ITAE performance by learning normality through implicitly learned features. Finally, we demonstrate the effectiveness of ITAE and its feature distribution modeling on six benchmarks, including databases that contain various anomalies in real-world scenarios. [ABSTRACT FROM AUTHOR]

Abstract: We propose a face detection method based on skin color likelihood via a boosting algorithm which emphasizes skin color information while deemphasizing non-skin color information. A stochastic model is adapted to compute the similarity between a color region and the skin color. Both Haar-like features and Local Binary Pattern (LBP) features are utilized to build a cascaded classifier. The boosted classifier is implemented based on skin color emphasis to localize the face region from a color image. Based on our experiments, the proposed method shows good tolerance to face pose variation and complex background with significant improvements over classical boosting-based classifiers in terms of total error rate performance. [Copyright &y& Elsevier]

Abstract: The primary goal of linear discriminant analysis (LDA) in face feature extraction is to find an effective subspace for identity discrimination. The introduction of kernel trick has extended the LDA to nonlinear decision hypersurface. However, there remained inherent limitations for the nonlinear LDA to deal with physical applications under complex environmental factors. These limitations include the use of a common covariance function among each class, and the limited dimensionality inherent to the definition of the between-class scatter. Since these problems are inherently caused by the definition of the Fisher''s criterion itself, they may not be solvable under the conventional LDA framework. This paper proposes to adopt a margin-based between-class scatter and a regularization process to resolve the issue. Essentially, we redesign the between-class scatter matrix based on the SVM margins to facilitate an effective and reliable feature extraction. This is followed by a regularization of the within-class scatter matrix. Extensive empirical experiments are performed to compare the proposed method with several other variants of the LDA method using the FERET, AR, and CMU-PIE databases. [Copyright &y& Elsevier]