The Experts below are selected from a list of 18015 Experts worldwide ranked by ideXlab platform
Yong Xu - One of the best experts on this subject based on the ideXlab platform.
-
a new discriminative sparse Representation Method for robust face recognition via l_ 2 regularization
IEEE Transactions on Neural Networks, 2017Co-Authors: Yong Xu, Jian Yang, Zuofeng Zhong, David ZhangAbstract:Sparse Representation has shown an attractive performance in a number of applications. However, the available sparse Representation Methods still suffer from some problems, and it is necessary to design more efficient Methods. Particularly, to design a computationally inexpensive, easily solvable, and robust sparse Representation Method is a significant task. In this paper, we explore the issue of designing the simple, robust, and powerfully efficient sparse Representation Methods for image classification. The contributions of this paper are as follows. First, a novel discriminative sparse Representation Method is proposed and its noticeable performance in image classification is demonstrated by the experimental results. More importantly, the proposed Method outperforms the existing state-of-the-art sparse Representation Methods. Second, the proposed Method is not only very computationally efficient but also has an intuitive and easily understandable idea. It exploits a simple algorithm to obtain a closed-form solution and discriminative Representation of the test sample. Third, the feasibility, computational efficiency, and remarkable classification accuracy of the proposed $l_{2}$ regularization-based Representation are comprehensively shown by extensive experiments and analysis. The code of the proposed Method is available at http://www.yongxu.org/lunwen.html .
-
A New Discriminative Sparse Representation Method for Robust Face Recognition via $l_{2}$ Regularization
IEEE Transactions on Neural Networks and Learning Systems, 2017Co-Authors: Yong Xu, Jian Yang, Zuofeng Zhong, David ZhangAbstract:Sparse Representation has shown an attractive performance in a number of applications. However, the available sparse Representation Methods still suffer from some problems, and it is necessary to design more efficient Methods. Particularly, to design a computationally inexpensive, easily solvable, and robust sparse Representation Method is a significant task. In this paper, we explore the issue of designing the simple, robust, and powerfully efficient sparse Representation Methods for image classification. The contributions of this paper are as follows. First, a novel discriminative sparse Representation Method is proposed and its noticeable performance in image classification is demonstrated by the experimental results. More importantly, the proposed Method outperforms the existing state-of-the-art sparse Representation Methods. Second, the proposed Method is not only very computationally efficient but also has an intuitive and easily understandable idea. It exploits a simple algorithm to obtain a closed-form solution and discriminative Representation of the test sample. Third, the feasibility, computational efficiency, and remarkable classification accuracy of the proposed l2 regularization-based Representation are comprehensively shown by extensive experiments and analysis. The code of the proposed Method is available at http://www.yongxu.org/lunwen.html.
-
supervised sparse Representation Method with a heuristic strategy and face recognition experiments
Neurocomputing, 2012Co-Authors: Yong XuAbstract:In this paper we propose a supervised sparse Representation Method for face recognition. We assume that the test sample could be approximately represented by a sparse linear combination of all the training samples, where the term ''sparse'' means that in the linear combination most training samples have zero coefficients. We exploit a heuristic strategy to achieve this goal. First, we determine a linear combination of all the training samples that best represents the test sample and delete the training sample whose coefficient has the minimum absolute value. Then a similar procedure is carried out for the remaining training samples and this procedure is repeatedly carried out till the predefined termination condition is satisfied. The finally remaining training samples are used to produce a best Representation of the test sample and to classify it. The face recognition experiments show that the proposed Method can achieve promising classification accuracy.
-
Supervised sparse Representation Method with a heuristic strategy and face recognition experiments
Neurocomputing, 2012Co-Authors: Yong Xu, Wangmeng Zuo, Zizhu FanAbstract:In this paper we propose a supervised sparse Representation Method for face recognition. We assume that the test sample could be approximately represented by a sparse linear combination of all the training samples, where the term "sparse" means that in the linear combination most training samples have zero coefficients. We exploit a heuristic strategy to achieve this goal. First, we determine a linear combination of all the training samples that best represents the test sample and delete the training sample whose coefficient has the minimum absolute value. Then a similar procedure is carried out for the remaining training samples and this procedure is repeatedly carried out till the predefined termination condition is satisfied. The finally remaining training samples are used to produce a best Representation of the test sample and to classify it. The face recognition experiments show that the proposed Method can achieve promising classification accuracy. © 2011 Elsevier B.V.
Zizhu Fan - One of the best experts on this subject based on the ideXlab platform.
-
Supervised sparse Representation Method with a heuristic strategy and face recognition experiments
Neurocomputing, 2012Co-Authors: Yong Xu, Wangmeng Zuo, Zizhu FanAbstract:In this paper we propose a supervised sparse Representation Method for face recognition. We assume that the test sample could be approximately represented by a sparse linear combination of all the training samples, where the term "sparse" means that in the linear combination most training samples have zero coefficients. We exploit a heuristic strategy to achieve this goal. First, we determine a linear combination of all the training samples that best represents the test sample and delete the training sample whose coefficient has the minimum absolute value. Then a similar procedure is carried out for the remaining training samples and this procedure is repeatedly carried out till the predefined termination condition is satisfied. The finally remaining training samples are used to produce a best Representation of the test sample and to classify it. The face recognition experiments show that the proposed Method can achieve promising classification accuracy. © 2011 Elsevier B.V.
David Zhang - One of the best experts on this subject based on the ideXlab platform.
-
a new discriminative sparse Representation Method for robust face recognition via l_ 2 regularization
IEEE Transactions on Neural Networks, 2017Co-Authors: Yong Xu, Jian Yang, Zuofeng Zhong, David ZhangAbstract:Sparse Representation has shown an attractive performance in a number of applications. However, the available sparse Representation Methods still suffer from some problems, and it is necessary to design more efficient Methods. Particularly, to design a computationally inexpensive, easily solvable, and robust sparse Representation Method is a significant task. In this paper, we explore the issue of designing the simple, robust, and powerfully efficient sparse Representation Methods for image classification. The contributions of this paper are as follows. First, a novel discriminative sparse Representation Method is proposed and its noticeable performance in image classification is demonstrated by the experimental results. More importantly, the proposed Method outperforms the existing state-of-the-art sparse Representation Methods. Second, the proposed Method is not only very computationally efficient but also has an intuitive and easily understandable idea. It exploits a simple algorithm to obtain a closed-form solution and discriminative Representation of the test sample. Third, the feasibility, computational efficiency, and remarkable classification accuracy of the proposed $l_{2}$ regularization-based Representation are comprehensively shown by extensive experiments and analysis. The code of the proposed Method is available at http://www.yongxu.org/lunwen.html .
-
A New Discriminative Sparse Representation Method for Robust Face Recognition via $l_{2}$ Regularization
IEEE Transactions on Neural Networks and Learning Systems, 2017Co-Authors: Yong Xu, Jian Yang, Zuofeng Zhong, David ZhangAbstract:Sparse Representation has shown an attractive performance in a number of applications. However, the available sparse Representation Methods still suffer from some problems, and it is necessary to design more efficient Methods. Particularly, to design a computationally inexpensive, easily solvable, and robust sparse Representation Method is a significant task. In this paper, we explore the issue of designing the simple, robust, and powerfully efficient sparse Representation Methods for image classification. The contributions of this paper are as follows. First, a novel discriminative sparse Representation Method is proposed and its noticeable performance in image classification is demonstrated by the experimental results. More importantly, the proposed Method outperforms the existing state-of-the-art sparse Representation Methods. Second, the proposed Method is not only very computationally efficient but also has an intuitive and easily understandable idea. It exploits a simple algorithm to obtain a closed-form solution and discriminative Representation of the test sample. Third, the feasibility, computational efficiency, and remarkable classification accuracy of the proposed l2 regularization-based Representation are comprehensively shown by extensive experiments and analysis. The code of the proposed Method is available at http://www.yongxu.org/lunwen.html.
Hiroshi Isshiki - One of the best experts on this subject based on the ideXlab platform.
-
Application of the Generalized Integral Representation Method (GIRM) to Tidal Wave Propagation
Applied and Computational Mathematics, 2015Co-Authors: Hiroshi IsshikiAbstract:Integral Representation Method (IRM) is one of convenient Methods to solve Initial and Boundary Value Problems (IBVP). It can be applied to irregular mesh, and the solution is stable and accurate. IRM is developed to Generalized Integral Representation Method (GIRM) to treat any kinds of problems including nonlinear problems. In GIRM, Generalized Fundamental Solution (GFS) is used instead of Fundamental Solution (FS) in IRM. We can use a variety of GFSs in GIRM. The effects of typical GFSs are investigated. In the present paper, an application of GIRM to tidal wave propagation is discussed, and the time evolution involves the second order time derivatives. An explicit time evolution is used successfully in the present paper.
-
Effects of Generalized Fundamental Solution (GFS) on Generalized Integral Representation Method (GIRM)
Applied and Computational Mathematics, 2015Co-Authors: Hiroshi IsshikiAbstract:Integral Representation Method (IRM) is one of convenient Methods to solve Initial and Boundary Value Problems (IBVP). It can be applied to irregular mesh, and the solution is stable and accurate. IRM is developed to Generalized Integral Representation Method (GIRM) to treat any kinds of problems including nonlinear problems. In GIRM, Generalized Fundamental Solution (GFS) is used instead of Fundamental Solution (FS) in IRM. Since GFS is not limited to one, the effects of individual GFSs must be clarified. The continuity of GFS is related to the characteristics of individual GFSs.
-
From Integral Representation Method (IRM) to Generalized Integral Representation Method (GIRM)
Applied and Computational Mathematics, 2015Co-Authors: Hiroshi IsshikiAbstract:Integral Representation Method (IRM) is one of convenient Methods to solve Initial and Boundary Value Problems (IBVP). It can be applied to irregular mesh, and the solution is stable and accurate. However, it was originally developed for linear equations with known fundamental solutions. In order to apply to general nonlinear equations, we must generalize the Method. In the present paper, a generalization of IRM (GIRM) is discussed and applied to specific problems and the numerical solutions obtained. The numerical results are stable and accurate. The generalized Method is called Generalized Integral Representation Method (GIRM). Brief explanations on the relationships with other numerical Methods are also given.
-
solution of a diffusion problem in a non homogeneous flow and diffusion field by the integral Representation Method irm
Applied and Computational Mathematics, 2014Co-Authors: Hiroshi Isshiki, Shuichi Nagata, Yasutaka ImaiAbstract:Integral Representations are derived from a differential-type boundary value problem using a fundamental solution. A set of integral Representations is equivalent to a set of differential equations. If the boundary conditions are substituted into the integral Representations, the integral equations are obtained, and the unknown variables are determined by solving the integral equations. In other words, an integral-type boundary value problem is derived from the integral Representations. An effective and flexible finite element algorithm is easily obtained from the integral-type boundary value problem. In the present paper, integral Representations are obtained for the diffusion of a material or heat in the sea, where the convective velocity and diffusion constant change in space and time. A new numerical solution of an advection-diffusion equation is proposed based integral Representations using the fundamental solution of the primary space-differential operator, and the numerical results are shown. An innovative generalization of the integral Representation Method: generalized integral Representation Method is also proposed. The numerical examples are given to verify the theory.
Wangmeng Zuo - One of the best experts on this subject based on the ideXlab platform.
-
Supervised sparse Representation Method with a heuristic strategy and face recognition experiments
Neurocomputing, 2012Co-Authors: Yong Xu, Wangmeng Zuo, Zizhu FanAbstract:In this paper we propose a supervised sparse Representation Method for face recognition. We assume that the test sample could be approximately represented by a sparse linear combination of all the training samples, where the term "sparse" means that in the linear combination most training samples have zero coefficients. We exploit a heuristic strategy to achieve this goal. First, we determine a linear combination of all the training samples that best represents the test sample and delete the training sample whose coefficient has the minimum absolute value. Then a similar procedure is carried out for the remaining training samples and this procedure is repeatedly carried out till the predefined termination condition is satisfied. The finally remaining training samples are used to produce a best Representation of the test sample and to classify it. The face recognition experiments show that the proposed Method can achieve promising classification accuracy. © 2011 Elsevier B.V.
