期刊
NEURAL NETWORKS
卷 155, 期 -, 页码 498-511出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2022.08.031
关键词
Discriminative dictionary learning; Pattern classification; Support vector machine; Sparse representation
资金
- National Natural Science Foundation of China
- [61906087]
Discriminative dictionary learning (DDL) is an approach to solving pattern classification problems by learning dictionaries from training samples. This study proposes a new DDL algorithm that enhances discrimination by introducing a discriminative term associated with coding coefficients. The algorithm employs a structured dictionary pair and support vector machines (SVMs) for joint learning, and a classification scheme based on reconstruction error and SVMs.
Discriminative dictionary learning (DDL) aims to address pattern classification problems via learning dictionaries from training samples. Dictionary pair learning (DPL) based DDL has shown superiority as compared with most existing algorithms which only learn synthesis dictionaries or analysis dictionaries. However, in the original DPL algorithm, the discrimination capability is only promoted via the reconstruction error and the structures of the learned dictionaries, while the discrimination of coding coefficients is not considered in the process of dictionary learning. To address this issue, we propose a new DDL algorithm by introducing an additional discriminative term associated with coding coefficients. Specifically, a support vector machine (SVM) based term is employed to enhance the discrimination of coding coefficients. In this model, a structured dictionary pair and SVM classifiers are jointly learned, and an optimization method is developed to address the formulated optimization problem. A classification scheme based on both the reconstruction error and SVMs is also proposed. Simulation results on several widely used databases demonstrate that the proposed method can achieve competitive performance as compared with some state-of-the-art DDL algorithms.(c) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据