期刊
NEUROCOMPUTING
卷 197, 期 -, 页码 212-220出版社
ELSEVIER
DOI: 10.1016/j.neucom.2016.02.061
关键词
Feature extraction; Texture classification; Dual-tree complex wavelet transform; Gray level co-occurrence matrix
资金
- National Natural Science Foundation of China [61363050, 61272077, 61563037]
- Natural Science Foundation of JiangXi Province [20142BDH80026]
This paper introduces a new feature extraction method for texture classification application. In the proposed method, dual-tree complex wavelet transform is first performed on the original image to obtain sub-images at six directions. After that gray level co-occurrence matrix of each sub-image is calculated and the corresponding statistical values are used to construct the final feature vector. The experimental results demonstrate that our proposed method has the property of robustness, and can achieve higher texture classification accuracy rate than the conventional methods. (C) 2016 Elsevier B.V. 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