Texture Classifications Based on Dual-tree Complex Wavelet Transform

摘要：

In this paper, a new texture classification method using the dual-tree complex wavelet transform (DTCWT) and support vector machines (SVM) is proposed. The DT-CWT provides a shift-invariant, multiseale, and multidirectional image representation which has proven to be very efficient in image analysis applications. Firstly, features are extracted from the high-frequency and low-frequency DTCWT coefficients of source images. Before the feature extraction process, the coefficients sub-band images are clipped in order to reduce the abrupt mutation produced when the filters pass through the border of texture image. In addition, SVMs, which are used as classifiers for texture classification.The Brodatz album texture images are used to test the proposed method. Experimental results demonstrate that the proposed method produces very high accurate classification results.

关键词： texture classification dual-tree complex wavelet transform support vector machines

作者: Rixin Chen

作者单位: Department of Electrical & Information Engineering Hunan University of Arts and Science Changde,China

会议类型: 国际会议

会议名称: The 10th International Conference on Intelligent Technologies(第十届智慧科技国际会议 InTech09)

会议地点: 桂林

会议语种:英文

页码: 63-66

在线出版日期: 2009-12-12（万方平台首次上网日期，不代表论文的发表时间）