期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：6
页码：7305-7308
出版社：TechScience Publications
摘要：The M-band wavelet decomposition, which is a direct generalization of the standard 2-band wavelet decomposition is applied to the problem of an unsupervised segmentation of different texture images. Orthogonal and linear phase M-band wavelet transform is used to decompose the image into MXM channels. Various sections of these bandpass sections are combined to obtain different scales and orientations in the frequency plane. Texture features are extracted by applying each bandpass section to a nonlinear transformation and computing the measure of energy in a window around each pixel of the filtered texture images. Then the window size is adaptively selected depending on the frequency content of the images. Unsupervised texture segmentation derived by combination of different clustering and feature extraction techniques is compared.
关键词：Discrete Wavelet Transform; M-band WT; Discrete;Wavelet Packet; K Means; FarthestFirst
