Texture feature extraction based on wavelet transform
The 2-D lifting-based DWT 9/7wavelet filter is used here, without additional computations, giving lifting-based architectures a significant advantage over convoiutional filter band-based architectures. This paper describes the texture classification using (I) the known texture images are decomposed using 9/7wavelet. Then, mean and standard deviation of approximation and detail sub-bands of 3-level decomposed images are calculated. They are wavelet statistical features (WSFs) (ii) In order to improve the correct classification rate further, it is proposed to find co-occurrence matrix features for original image, approximation and detail sub-bands of 1-level 9/7 wavelet decomposed images. The various cooccurrence features such as contrast, energy, entropy and homogeneity are calculated from the co-occurrence matrix. These are wavelet co-occurrence features (WCFs). (iii) At last, the combination of WSFs and WCFs (feature vector) are used to classify images.
feature extraction texture classification wavelet transform wavelet statistical features(WSFs) wavelet co-occurrence features (WCFs)
Zhang Hong Zhang Xuanbing
School of Civil Engineering and Architecture Nanchang University Nanchang, China
国际会议
太原
英文
146-149
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）