Abstract—This paper proposes a technique for image texture classification based on cosine-modulated wavelet transform. Better discriminability and low implementation cost of the cosine-modulated wavelets has been effectively utilized to yield better features and more accurate classification results. Experimental results demonstrate the effectiveness of this approach on different datasets in three experiments. The proposed approach improves classification rates compared to the traditional Gabor wavelet based approach, rotated wavelet filters based approach, DT-CWT approach and the DLBP approach. The computational cost of the proposed method is less as compared to the other two methods.

Index Terms—Texture classification, cosine-modulated wavelets, gabor wavelets.

The authors are with the Department of Electronics and Telecommunication, Yeshwantrao Chavan College of Engineering, Nagpur(e-mail: milindmushrif@yahoo.co.in, yogeetakdubey@yahoo.co.in)

Cite: Milind M. Mushrif and Yogita K. Dubey, "Texture Classification Using Cosine-modulated Wavelets," International Journal of Computer and Electrical Engineering vol. 4, no. 3, pp. 270-273, 2012.