Project: Image Texture Analysis

People

S.Hatipoglu, S.K.Mitra

Objective

Efficient texture representation is important in search and retrieval of similar texture patterns from a large database. Tests indicate that the texture features, which can efficiently define directional and spatial/frequency characteristics of the patterns, lead to good texture analysis and classification results.  In this project, applications of dual-tree complex wavelet transform (DT-CWT) in texture description and texture based image retrieval were investigated. Its approximate shift invariance, good directional selectivity in 2 dimensions and perfect reconstruction properties make it a fast and efficient tool for texture based image-processing tasks.  The idea of finding the frequency channels with the most significant orientations of the texture pattern and continuing the decomposition only for the corresponding sub-images were used in finding the feature vector elements.  The normalized Euclidian distance between extracted feature vectors gives a good measure of similarity between the texture patterns. Tests performed by using Brodatz texture database and comparisons with various feature extraction methods have shown that DT-CWT is effective in finding similar patterns from a large texture database. Initial results of this project have been presented at an international conference [1].  

Publications

These materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

1. S. Hatipoglu, S.K. Mitra, and N. Kingsbury, "Image texture description using complex wavelet transform," Proc. IEEE International Conference on Image Processing , Vancouver, B.C., Canada, September 2000, vol. II, pp. 530-533.

2. S.Hatipoglu, S.K.Mitra and N. Kingsbury, "Texture classification using dual-tree complex wavelet transform," Seventh International Conference on Image Processing and Its Applications, Manchester, UK, 13-15 July 1999. Lo p.344-7 vol.1. 2.