Efficient colour texture image retrieval by combination of colour and texture features in wavelet domain

A new approach for image retrieval by combination of colour and texture features is proposed. This approach uses the histogram of feature vectors, which are constructed from the coefficients of some subbands of wavelet transform and chosen according to their intrinsic characters. A K-means algorithm is used to quantise feature vectors. The experimental results both on small size databases (40 classes of textures) and large size databases (167 classes of textures) show that, compared with the state-of-the-art approaches, the proposed approach can achieve better retrieval performance.

[1]  Kidiyo Kpalma,et al.  Color textured image retrieval by combining texture and color features , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[2]  Cun Lu Xu,et al.  Chromatic Statistical Landscape Features for Retrieval of Color Textured Images , 2009, 2009 Fourth International Conference on Internet Computing for Science and Engineering.

[3]  Yannick Berthoumieu,et al.  Copulas based multivariate gamma modeling for texture classification , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Yannick Berthoumieu,et al.  Multivariate texture retrieval using the geodesic distance between elliptically distributed random variables , 2011, 2011 18th IEEE International Conference on Image Processing.

[5]  Nam Chul Kim,et al.  Content-Based Image Retrieval Using Multiresolution Color and Texture Features , 2008, IEEE Transactions on Multimedia.

[6]  Amit Jain,et al.  A multiscale representation including opponent color features for texture recognition , 1998, IEEE Trans. Image Process..

[7]  Spyros Liapis,et al.  Color and texture image retrieval using chromaticity histograms and wavelet frames , 2004, IEEE Transactions on Multimedia.