An Image Retrieval Method Based on Tree

In this paper, the investigation on using the proposed ZTE wavelet based compression algorithm for the image retrieval system is presented. The proposed algorithm transform an image into multi-layer bitstream, the base layer and enhancement layer bitstreams.Then the multi-layer bitstream is coded with the improved adaptive binary arithmetic by changed the length of the interval of the symbols. The experimental results show that the proposed algorithm outperforms the Embedded Zerotree Wavelets algorithm, in compression efficiency. On the other hand, the base layer and enhancement layer bitstreams, it provides superior benefits to the retrieval system compared to other compression methods. Moreover, the enhancement layer bitstream also allows fast transmission that enhances the performance of retrieval systems.

[1]  Ian H. Witten,et al.  Arithmetic coding for data compression , 1987, CACM.

[2]  B. S. Manjunath,et al.  NeTra: A toolbox for navigating large image databases , 1997, Multimedia Systems.

[3]  Michel Barlaud,et al.  Image coding using wavelet transform , 1992, IEEE Trans. Image Process..

[4]  Ian H. Witten,et al.  Arithmetic coding revisited , 1998, TOIS.

[5]  Jerome M. Shapiro,et al.  Embedded image coding using zerotrees of wavelet coefficients , 1993, IEEE Trans. Signal Process..