Fuzzy Wavelets based Color Image Compression/Reconstruction with Soft Thresholding

H. Nobuhara and K. Hirota (Japan)


Wavelets, Fuzzy Wavelets, Image Compression, Fuzzy Relation, Alpha-Cut, YUV Color Space


A color image compression and reconstruction method based on fuzzy wavelets is proposed, where a soft thresh olding scheme can be formulated as an extension of alpha cut of fuzzy relation. The proposed fuzzy wavelets are based on a partial fuzzification of morphological wavelets and the image compression and reconstruction process can be adjusted by fuzzy sets that correspond to soft thresh old. Therefore,the proposed fuzzy wavelets are more natu ral interpretation of fuzzy wavelets and a human subjectiv ity can be applied to the image compression process, com pared with the conventional fuzzy wavelets. Through an experiment using a color image extracted from Standard Image DataBAse (SIDBA), it is confirmed that the root mean square error of the reconstructed image obtained by the soft thresholding is decreased to 84.79% of that of the hard thredholding, under the condition that the compres sion rate is about 0.06.

Important Links:

Go Back