Title :
Wavelet filter selection by clustering of image measures
Author :
Patuck, N. ; McLernon, D.
Author_Institution :
Sch. of Electron. & Electr. Eng., Leeds Univ., UK
Abstract :
It has been shown that a single wavelet filter bank is not optimal for all types of images in a wavelet based image coding system. This paper describes a method to overcome this problem by selecting the most appropriate filter bank using a classification algorithm. The classification is performed by calculating feature measures from the image data which form clusters for images with similar properties. An analysis of this clustering was also performed and shown to be near optimal. By selecting the most appropriate filter bank for the wavelet transform, a PSNR coding gain varying from 0.2 (for aerial images) to 10 dB (for scanned text images) has been achieved.
Keywords :
channel bank filters; data compression; image coding; pattern clustering; transform coding; wavelet transforms; 0.2 to 10 dB; PSNR coding gain; aerial image; classification algorithm; feature measure calculation; image coding system; image data; image measure clustering; scanned text image; wavelet filter bank selection; wavelet transform; Biomedical imaging; Classification algorithms; Clustering algorithms; Electric variables measurement; Filter bank; Image coding; PSNR; Performance analysis; Performance evaluation; Wavelet transforms;
Conference_Titel :
Video/Image Processing and Multimedia Communications, 2003. 4th EURASIP Conference focused on
Print_ISBN :
953-184-054-7
DOI :
10.1109/VIPMC.2003.1220490
