SSP'05 -- Proceedings

	IEEE/SP 13th workshop on Statistical Signal Processing July, 17-20, 2005 - Bordeaux - France

Information regarding the paper

Title

Image Compression with Best Local Cosine Bases

Author(s)

Yan Huang	Purdue University
Ilya Pollak	Purdue University

Get the paper in PDF format

To obtain Acrobat Reader (version 5 minimum required) necessary to his read.

Abstract

We use our framework of multitree dictionaries to design a novel image coder based on lapped orthogonal bases of local cosines. We illustrate our approach using several textured images and show that our image coder has better rate-distortion performance than both the quadtree local cosine coder and SPIHT which is an embedded wavelet coder.