Image compression in the wavelet domain using an AR texture model with compressed initial conditions
Ming-Hwei Perng, Hsiu‐Hau Lin · 2006
Abstract:- This paper present a texture compression technique for still images based on the wavelet transform and the auto-regressive (AR) texture model in order to increase the compression ratio with a minimal loss of image quality. First the influences of the initial condition and the order of an AR model on the resulting texture model are investigated to serve as a theoretical foundation for the proposed approach. To further the compression ratio, this paper also presents a texture compressing technique using an auto-regressive texture model with compressed initial conditions. Results show that the AR model is better than a random texture model when the order of the AR model is adequately chosen, and compression of the initial conditions in the AR model can significantly improve the compression ratio without a noticeable loss of image quality. Key-Words:- image compression, AR model, texture model, initial conditions, order 1