Image coding using 2-D space-varying linear predictive filters excited by a 2-D multipulse field

Abstract

This paper deals with information compression for digitized image encoding. Among the different techniques, we discuss the Linear Predictive Coding (LPC) technique. Because of the non-homogeneous nature of images, a space-varying model would yield better results. Therefore, we propose a Linear Predictive Image Coding technique using a space-varying 2-D AR filter. Compression is achieved by an approximation of the AR model input (prediction residual) with a limited number of pulses. The multipulse techniques of Atal and Depreterre are used for the input estimation. First, the space-varying AR 2-D filter is presented for image modeling. Using space basis functions, the LPC parameters are estimated. Then, the problem of the estimation of the synthetic input (location and amplitude of pulses) is stated. Two solutions are given to overcome the computational difficulties that arise when excitation estimation methods (Atal and Depreterre) are applied with a space-varying image model. The efficiency of the proposed solutions is shown by experimental results.