Fuzzy coded trellis quantization

Abstract

In this paper we propose an image compression algorithm based on embedded trellis quantization and inventive fuzzy context based modeling (TCQFCB). The indices produced by trellis-coded quantization are adaptively arithmetically coded, bit plane by bit plane. The fuzzy logic is used to assign the probability of the coded symbol for an arithmetic coder. The probability of the coded bit depends on the previous coded bits. The fuzzy logic is used in order to attribute the highest possible probability of the coded bit. The performance of the proposed method is comparable with the state-of-the-art methods.