Color image compression using self organizing feature map

Abstract

This paper presents a compression scheme for color images, by using Self-Organizing Feature Map (SOFM) algorithm, which is a neural network structure. In this application 1-dimensional SOFM is used to map 256-color to 64-, 32- and 16-color. After the quantization process, relative coding and entropy coding are performed without any loss in the information. Obtained results encourage the use of SOFM for image compression.