Toward an optimal medical image compression based on ISOM

Abstract

Images require substantial storage and transmission resources, thus image compression is advantageous to reduce these requirements. A good strategy of pictures compression should assure a good compromise between a high compression rate and a low distortion of the picture. In this paper, we present a direct solution method based on incremental self organizing map (ISOM) and discrete wavelet transform (DWT) for image compression. This method is a combination of DWT decomposition and ISOM image compression. Wavelet transform is applied to medical ultrasound images, so it produces no blocking artefacts; this is a major advantage of wavelet over other transform methods. In fact, we apply a lossless codec for approximation coefficients and ISOM for horizontal, vertical and diagonal coefficients. The results show that the proposed approach for medical ultrasound image succeeded to improve high performances in terms of compression ratio and reconstruction quality compared to JPEG image compression.