Self Organizing Map Cluster Approach for Wavelet Based Medical Image Compression

Abstract

Digital medical powerful tools for diagnosis, treatment and surgery and plays a vital role in modern healthcare delivery. Large storage capacity is needed for storing these images and for transmitting them. This leads to the strong demand for digital medical image compression and reliable transmission. In this study, we have applied three compression methods to medical images. In all the methods discrete wavelet transform is applied followed by the corresponding compression methods. The experiments are carried on three medical images and the quality of reconstructed images is evaluated based on Compression Ratio (CR) and Peak Signal to Noise Ratio. The results show that the SOM algorithm has higher compression ratio than FCM and FKM while maintaining the image quality and preserving the information. The results show that the SOM algorithm outperforms the existing methods FCM and FKM for medical image compression.