A case study of evaluation factors for biomedical images using neural networks

Abstract

The overall aim of the research is to compare the retrieved image with the original image with respect to the evaluation factors such as MAE, MSE, PSNR and RMSE which reflects the quality of biomedical image for telemedicine with minimum percentage of error at the recipient side. This paper presents spectral coding technique for biomedical images using neural networks in-order to accomplish the above objectives. This work is in continuity of ongoing research project aimed at developing a system for efficient image compression approach for telemedicine in Saudi Arabia. This work compares the efficiency of proposed technique against existing image compression techniques viz JPEG2000 and improved BPNN. To my knowledge, the research is the primary in providing a comparative study of evaluation factors with other techniques used in compression of biomedical images. This work is explored and tested on biomedical images such as X-rays, CT, MRI, PET etc.