Grayscale Medical Image Compression Using Feedforward Neural Networks

Authors

  • W. K. Yeo University Teknikal Malaysia Melaka
  • F. W. Yap University Teknikal Malaysia Melaka
  • D. P. Andito University Teknikal Malaysia Melaka
  • M. K. Suaidi University Teknikal Malaysia Melaka

Keywords:

Artificial intelligence, lossless compression, medical image compression, neural network

Abstract

In this paper, feedforward neural network train with backpropagation algorithm is propose to compress grayscale medical images. In this new method, a three hidden layer feedforward network (FFN) is applied directly as the main compression algorithm to compress an MRI image. After training with sufficient sample images, the compression process will be carried out on the target image. The coupling weights and activation values of each neuron in the hidden layer will be stored after training. Compression is then achieved by using smaller number of hidden neurons as compared to the number of image pixels due to lesser information being stored. Experimental results show that the FFN is able to achieve comparable compression ratio of 1:36 at PSNR 35.89 dB as compared to JPEG2000 with compression ratio of 1:20 at PSNR 40 dB.

 

Downloads

Download data is not yet available.

Downloads

How to Cite

Yeo, W. K., Yap, F. W., Andito, D. P., & Suaidi, M. K. (2011). Grayscale Medical Image Compression Using Feedforward Neural Networks. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 3(1), 39–44. Retrieved from https://jtec.utem.edu.my/jtec/article/view/421

Issue

Section

Articles