An Experience in Image Compression Using Neural Networks

There are number trials of using neural networks as signal processing tools for image compression. In this paper, a direct solution method is used for image compression using the neural networks. An experience of using multilayer perceptron for image compression is presented. The multilayer perceptron is used for transform coding of the image. The network is trained for different number of hidden neurons with direct impact to compress ratio. It is experimented with different images that have been segmented in the blocks of various sizes for compression process. Reconstructed image is compared with original image using signal-to-noise ratio and number of bits per pixel. The results show the possibility of using multilayer perceptrons for image compression

[1]  J. Jiang,et al.  Image compression with neural networks - A survey , 1999, Signal Process. Image Commun..

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  L. E. Russo,et al.  Image compression using an outer product neural network , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Simone G. O. Fiori,et al.  Image compression using principal component neural networks , 2001, Image Vis. Comput..

[5]  Simon Haykin,et al.  Neural networks , 1994 .

[6]  Simon Haykin,et al.  Neural network approaches to image compression , 1995, Proc. IEEE.

[7]  De-Shuang Huang,et al.  Image compression using principal component neural network , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[8]  M. Arozullah,et al.  Image compression with a hierarchical neural network , 1996, IEEE Transactions on Aerospace and Electronic Systems.