Image Compression Using Neural Networks

In this project, multilayer neural network will be employed to achieve image compression. The network parameters will be adjusted using different learning rules for comparison purposes. Mainly, the input pixels will be used as target values so that assigned mean square error can be obtained, and then the hidden layer output will be the compressed image. It was noticed that selection between learning algorithms is important as a result of big variations among them with respect to convergence time and accuracy of results.

[1]  H. Nait Charif,et al.  Neural networks-based image compression system , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[2]  S. Patnaik,et al.  Image compression using auto-associative neural network and embedded zero-tree coding , 2001, 2001 IEEE Third Workshop on Signal Processing Advances in Wireless Communications (SPAWC'01). Workshop Proceedings (Cat. No.01EX471).

[3]  O. Abdel-Wahhab,et al.  Image compression using multilayer neural networks , 1997 .

[4]  E. Watanabe,et al.  Lossy image compression using a modular structured neural network , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

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

[6]  Cheng-Chang Lu,et al.  A neural network based image compression system , 1992 .

[7]  Abdesselam Bouzerdoum.  Image compression using a stochastic competitive learning algorithm (SCoLA) , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).