Image compression using cascade of neural networks

Dimitrios Charalampidis; Chigozie Obiegbu

doi:10.1117/12.484830

Translator Disclaimer

8 August 2003 Image compression using cascade of neural networks

Dimitrios Charalampidis; Chigozie Obiegbu

Author Affiliations +

Proceedings Volume 5108, Visual Information Processing XII; (2003) https://doi.org/10.1117/12.484830
Event: AeroSense 2003, 2003, Orlando, Florida, United States

Abstract

This paper introduces a novel adaptive cascade architecture for image compression. The idea is an extension of parallel neural network (NN) architectures which have been previously used for image compression. It is shown that the proposed technique results in higher image quality for a given compression ratio than existing NN image compression schemes. It is also shown that training of the proposed architecture is significantly faster than that of other NN-based techniques and that the number of learning parameters is small. This allows the coding process to include adaptation of the learning parameters, thus, compression does not depend on the selection of the training set as in previous single and parallel structure NN.

Citation Download Citation

Dimitrios Charalampidis and Chigozie Obiegbu "Image compression using cascade of neural networks", Proc. SPIE 5108, Visual Information Processing XII, (8 August 2003); https://doi.org/10.1117/12.484830

ACCESS THE FULL ARTICLE