Image compression using a neural network with learning capability of variable function of a neural unit

Ryuji Kohno; Mitsuru Arai; Hideki Imai

doi:10.1117/12.24107

Translator Disclaimer

1 September 1990 Image compression using a neural network with learning capability of variable function of a neural unit

Ryuji Kohno, Mitsuru Arai, Hideki Imai

Author Affiliations +

Proceedings Volume 1360, Visual Communications and Image Processing '90: Fifth in a Series; (1990) https://doi.org/10.1117/12.24107
Event: Visual Communications and Image Processing '90, 1990, Lausanne, Switzerland

Abstract

This paper proposes image compression using an advanced neural network in which a variable input-output function of a neural unit can be learnt as well as a weight coefficient of a neural connection corresponding to information source and application. Since the neural network has the improved learning capability for local nonlinearity of information source, its application to compression of nonlinear information such as image is investigated. A learning algorithm and adaptive controlling schemes of input-output functions are derived. Simulation results show that the neural network can achieve higher SNR and shorter learning time than a conventional network having only variable weights.

Citation Download Citation

Ryuji Kohno, Mitsuru Arai, and Hideki Imai "Image compression using a neural network with learning capability of variable function of a neural unit", Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); https://doi.org/10.1117/12.24107

ACCESS THE FULL ARTICLE