International Journal of Advanced Research in Computer and Communication Engineering

A monthly peer-reviewed online and print journal

ISSN Online 2278-1021
ISSN Print 2319-5940

Abstract: Genetic algorithm and neural system based strategies are intense technique for taking care of genuine issues and has been generally considered for its applications in territories of picture pressure. For picture based learning for neural system is experiencing condemnation of moderate union and low quality of pressure. Neural systems for tuning more often than not have a settled structure. The quantity of associations must be sufficiently huge to fit a given application. This may cause the neural system structure to be pointlessly intricate and increment the usage cost. The present work proposes a neural system with switches. By doing this, the proposed neural system can learn both the information yield connections of an application and the system structure. The trial results demonstrate that the method performed productively then the calculation variant without switches.

Keywords: Image Processing, Image Compression, Genetic Algorithm, Switches

PDF | DOI: 10.17148/IJARCCE.2018.782