Evolutionary computation using reinforced learning on image compression

  • Authors:
  • Sadaf Sajjad;Sajjad Mohsin

  • Affiliations:
  • COMSATS Institute of Information Technology, Department of Management Sciences, Islamabad, Pakistan;COMSATS Institute of Information Technology, Department of Computer Science, Islamabad, Pakistan

  • Venue:
  • SSIP'08 Proceedings of the 8th conference on Signal, Speech and image processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The present work is based on using the reinforced learning technique on evolutionary computation for compressing an image. We have reinforced the best code vectors for a codebook in vector quantization, and kept them alive for the next generation until we got the best image. A genetic algorithm model was designed using reinforced learning with the pairwise nearest neighbor approach (PNN). The proposed method was evaluated with respect to quality of compressed image by calculating Peak Signal to Noise Ratio (PSNR). We used Lena image for our experiments and the PSNR value for proposed method is 34.6.