An Evolutionary Approach for Vector Quantization Codebook Optimization

Authors:
Carlos R. Azevedo;Esdras L. Bispo, Jr.;Tiago A. Ferreira;Francisco Madeiro;Marcelo S. Alencar
Affiliations:
Center for Science and Technology, Catholic University of Pernambuco, Brazil;Center for Science and Technology, Catholic University of Pernambuco, Brazil;Department of Statistics and Informatics, Federal Rural University of Pernambuco,;Center for Science and Technology, Catholic University of Pernambuco, Brazil;Department of Electrical Engineering, Federal University of Campina Grande,
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Year:
2008

Citing 6
Cited 0

Vector quantization and signal compression

Vector quantization and signal compression
Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Genetic algorithm with deterministic crossover for vector quantization

Pattern Recognition Letters
On Replacement Strategies in Steady State Evolutionary Algorithms

Evolutionary Computation
Genetic K-means algorithm

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Tuning of the structure and parameters of a neural network using an improved genetic algorithm

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a hybrid evolutionary algorithm based on an accelerated version of K-means integrated with a modified genetic algorithm (GA) for vector quantization (VQ) codebook optimization. From simulation results involving image compression based on VQ, it is observed that the proposed method leads to better codebooks when compared with the conventional one (GA + standard K-means), in the sense that the former leads to higher peak signal-to-noise ratio (PSNR) results for the reconstructed images. Additionally, it is observed that the proposed method requires fewer GA generations (up to 40%) to achieve the best PSNR results produced by the conventional method.