Recently, a Genetic Accelerated K-Means Algorithm (GAKM) was proposed as an approach for optimizing Vector Quantization (VQ) codebooks, relying on an accelerated version of K-Means algorithm as a new local learning module. This approach requires the determination of a scale factor parameter (η), which affects the local search performed by GAKM. The problem of auto-adapting the local search in GAKM, by adjusting the q parameter, is addressed in this work by the proposal of a Terrain-Based Memetic Algorithm (TBMA), derived from existing spatially distributed evolutionary models. Simulation results regarding image VQ show that this new approach is able to adjust the scale factor (η) for different images at distinct coding rates, leading to better Peak Signal-to-Noise Ratio values for the reconstructed images when compared to both K-Means and Cellular Genetic Algorithm + K-Means. The TBMA also demonstrates capability of tuning the mutation rate throughout the genetic search.
展开▼
