Optimization of Gabor Wavelet Correlogram Quantization Thresholds Using

Friday, 21 October 2011 11:00 administrator
Print PDF
Abstract— Now a day’s digital libraries are increased drastically over the past decade, retrieval of images based on content, often referred as CBIR has gained a lot of research interests. The Gabor Wavelet Correlogram (GWC) method is based on a combination of multi-resolution image decomposition and color correlation histogram. According to GWC algorithm, Gabor wavelet coefficients of the image are computed using a directional Gabor wavelets transform. A quantization step is then applied before computing one-directional Auto-Correlogram of the Gabor wavelet coefficients. Finally, index vectors are constructed using this one-directional Gabor Wavelet Correlogram. The quantization step is more important for Gabor Wavelet Correlogram based image indexing and retrieval. A novel evolutionary method called Evolutionary Group Algorithm (EGA) is proposed in [1] for complicated time-consuming optimization problems such as finding optimal parameters of content-based image indexing algorithms. In the new evolutionary algorithm, the image database is partitioned into several smaller subsets, and each subset is used by an updating process as training patterns for each chromosome during evolution. This is in contrast to Genetic Algorithms that use the whole database as training patterns for evolution. The optimal quantization thresholds computed by EGA improved significantly all the evaluation measures including average precision and average recall for the Gabor Wavelet Correlogram method.