Image retrieval based on 72-trees and genetic algorithm

Color, texture and shape information have been the primitive image descriptors in content based image retrieval systems. However, how to quickly retrieving images is a challenge because that the speed and efficiency of retrieving image from Internet image is most important. We used genetic algorithm to improve the method based on HSV color space, and optimized the computational workload. First, the paper introduces how to extract dominant color of an image based on HSV color space. Then, it describes how to use genetic algorithm to optimize the algorithm of extracting dominant color. In the end, genetic algorithm is be used for the similarity measure of images. The experiments and results, which based on Corel database, showed that this method has greatly improved the image retrieval in time and precision rates.