An Improved Algorithm Based on Color Feature Extraction for Image Retrieval
Li Mengzhe, Jiang Xiuhua · 2016
With the rapid development of computer vision and digital technology, producing the vast amounts of image data, how to realize a rapid, easy and high effective algorithm of image retrieval has been the issue of study, just so the main goal of this paper is to implement an effective improved algorithm based on color feature. There are two main types of algorithm based on color feature: global algorithm and local color algorithm, including RGB, HSV color space and so on. This improved algorithm fully considers the global and local color information, fusing the fuzzy color histogram and block color histogram, decreasing the color feature dimension. This paper compares uniform HSV histogram, non-uniform quantization HSV histogram, fuzzy HSV histogram, block color moment, the improved color feature in image database COREL1000. According to the analysis of experiment results based on the precision of first N terms, the improved algorithm has the best retrieval accuracy and low feature dimension.