Image retrieval based on YCbCr color histogram

摘要

How to quickly retrieval the image is a very action research topic in the research of image retrieval based on Internet because of the large amount of data required by images. We propose a novel image indexing method based on YCbCr color space and design a system to improve retrieval efficiency. The main focus of this study is dimensionality reduction and image index of Web image. First, the paper presents the commonly used methods for image retrieval. Then, it describes how to convert from RGB color space to YCbCr color space, and how to extract 4096- dimensional feature of image based on YCbCr color space. In the end, the method about 4096-trees for image index is discussed. The experiments and results, which based on Corel database, showed that this method has greatly improved the image retrieval in time and precision rates.