Content-Based Image Retrieval Using Hybrid Micro-Structure Descriptor

Along with the speedy increase in the size of digital image collections, the content-based image retrieval (CBIR) has already become one of the hot topics in both image processing and computer vision. And it has been widely used in browsing, searching, and retrieving certain interested information from a huge amount of data. In this paper, we present a hybrid micro-structure descriptor (HMSD) to describe the image feature, which is used for image retrieval. This method makes a color quantization and edge orientation detection of the image in both HSV and RGB color space to extract four kinds of micro-structure and then hybrid these four via an effective way. The experimental results show that the information of images such as color, texture, shape, and color layout can be described more effectively by using this method and the accuracy of image retrieval is improved greatly than several well-known methods.