Research on Colour and Texture Feature Based Image Retrieval

This paper focuses on the content-based image retrieval technique, and mainly from the perspective of image color, texture feature extraction and feature matching, explores: 1 using a variety of improved color histogram and gray level co-occurrence matrix based on the retrieval means, so as to lessen the shortage of information space of the traditional color feature extraction and to improve the efficiency of the retrieval system, 2 the relations between information of different feature, hence proposing the normalized algorithm of internal and external features to integrate different retrieval methods effectively.