Research On The Techniques For Color And Texture-Based Image Retrieval

With the rapid development of modern information technology, the number of digital images is growing rapidly. How to find the image data we need in the massive database is attracted by more and more people. Now the Content-Based Image Retrieval technique has been an important research subject.The main techniques of CBIR are discussed in this thesis. During the study of color features extraction and matching, HSV color model is chosen and divided into small spaces according to the perception of human eyes. The details of extracting HSV-based color histogram are described. In order to deal with the shortcoming of color histogram - it includes no spatial distribution information of the image, this thesis proposes a new content-based color image retrieval method, in which both the color and the spatial relationship of image are taken into account. The new method divides the image into blocks, which contain spatial information. Besides, the Laplace Operator is employed on the blocks' numbers to obtain the relative locations of blocks rather than the absolute locations of blocks, which ensures the property of distinguishing different images as well as the image's rotation invariant. In extracting the texture features, the thesis compresses the image, converts it to gray image and calculates four numerical features identifying the content of image by gray-level co-occurrence matrix of the image. In addition, the extracted texture features are used to retrieval more fine results on the basis of color and spatial features retrieval results.The above retrieval methods are programmed and realized by MATLAB. Experimental results shows that the proposed algorithm is effective and the new color-spatial based image retrieval algorithm has better performance than the normal color based image retrieval algorithm.