Image Retrieving System Research Based On Content Characteristic

Content-based image retrieval (CBIR) has been an active research area in recent years. The use of digital image brings all kind of image database. The image retrieving from database tables and the management of image database has become a urgent research area, the task of this research is to index, retrieve, administer images automatically and intelligently, on this basis, the user of CBIR system can retrieve images easily, quickly and accurately, and the manager of CBIR system can manage the system without a lot of tedious manual work.This thesis presents a practical image retrieving system based on color and texture characteristic. In CBIR system, the histograms of extracting characteristic and matching image are important. On this basis, the color characteristic in this system we extract is: a 72 bit vector of one dimension by statistical color histogram in HSV space; a set of color average of sub-images and a set of position of sub-images by dividing the original image and using statistic information of pixels' color; a set of representative color of an image using a suitable cluster algorithm in the HSL space. In extracting texture characteristic, to cut down the amount of calculation, we compress the image and convert it to gray image. On this basis, the four numerical features identifying the content of image are raised from gray-level co-occurrence matrix of the image.Finally, we evaluate the retrieving result. Practicality of the system will be proved through experiments.