Extraction of bibliography information based on image of book cover

This paper describes a new system for extracting and classifying bibliograp hy regions from the color image of a book cover. The system consists of thr ee major components: preprocessing, color space segmentation and text regio n extraction and classification. Preprocessing extracts the edge lines of the book and geometrically correct s and segments the input image, into the parts of front cover, spine and ba ck cover. The same as all color image processing researches, the segmentation of colo r space is an essential and important step here. Instead of RGB color space , HSI color space is used in this system. The color space is segmented into achromatic and chromatic regions first; and both the achromatic and chroma tic regions are segmented further to complete the color space segmentation. Then text region extraction and classification follow. After detecting fund amental features (stroke width and local label width) text regions are dete rmined. By comparing the text regions on front cover with those on spine, a ll extracted text regions are classified into suitable bibliography categor ies: author, title, publisher and other information, without applying OCR.