Digital Bleaching and Content Extraction for the Digital Archive of Rare Books

Asanobu KITAMOTO
Tomohiro IKEZAKI
 Dominique DEUFF
 Eka MEYER
 Sonoko SATO
 Takako MURAMATSU
 Ryo KAMIDA
 Takeo YAMAMOTO
 Kinji ONO

This paper reports our experience with the digitization project
 "Digital Archive of Toyo Bunko Rare Books." The mission of this project is to make rare books accessible to the public through our Website. This paper describes the image analysis aspect of this project from the viewpoint of digitization workflow
 starting from image capture to Website architecture. The uniqueness of this paper is in two-fold
 digital bleaching and content extraction. Digital bleaching is a kind of image enhancement method with the aim of improving the readability of text for both humans and machines. Then textual content and graphical content is extracted automatically from the image
 and applied indexing methods for searching. Our digital archive contains 53 books and about 14
000 pages
 all of which are accessible on the Website http://dsr.nii.ac.jp/toyobunko/.

Proceedings of the 2nd International Conference on Document Image Analysis for Libraries (DIAL)