Abstract
This paper addresses the task of extracting the table of contents (TOC) from OCR-ed books. Since the OCR process misses a lot of layout and structural information, it is incapable of enabling navigation experience. A TOC is needed to provide a convenient and quick way to locate the content of interest. In this paper, we propose a hybrid method to extract TOC, which is composed of rule-based method and SVM-based method. The rule-based method mainly focuses on discovering the TOC from the books with TOC pages while the SVM-based method is employed to handle with the books without TOC pages. Experimental results indicate that the proposed methods obtain comparable performance against the other participants of the ICDAR 2011 Book structure extraction competition.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
