2015 | OriginalPaper | Chapter
Improving Table of Contents Recognition Using Layout-Based Features
Authors : Phuc Tri Nguyen, Dang Tuan Nguyen
Published in: Knowledge and Systems Engineering
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Table of content (TOC) recognition is an essential task in processing book contents for document retrieval applications. Existing methods focus on exploiting characteristic information of TOC page formats on specific types of books. However, we observe that many other normal layout based features of pages can also identify the nature of pages (TOC pages or not). In this paper we propose using some selected layout-based features for improving TOC pages recognition. To show the effectiveness of our proposed method, we conduct experiments on ICDAR Book Structure Extraction Datasets 2009, 2011 and 2013, on which it improves the stateof- the-art performance of current approach focusing on TOC pages based features only.