Title :
Logical Labeling of Fixed Layout PDF Documents Using Multiple Contexts
Author :
Xin Tao ; Zhi Tang ; Canhui Xu ; Yongtao Wang
Author_Institution :
Inst. of Comput. Sci. & Technol., Peking Univ., Beijing, China
Abstract :
The task of logical structure recovery is known to be of crucial importance, yet remains unsolved not only for image based document but also for born-digital document system. In this work, the modeling of contextual information based on 2D Conditional Random Fields is proposed to learn page structure for born-digital fixed-layout documents. Heuristic prior knowledge of Portable Document Format (PDF) content and layout are interpreted to construct neighborhood graphs and various pair wise clique templates for the modeling of multiple contexts. By integrating local and contextual observations obtained from PDF attributes, the ambiguities of semantic labels are better resolved. Experimental comparisons for six types of clique templates has demonstrated the benefits of contextual information in logical labeling of 16 finely defined categories.
Keywords :
document image processing; graph theory; random processes; 2D conditional random field; PDF attribute; PDF content; PDF documents; PDF layout; born-digital document system; born-digital fixed-layout document; clique templates; contextual information; contextual observation; heuristic prior knowledge; image based document; local observation; logical labeling; logical structure recovery; neighborhood graphs; page structure; pairwise clique template; portable document format content; semantic label; Context; Context modeling; Labeling; Layout; Portable document format; Semantics; Text analysis; Conditional Random Fields; born-digital fixed-layout document; logical labeling;
Conference_Titel :
Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on
Conference_Location :
Tours
Print_ISBN :
978-1-4799-3243-6
DOI :
10.1109/DAS.2014.54
