Title :
A study of document format identification based on table structure
Author :
Matsunaga, Tsutomu ; Tokumasu, Atsumi ; Iwaki, Osamu
Author_Institution :
NTT Data Commun. Syst. Corp., Kanagawa, Japan
Abstract :
A method to identify formatted documents through table structure is described. This method extracts connected components of white pixels in documents for identification, using a subspace classification method. The effectiveness of this method is discussed. The authors focus on the discriminant functions of this classification and consider the applicability of the method for practical use
Keywords :
computerised pattern recognition; discriminant functions; document format identification; subspace classification; table structure; white pixels; Euclidean distance; Independent component analysis; Pattern recognition; Quantization; Robustness; Strips; Testing;
Conference_Titel :
Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on
Conference_Location :
Cambridge, MA
DOI :
10.1109/ICSMC.1989.71413
