DocumentCode :
3031628
Title :
Layout recognition of multi-page document based on Naive Bayes
Author :
Zhu, Lvxing ; Chen, YouGuang ; Zhu, Min
Author_Institution :
Comput. Center, East China Normal Univ., Shanghai, China
fYear :
2011
fDate :
26-28 July 2011
Firstpage :
568
Lastpage :
571
Abstract :
A layout recognition method for multi-page document image is proposed in this paper.Because there exists of spacings in vertical and horizontal direction in this kind of document, vertical and horizontal projection are used to extract the layout feature and Naive Bayes classifier is generated to realize the layout recognition of multi-page document. Experimental results show that the method of this paper has higher accuracy and efficiency,and has practicality and value to some extent.
Keywords :
Bayes methods; document image processing; feature extraction; image recognition; Naive Bayes classifier; horizontal direction; layout feature extraction; layout recognition method; multipage document image; vertical direction; Accuracy; Classification algorithms; Feature extraction; Image recognition; Layout; Support vector machine classification; Training; Naive Bayes classification; feature extraction; image preprocessing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
Type :
conf
DOI :
10.1109/ICMT.2011.6002154
Filename :
6002154
Link To Document :
بازگشت