Title :
A Chinese Document Layout Analysis Based on Non-text Images
Author :
Xiaoling, Fu ; Xiaofeng, Li
Author_Institution :
Multimedia Technol. Lab., North China Univ. of Inf. Eng. (NCUT), Beijing, China
Abstract :
With the paper as the medium of electronic information, traditional books, magazines, newspapers, etc are scanned into the images, and changed into electronic documents through OCR (optical character recognition) technology, layout analysis as an important part of OCR has played a greater role. This paper presents a Chinese document layout analysis based on non-text images, solve the deformed image of the issue of text extraction, and there is great value in practice.
Keywords :
document image processing; optical character recognition; Chinese document layout; OCR; document layout analysis; electronic documents; nontext images; optical character recognition; text extraction; Algorithm design and analysis; Character recognition; Computer applications; Flowcharts; Image analysis; Image reconstruction; Information analysis; Optical character recognition software; Pixel; Text analysis; connective region; layout analysis; projection; threshold;
Conference_Titel :
Computer Science-Technology and Applications, 2009. IFCSTA '09. International Forum on
Conference_Location :
Chongqing
Print_ISBN :
978-0-7695-3930-0
Electronic_ISBN :
978-1-4244-5423-5
DOI :
10.1109/IFCSTA.2009.85
