Title :
Resolution Enhancement from Document Images for Text Extraction
Author :
Li, Zhan ; Luo, Jiangao
Author_Institution :
Dept. of Comput. Sci., Jinan Univ., Guangzhou, China
Abstract :
Text extraction from low resolution document image sequences suffers from high error rate for most character recognition systems. To address this problem, an effective and efficient interpolation-based resolution enhancement algorithm is proposed and applied in this paper. Image registration and interpolation algorithms are discussed and specified. Further, based on a reliability measurement for pixels, a new iterative weighed average strategy for filling in holes after interpolation is introduced. Finally, comparisons with several other Resolution Enhancement (RE) algorithms are shown in experiments. The results show that definition of images is improved and recognition error rate is decreased.
Keywords :
character recognition; document image processing; error statistics; feature extraction; image recognition; image registration; image resolution; image sequences; interpolation; iterative methods; text analysis; visual databases; character recognition system; document image resolution enhancement; image interpolation algorithm; image recognition error rate; image registration; interpolation-based resolution enhancement algorithm; iterative weighed average strategy; low resolution document image sequence; reliability measurement; text extraction; Algorithm design and analysis; Error analysis; Image recognition; Image reconstruction; Image resolution; Interpolation; Optical character recognition software; document image sequence; optical character recognition; resolution enhancement; text extraction;
Conference_Titel :
Multimedia and Ubiquitous Engineering (MUE), 2011 5th FTRA International Conference on
Conference_Location :
Loutraki
Print_ISBN :
978-1-4577-1228-9
Electronic_ISBN :
978-0-7695-4470-0
DOI :
10.1109/MUE.2011.52
