DocumentCode :
419542
Title :
Screen pattern removal for character pattern extraction from high-resolution color document images
Author :
Goto, Hideaki ; Aso, Hirotomo
Author_Institution :
Inf. Synergy Center, Tohoku Univ., Sendai, Japan
Volume :
1
fYear :
2004
fDate :
23-26 Aug. 2004
Firstpage :
490
Abstract :
Screen patterns used in offset-printing become visible or cause moire noise in the images if the documents are scanned at high resolution such as 400dpi or more. This has been an obstacle in developing document recognition systems which handle color documents. This paper proposes a new method for filtering screen patterns/noise in high-resolution color document images. The method utilizes a wavelet analysis for screen pattern detection. Experimental results show that our method can smear periodic screen patterns effectively preserving thin character strokes.
Keywords :
character recognition; document image processing; feature extraction; image colour analysis; image resolution; printing; wavelet transforms; character pattern extraction; color document images; document recognition systems; high resolution images; moire noise; offset printing; screen pattern detection; screen pattern filtering; screen pattern removal; thin character strokes preservation; wavelet analysis; Color; Colored noise; Filtering; Image resolution; Image segmentation; Ink; Optical character recognition software; Pattern analysis; Smoothing methods; Wavelet analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN :
1051-4651
Print_ISBN :
0-7695-2128-2
Type :
conf
DOI :
10.1109/ICPR.2004.1334173
Filename :
1334173
Link To Document :
بازگشت