Title :
Local Contrast Segmentation to Binarize Images
Author :
Block, Marco ; Rojas, RaÙl
Author_Institution :
Inst. fur Inf., Freie Univ. Berlin, Berlin
Abstract :
In this paper, a new binarization algorithm for degraded document images is proposed. The method is based on positive and negative pixel energies using the Laplacian of an image. After a filtering step and morphological operations our local contrast segmentation method is able to detecting connected components. The given approach is applied to cases of sophisticated, challenging documents and other application scenarios like whiteboard and chalk images.
Keywords :
document image processing; image segmentation; optical character recognition; binarization algorithm; binarize images; chalk images; degraded document images; filtering step; local contrast segmentation; morphological operations; negative pixel energy; positive pixel energy; whiteboard; Degradation; Filtering; Image processing; Image segmentation; Laplace equations; Lighting; Morphological operations; Optical character recognition software; Pixel; Shape; binarization; contrast; text;
Conference_Titel :
Digital Society, 2009. ICDS '09. Third International Conference on
Conference_Location :
Cancun
Print_ISBN :
978-1-4244-3550-6
Electronic_ISBN :
978-0-7695-3526-5
DOI :
10.1109/ICDS.2009.45
