Title :
Multi-window binarization of camera image for document recognition
Author_Institution :
Inzisoft Co. Ltd., South Korea
Abstract :
This paper proposes an adaptive binarization method for the document image acquired by camera. By applying multiple windows vary in size, it determines the local thresholds with the information from the global trend as well as the local detail. As the consequence, the proposed method is good at not only preserving fine detail of the character structure but also absorbing noise. The effectiveness of the proposed method was shown by the experiment.
Keywords :
cameras; document image processing; image recognition; adaptive binarization method; camera image; document image recognition; multiwindow binarization; Brightness; Cameras; Focusing; Image analysis; Image recognition; Lenses; Text analysis; adaptive binarization; camera image;
Conference_Titel :
Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on
Print_ISBN :
0-7695-2187-8
DOI :
10.1109/IWFHR.2004.70