Title :
Line Removal and Restoration of Handwritten Strokes
Author :
Arvind, K.R. ; Kumar, Jayant ; Ramakrishnan, A.G.
Author_Institution :
Indian Inst. of Sci., Bangalore
Abstract :
In document images, we often find printed lines over-lapping with hand written elements especially in case of signatures. Typical examples of such images are bank cheques and payment slips. Although the detection and removal of the horizontal lines has been addressed, the restoration of the handwritten area after removal of lines, persists to be a problem of interest. In this paper, we propose a method for line removal and restoration of the erased areas of the handwritten elements. Subjective evaluation of the results have been conducted to analyze the effectiveness of the proposed method. The results are promising with an accuracy of 86.33%. The entire process takes less than half a second for completion on a 2.4 GHz 512 MB RAM Pentium IV PC for a document image.
Keywords :
document image processing; image restoration; document images; handwritten strokes restoration; line removal; lines over-lapping; Computational intelligence; Handwriting recognition; Image analysis; Image recognition; Image reconstruction; Image restoration; Image segmentation; Noise level; Shape; Text analysis;
Conference_Titel :
Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on
Conference_Location :
Sivakasi, Tamil Nadu
Print_ISBN :
0-7695-3050-8
DOI :
10.1109/ICCIMA.2007.306