Detail of Publication

Text Language Japanese Masakazu Iwamura, Kazuya Negishi, Shinichiro Omachi, and Hirotomo Aso Isolated Character Recognition by Searching Feature Points and Voting Proceedings of MIRU 2005 pp.559-566 Not reviewed July 2005 To utilize a character information in scene images, character recognition and segmentation are required. Character segmentation is essential preliminary of character recognition. However, most character segmentation methods cannot extract {\it isolated characters} which do not constitute a character string, characters in a complex equation, touching characters where two characters are connected and so on. Therefore, they cannot be recognized. In this paper, to utilize information of such characters, we propose a novel recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. The proposed method generalizes the conventional character recognition for character images segmented correctly to one for {\it unsegmented} character images. In experiments, the proposed method extracted isolated characters in the face of a clock and touching characters well even if the fonts of a reference image and a target one were different.
• Following file is available.
• Entry for BibTeX
@InCollection{Iwamura2005,
author =	{Masakazu Iwamura and Kazuya Negishi and Shinichiro Omachi and Hirotomo Aso},
title =	{Isolated Character Recognition by Searching Feature Points and Voting},
booktitle =	{Proceedings of MIRU 2005},
year =	2005,
month =	jul,
pages =	{559--566}
}


Back to list