Detection and segmentation of touching characters in mathematical
expressions
A. Nomura, K. Michishita, S. Uchida, and M. Suzuki. Proceedings of the Seventh International Conference on Document Analysis
and Recognition, (ICDAR2003), 1, page 126--130. ieeeaddr, ieee, (August 2003)
Abstract
A technique for the detection and the segmentation of touching characters
in mathematical expressions is presented. In the detection stage,
a connected component initially recognized into some category is
judged as a candidate of touched characters if its feature values
deviate from the standard feature values of the category. In the
segmentation stage, two component characters of the candidate are
decided by the comparison with touching character images synthesized
from two single character images. Experimental results showed the
effectiveness on the accuracy improvement of the recognition of mathematical
expressions.
%0 Conference Paper
%1 Nomura2003
%A Nomura, A.
%A Michishita, K.
%A Uchida, S.
%A Suzuki, M.
%B Proceedings of the Seventh International Conference on Document Analysis
and Recognition, (ICDAR2003)
%C ieeeaddr
%D 2003
%E Antonacopoulos, Apostolos
%I ieee
%K , character detection, document edge expressions, image image, mathematical processing, recognition, segmentation touching
%P 126--130
%T Detection and segmentation of touching characters in mathematical
expressions
%U http://www.cse.salford.ac.uk/prima/ICDAR2003/Papers/0022_700_uchida_s.pdf
%V 1
%X A technique for the detection and the segmentation of touching characters
in mathematical expressions is presented. In the detection stage,
a connected component initially recognized into some category is
judged as a candidate of touched characters if its feature values
deviate from the standard feature values of the category. In the
segmentation stage, two component characters of the candidate are
decided by the comparison with touching character images synthesized
from two single character images. Experimental results showed the
effectiveness on the accuracy improvement of the recognition of mathematical
expressions.
%@ 0-7695-1960-1
@inproceedings{Nomura2003,
abstract = {A technique for the detection and the segmentation of touching characters
in mathematical expressions is presented. In the detection stage,
a connected component initially recognized into some category is
judged as a candidate of touched characters if its feature values
deviate from the standard feature values of the category. In the
segmentation stage, two component characters of the candidate are
decided by the comparison with touching character images synthesized
from two single character images. Experimental results showed the
effectiveness on the accuracy improvement of the recognition of mathematical
expressions.},
added-at = {2011-03-27T19:35:34.000+0200},
address = {ieeeaddr},
author = {Nomura, A. and Michishita, K. and Uchida, S. and Suzuki, M.},
biburl = {https://www.bibsonomy.org/bibtex/249857c0a7589f732d19045de0692471e/cocus},
booktitle = {Proceedings of the Seventh International Conference on Document Analysis
and Recognition, (ICDAR2003)},
booktitleaddon = {3--6 August 2003},
editor = {Antonacopoulos, Apostolos},
file = {:./0022_700_uchida_s.pdf:PDF},
interhash = {72b84b747cc325a10c269e4a8e05019d},
intrahash = {49857c0a7589f732d19045de0692471e},
isbn = {0-7695-1960-1},
keywords = {, character detection, document edge expressions, image image, mathematical processing, recognition, segmentation touching},
month = aug,
owner = {CK},
pages = {126--130},
publisher = {ieee},
timestamp = {2011-03-27T19:35:42.000+0200},
title = {Detection and segmentation of touching characters in mathematical
expressions},
url = {http://www.cse.salford.ac.uk/prima/ICDAR2003/Papers/0022_700_uchida_s.pdf},
urldate = {2008.11.04},
venue = {Edinburgh, Scotland},
volume = 1,
year = 2003
}