Advanced

Core Points - a framework for structural parameterization

Sternby, Jakob LU and Ericsson, Anders LU (2005) International Conference on Document Analysis and Recognition, ICDAR'05 In Eighth International Conference on Document Analysis and Recognition, ICDAR'05 1. p.217-221
Abstract
Most implementations of single character recognition use standard arclength parameterization of the handwritten samples. A problem with the arclength approach is that points on curves of different samples from one character class may then actually correspond to parts of different structural significance. Many methods such as DTW and HMM have been successful partly because they are less sensitive to parameterizational differences. Given a sufficiently fine decomposition of a character sample into smaller segments, the complex non-linear variations of handwritten data can be viewed as a set of local linear transformations of the segments. In this paper we present a parameterization technique that implicitly defines such a structural... (More)
Most implementations of single character recognition use standard arclength parameterization of the handwritten samples. A problem with the arclength approach is that points on curves of different samples from one character class may then actually correspond to parts of different structural significance. Many methods such as DTW and HMM have been successful partly because they are less sensitive to parameterizational differences. Given a sufficiently fine decomposition of a character sample into smaller segments, the complex non-linear variations of handwritten data can be viewed as a set of local linear transformations of the segments. In this paper we present a parameterization technique that implicitly defines such a structural decomposition. Experiments reveal that recognition rates for kNN template matching increase for reparameterized samples thus proving that the new parameterization removes redundance in a way that is genuinely beneficial for discrimination purposes. In addition to these quantitive results, visual inspection of the modes of singular value decomposition of reparameterized samples show that the new parameterization reduces the impact of parameterizational differences in shape variations of character samples. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Eighth International Conference on Document Analysis and Recognition, ICDAR'05
volume
1
pages
217 - 221
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
International Conference on Document Analysis and Recognition, ICDAR'05
external identifiers
  • WOS:000232022600043
  • Scopus:33947422109
ISBN
0-7695-2420-6
DOI
10.1109/ICDAR.2005.116
language
English
LU publication?
yes
id
bfa7727d-048e-44d4-b58a-0add1f765bd6 (old id 787627)
alternative location
http://www.maths.lth.se/matematiklth/personal/anderse/publications.html
date added to LUP
2008-01-15 08:25:01
date last changed
2017-01-01 08:02:27
@inproceedings{bfa7727d-048e-44d4-b58a-0add1f765bd6,
  abstract     = {Most implementations of single character recognition use standard arclength parameterization of the handwritten samples. A problem with the arclength approach is that points on curves of different samples from one character class may then actually correspond to parts of different structural significance. Many methods such as DTW and HMM have been successful partly because they are less sensitive to parameterizational differences. Given a sufficiently fine decomposition of a character sample into smaller segments, the complex non-linear variations of handwritten data can be viewed as a set of local linear transformations of the segments. In this paper we present a parameterization technique that implicitly defines such a structural decomposition. Experiments reveal that recognition rates for kNN template matching increase for reparameterized samples thus proving that the new parameterization removes redundance in a way that is genuinely beneficial for discrimination purposes. In addition to these quantitive results, visual inspection of the modes of singular value decomposition of reparameterized samples show that the new parameterization reduces the impact of parameterizational differences in shape variations of character samples.},
  author       = {Sternby, Jakob and Ericsson, Anders},
  booktitle    = {Eighth International Conference on Document Analysis and Recognition, ICDAR'05},
  isbn         = {0-7695-2420-6},
  language     = {eng},
  pages        = {217--221},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Core Points - a framework for structural parameterization},
  url          = {http://dx.doi.org/10.1109/ICDAR.2005.116},
  volume       = {1},
  year         = {2005},
}