Advanced

Frame Deformation Energy Matching of On-line Handwritten Characters

Sternby, Jakob LU (2005) 10th Iberoamerican Congress on Pattern Recognition, 2005 3773. p.128-137
Abstract
The coarse to fine search methodology is frequently applied to a wide variety of problems in computer vision. In this paper it is shown that this strategy can be used to enhance the recognition of on-line handwritten characters. Some explicit knowledge about the structure of a handwritten character can be obtained through a structural parameterization. The Frame Deformation Energy matching (FDE) method is a method optimized to include such knowledge in the discrimination process. This paper presents a novel parameterization strategy, the Djikstra Curve Maximization (DCM) method, for the segments of the structural frame. Since this method distributes points unevenly on each segment, point-to-point matching strategies are not suitable. A new... (More)
The coarse to fine search methodology is frequently applied to a wide variety of problems in computer vision. In this paper it is shown that this strategy can be used to enhance the recognition of on-line handwritten characters. Some explicit knowledge about the structure of a handwritten character can be obtained through a structural parameterization. The Frame Deformation Energy matching (FDE) method is a method optimized to include such knowledge in the discrimination process. This paper presents a novel parameterization strategy, the Djikstra Curve Maximization (DCM) method, for the segments of the structural frame. Since this method distributes points unevenly on each segment, point-to-point matching strategies are not suitable. A new distance measure for these segment-to-segment comparisons have been developed. Experiments have been conducted with various settings for the new FDE on a large data set both with a single model matching scheme and with a kNN type template matching scheme. The results reveal that the FDE even in an ad hoc implementation is a robust matching method with recognition results well comparing to the existing state-of-the-art methods. (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
host publication
Progress in Pattern Recognition, Image Analysis and Applications (Lecture Notes in Computer Science)
editor
Sanfeliu, Alberto and Cortés, Manuel Lazo
volume
3773
pages
128 - 137
publisher
Springer
conference name
10th Iberoamerican Congress on Pattern Recognition, 2005
conference location
Havanna, Cuba
conference dates
2005-11-15 - 2005-11-18
external identifiers
  • wos:000234341500014
  • scopus:33745407883
ISSN
1611-3349
0302-9743
ISBN
978-3-540-29850-2
DOI
10.1007/11578079
language
English
LU publication?
yes
id
8f6ecfce-65a5-4286-b640-4d6fbf5e660b (old id 787847)
date added to LUP
2016-04-01 11:58:12
date last changed
2021-03-09 05:24:45
@inproceedings{8f6ecfce-65a5-4286-b640-4d6fbf5e660b,
  abstract     = {The coarse to fine search methodology is frequently applied to a wide variety of problems in computer vision. In this paper it is shown that this strategy can be used to enhance the recognition of on-line handwritten characters. Some explicit knowledge about the structure of a handwritten character can be obtained through a structural parameterization. The Frame Deformation Energy matching (FDE) method is a method optimized to include such knowledge in the discrimination process. This paper presents a novel parameterization strategy, the Djikstra Curve Maximization (DCM) method, for the segments of the structural frame. Since this method distributes points unevenly on each segment, point-to-point matching strategies are not suitable. A new distance measure for these segment-to-segment comparisons have been developed. Experiments have been conducted with various settings for the new FDE on a large data set both with a single model matching scheme and with a kNN type template matching scheme. The results reveal that the FDE even in an ad hoc implementation is a robust matching method with recognition results well comparing to the existing state-of-the-art methods.},
  author       = {Sternby, Jakob},
  booktitle    = {Progress in Pattern Recognition, Image Analysis and Applications (Lecture Notes in Computer Science)},
  editor       = {Sanfeliu, Alberto and Cortés, Manuel Lazo},
  isbn         = {978-3-540-29850-2},
  issn         = {1611-3349},
  language     = {eng},
  pages        = {128--137},
  publisher    = {Springer},
  title        = {Frame Deformation Energy Matching of On-line Handwritten Characters},
  url          = {http://dx.doi.org/10.1007/11578079},
  doi          = {10.1007/11578079},
  volume       = {3773},
  year         = {2005},
}