Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions

Fang SUN; Shin'ichiro OMACHI; Hirotomo ASO

Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions

Fang SUN, Shin'ichiro OMACHI, Hirotomo ASO

Full Text Views

0

Share
Cite this

Summary :

In this paper, a new algorithm for selection of candidates for handwritten character recognition is presented. Since we adopt the concept of the marginal radius to examine the confidence of candidates, the evaluation function is required to describe the pattern distribution correctly. For this reason, we propose Simplified Mahalanobis distance and observe its behavior by simulation. In the proposed algorithm, first, for each character, two types of feature regions (multi-dimensional one and one-dimensional one) are estimated from training samples statistically. Then, by referring to the feature regions, candidates are selected and verified. Using two types of feature regions is a principal characteristic of our method. If parameters are estimated accurately, the multi-dimensional feature region is extremely effective for character recognition. But generally, estimation errors in parameters occur, especially with a small number of sample patterns. Although the recognition ability of one-dimensional feature region is not so high, it can express the distribution comparatively precisely in one-dimensional space. By combining these feature regions, they will work concurrently to overcome the defects of each other. The effectiveness of the method is shown with the results of experiments.

Publication: IEICE TRANSACTIONS on Information Vol.E79-D No.5 pp.510-515

Publication Date: 1996/05/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Character Recognition and Document Understanding)

Category: Handwritten Character Recognition

Cite this

Copy

Fang SUN, Shin'ichiro OMACHI, Hirotomo ASO, "Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions" in IEICE TRANSACTIONS on Information, vol. E79-D, no. 5, pp. 510-515, May 1996, doi: .
Abstract: In this paper, a new algorithm for selection of candidates for handwritten character recognition is presented. Since we adopt the concept of the marginal radius to examine the confidence of candidates, the evaluation function is required to describe the pattern distribution correctly. For this reason, we propose Simplified Mahalanobis distance and observe its behavior by simulation. In the proposed algorithm, first, for each character, two types of feature regions (multi-dimensional one and one-dimensional one) are estimated from training samples statistically. Then, by referring to the feature regions, candidates are selected and verified. Using two types of feature regions is a principal characteristic of our method. If parameters are estimated accurately, the multi-dimensional feature region is extremely effective for character recognition. But generally, estimation errors in parameters occur, especially with a small number of sample patterns. Although the recognition ability of one-dimensional feature region is not so high, it can express the distribution comparatively precisely in one-dimensional space. By combining these feature regions, they will work concurrently to overcome the defects of each other. The effectiveness of the method is shown with the results of experiments.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e79-d_5_510/_p

Copy

@ARTICLE{e79-d_5_510,
author={Fang SUN, Shin'ichiro OMACHI, Hirotomo ASO, },
journal={IEICE TRANSACTIONS on Information},
title={Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions},
year={1996},
volume={E79-D},
number={5},
pages={510-515},
abstract={In this paper, a new algorithm for selection of candidates for handwritten character recognition is presented. Since we adopt the concept of the marginal radius to examine the confidence of candidates, the evaluation function is required to describe the pattern distribution correctly. For this reason, we propose Simplified Mahalanobis distance and observe its behavior by simulation. In the proposed algorithm, first, for each character, two types of feature regions (multi-dimensional one and one-dimensional one) are estimated from training samples statistically. Then, by referring to the feature regions, candidates are selected and verified. Using two types of feature regions is a principal characteristic of our method. If parameters are estimated accurately, the multi-dimensional feature region is extremely effective for character recognition. But generally, estimation errors in parameters occur, especially with a small number of sample patterns. Although the recognition ability of one-dimensional feature region is not so high, it can express the distribution comparatively precisely in one-dimensional space. By combining these feature regions, they will work concurrently to overcome the defects of each other. The effectiveness of the method is shown with the results of experiments.},
keywords={},
doi={},
ISSN={},
month={May},}

Copy

TY - JOUR
TI - Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions
T2 - IEICE TRANSACTIONS on Information
SP - 510
EP - 515
AU - Fang SUN
AU - Shin'ichiro OMACHI
AU - Hirotomo ASO
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E79-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 1996
AB - In this paper, a new algorithm for selection of candidates for handwritten character recognition is presented. Since we adopt the concept of the marginal radius to examine the confidence of candidates, the evaluation function is required to describe the pattern distribution correctly. For this reason, we propose Simplified Mahalanobis distance and observe its behavior by simulation. In the proposed algorithm, first, for each character, two types of feature regions (multi-dimensional one and one-dimensional one) are estimated from training samples statistically. Then, by referring to the feature regions, candidates are selected and verified. Using two types of feature regions is a principal characteristic of our method. If parameters are estimated accurately, the multi-dimensional feature region is extremely effective for character recognition. But generally, estimation errors in parameters occur, especially with a small number of sample patterns. Although the recognition ability of one-dimensional feature region is not so high, it can express the distribution comparatively precisely in one-dimensional space. By combining these feature regions, they will work concurrently to overcome the defects of each other. The effectiveness of the method is shown with the results of experiments.
ER -