A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words

Fumitaka KIMURA; Shinji TSURUOKA; Yasuji MIYAKE; Malayappan SHRIDHAR

A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words

Fumitaka KIMURA, Shinji TSURUOKA, Yasuji MIYAKE, Malayappan SHRIDHAR

Full Text Views

0

Cite this

Summary :

In this paper, authors discuss on a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces. The procedure consists of binarization, presegmentation, intermediate feature extraction, segmentation recognition, and post-processing. The segmentation recognition and the post-processing are repeated for all lexicon words while the binarization to the intermediate feature extraction are applied once for an input word. This algorithm is essentially non hierarchical in character segmentation and recognition which are performed in a single segmentation recognition process. The result of performance evaluation using large handwritten address block database, and algorithm improvements are described and discussed to achieve higher recognition accuracy and speed. Experimental studies with about 3000 word images indicate that overall accuracy in the range of 91% to 98% depending on the size of the lexicon (assumed to contain correct word) are achievable with the processing speed of 20 to 30 word per minute on typical work station.

Publication: IEICE TRANSACTIONS on Information Vol.E77-D No.7 pp.785-793

Publication Date: 1994/07/25

Publicized

Online ISSN

DOI

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

Category

Cite this

Copy

Fumitaka KIMURA, Shinji TSURUOKA, Yasuji MIYAKE, Malayappan SHRIDHAR, "A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words" in IEICE TRANSACTIONS on Information, vol. E77-D, no. 7, pp. 785-793, July 1994, doi: .
Abstract: In this paper, authors discuss on a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces. The procedure consists of binarization, presegmentation, intermediate feature extraction, segmentation recognition, and post-processing. The segmentation recognition and the post-processing are repeated for all lexicon words while the binarization to the intermediate feature extraction are applied once for an input word. This algorithm is essentially non hierarchical in character segmentation and recognition which are performed in a single segmentation recognition process. The result of performance evaluation using large handwritten address block database, and algorithm improvements are described and discussed to achieve higher recognition accuracy and speed. Experimental studies with about 3000 word images indicate that overall accuracy in the range of 91% to 98% depending on the size of the lexicon (assumed to contain correct word) are achievable with the processing speed of 20 to 30 word per minute on typical work station.
URL: https://global.ieice.org/en_transactions/information/10.1587/e77-d_7_785/_p

Copy

@ARTICLE{e77-d_7_785,
author={Fumitaka KIMURA, Shinji TSURUOKA, Yasuji MIYAKE, Malayappan SHRIDHAR, },
journal={IEICE TRANSACTIONS on Information},
title={A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words},
year={1994},
volume={E77-D},
number={7},
pages={785-793},
abstract={In this paper, authors discuss on a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces. The procedure consists of binarization, presegmentation, intermediate feature extraction, segmentation recognition, and post-processing. The segmentation recognition and the post-processing are repeated for all lexicon words while the binarization to the intermediate feature extraction are applied once for an input word. This algorithm is essentially non hierarchical in character segmentation and recognition which are performed in a single segmentation recognition process. The result of performance evaluation using large handwritten address block database, and algorithm improvements are described and discussed to achieve higher recognition accuracy and speed. Experimental studies with about 3000 word images indicate that overall accuracy in the range of 91% to 98% depending on the size of the lexicon (assumed to contain correct word) are achievable with the processing speed of 20 to 30 word per minute on typical work station.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words
T2 - IEICE TRANSACTIONS on Information
SP - 785
EP - 793
AU - Fumitaka KIMURA
AU - Shinji TSURUOKA
AU - Yasuji MIYAKE
AU - Malayappan SHRIDHAR
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E77-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 1994
AB - In this paper, authors discuss on a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces. The procedure consists of binarization, presegmentation, intermediate feature extraction, segmentation recognition, and post-processing. The segmentation recognition and the post-processing are repeated for all lexicon words while the binarization to the intermediate feature extraction are applied once for an input word. This algorithm is essentially non hierarchical in character segmentation and recognition which are performed in a single segmentation recognition process. The result of performance evaluation using large handwritten address block database, and algorithm improvements are described and discussed to achieve higher recognition accuracy and speed. Experimental studies with about 3000 word images indicate that overall accuracy in the range of 91% to 98% depending on the size of the lexicon (assumed to contain correct word) are achievable with the processing speed of 20 to 30 word per minute on typical work station.
ER -