CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL

N. Z. Hakim; J. J. Kaufman; G. Cerf; H. E. Meadows

doi:10.1109/IJCNN.1992.227068

CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL

N. Z. Hakim
, J. J. Kaufman
, G. Cerf
, H. E. Meadows

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

This paper presents a study to assess the performance of a discrete-time recurrent neural network in cursive script character recognition. The pen coordinates are sampled at discrete times and sequentially entered on two separate channels to a bank of neural network-based recognizers, each trained to recognize one specific character. The recognizers outputs are collected and reconverted into a string of characters, with associated probabilities. This method was tried on a restricted alphabet of six letters. We present here the results of the study and discuss its extension to more complex situations.

Original language	English
Title of host publication	Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	711-716
Number of pages	6
ISBN (Electronic)	0780305590
DOIs	https://doi.org/10.1109/IJCNN.1992.227068
State	Published - 1992
Externally published	Yes
Event	1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States Duration: 7 Jun 1992 → 11 Jun 1992

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	3

Conference

Conference	1992 International Joint Conference on Neural Networks, IJCNN 1992
Country/Territory	United States
City	Baltimore
Period	7/06/92 → 11/06/92

Access to Document

10.1109/IJCNN.1992.227068

Cite this

Hakim, N. Z., Kaufman, J. J., Cerf, G., & Meadows, H. E. (1992). CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL. In Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992 (pp. 711-716). (Proceedings of the International Joint Conference on Neural Networks; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.1992.227068

@inproceedings{91ce18efd6d34ef6a19028118f7e50ab,

title = "CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL",

abstract = "This paper presents a study to assess the performance of a discrete-time recurrent neural network in cursive script character recognition. The pen coordinates are sampled at discrete times and sequentially entered on two separate channels to a bank of neural network-based recognizers, each trained to recognize one specific character. The recognizers outputs are collected and reconverted into a string of characters, with associated probabilities. This method was tried on a restricted alphabet of six letters. We present here the results of the study and discuss its extension to more complex situations.",

author = "Hakim, \{N. Z.\} and Kaufman, \{J. J.\} and G. Cerf and Meadows, \{H. E.\}",

note = "Publisher Copyright: {\textcopyright} 1992 IEEE; 1992 International Joint Conference on Neural Networks, IJCNN 1992 ; Conference date: 07-06-1992 Through 11-06-1992",

year = "1992",

doi = "10.1109/IJCNN.1992.227068",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "711--716",

booktitle = "Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992",

address = "United States",

}

Hakim, NZ, Kaufman, JJ, Cerf, G & Meadows, HE 1992, CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL. in Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Proceedings of the International Joint Conference on Neural Networks, vol. 3, Institute of Electrical and Electronics Engineers Inc., pp. 711-716, 1992 International Joint Conference on Neural Networks, IJCNN 1992, Baltimore, United States, 7/06/92. https://doi.org/10.1109/IJCNN.1992.227068

CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL. / Hakim, N. Z.; Kaufman, J. J.; Cerf, G. et al.
Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 711-716 (Proceedings of the International Joint Conference on Neural Networks; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL

AU - Hakim, N. Z.

AU - Kaufman, J. J.

AU - Cerf, G.

AU - Meadows, H. E.

PY - 1992

Y1 - 1992

N2 - This paper presents a study to assess the performance of a discrete-time recurrent neural network in cursive script character recognition. The pen coordinates are sampled at discrete times and sequentially entered on two separate channels to a bank of neural network-based recognizers, each trained to recognize one specific character. The recognizers outputs are collected and reconverted into a string of characters, with associated probabilities. This method was tried on a restricted alphabet of six letters. We present here the results of the study and discuss its extension to more complex situations.

AB - This paper presents a study to assess the performance of a discrete-time recurrent neural network in cursive script character recognition. The pen coordinates are sampled at discrete times and sequentially entered on two separate channels to a bank of neural network-based recognizers, each trained to recognize one specific character. The recognizers outputs are collected and reconverted into a string of characters, with associated probabilities. This method was tried on a restricted alphabet of six letters. We present here the results of the study and discuss its extension to more complex situations.

UR - https://www.scopus.com/pages/publications/84912971527

U2 - 10.1109/IJCNN.1992.227068

DO - 10.1109/IJCNN.1992.227068

M3 - Conference contribution

AN - SCOPUS:84912971527

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 711

EP - 716

BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992

Y2 - 7 June 1992 through 11 June 1992

ER -

Hakim NZ, Kaufman JJ, Cerf G, Meadows HE. CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL. In Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 711-716. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.1992.227068

CURSIVE SCRIPT ONLINE CHARACTER RECOGNITION WITH A RECURRENT NEURAL NETWORK MODEL

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this