Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition

研究成果: Paper

1 引文 (Scopus)

摘要

A hybrid feature extraction framework for handwritten numeric fields recognition is described. The numeric fields were extracted from binary images of credit card application forms. The images include identity numbers (ID) and telephone numbers. The feature extraction framework utilizes a cascade of multiple Kohonen self-organizing feature maps(SOMs) and sets of membership value generation units. The goal of our feature extraction process is to provide reliable information to the recognition stage. The recognition stage uses the fuzzy feature set as inputs to a multi-layer neural network. The desired outputs for the networks were set using a fuzzy k-nearest neighbor algorithm. We present experimental results which demonstrate the ability to extract features automatically in handwritten digit recognition. Experiments were performed on a test data set from the CCL/ITRI Database which consists of over 90,390 handwritten numeric digits. A recognition rate of 98.74% is achieved on this database.

原文English
頁面1881-1883
頁數3
出版狀態Published - 1996 十二月 1
事件Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3) - New Orleans, LA, USA
持續時間: 1996 九月 81996 九月 11

Other

OtherProceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3)
城市New Orleans, LA, USA
期間96-09-0896-09-11

指紋

Numerics
Feature Extraction
Feature extraction
Binary images
Self organizing maps
Handwritten Digit Recognition
Multilayer neural networks
Self-organizing Feature Map
Telephone
Multilayer Neural Network
Binary Image
Digit
Cascade
Nearest Neighbor
Unit
Framework
Output
Experimental Results
Experiments
Demonstrate

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

引用此文

Chiang, J-H., & Gader, P. (1996). Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition. 1881-1883. 論文發表於 Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3), New Orleans, LA, USA, .
Chiang, Jung-Hsien ; Gader, P. / Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition. 論文發表於 Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3), New Orleans, LA, USA, .3 p.
@conference{a1b917c2e0a64b34916920cb48cbe856,
title = "Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition",
abstract = "A hybrid feature extraction framework for handwritten numeric fields recognition is described. The numeric fields were extracted from binary images of credit card application forms. The images include identity numbers (ID) and telephone numbers. The feature extraction framework utilizes a cascade of multiple Kohonen self-organizing feature maps(SOMs) and sets of membership value generation units. The goal of our feature extraction process is to provide reliable information to the recognition stage. The recognition stage uses the fuzzy feature set as inputs to a multi-layer neural network. The desired outputs for the networks were set using a fuzzy k-nearest neighbor algorithm. We present experimental results which demonstrate the ability to extract features automatically in handwritten digit recognition. Experiments were performed on a test data set from the CCL/ITRI Database which consists of over 90,390 handwritten numeric digits. A recognition rate of 98.74{\%} is achieved on this database.",
author = "Jung-Hsien Chiang and P. Gader",
year = "1996",
month = "12",
day = "1",
language = "English",
pages = "1881--1883",
note = "Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3) ; Conference date: 08-09-1996 Through 11-09-1996",

}

Chiang, J-H & Gader, P 1996, 'Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition', 論文發表於 Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3), New Orleans, LA, USA, 96-09-08 - 96-09-11 頁 1881-1883.

Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition. / Chiang, Jung-Hsien; Gader, P.

1996. 1881-1883 論文發表於 Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3), New Orleans, LA, USA, .

研究成果: Paper

TY - CONF

T1 - Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition

AU - Chiang, Jung-Hsien

AU - Gader, P.

PY - 1996/12/1

Y1 - 1996/12/1

N2 - A hybrid feature extraction framework for handwritten numeric fields recognition is described. The numeric fields were extracted from binary images of credit card application forms. The images include identity numbers (ID) and telephone numbers. The feature extraction framework utilizes a cascade of multiple Kohonen self-organizing feature maps(SOMs) and sets of membership value generation units. The goal of our feature extraction process is to provide reliable information to the recognition stage. The recognition stage uses the fuzzy feature set as inputs to a multi-layer neural network. The desired outputs for the networks were set using a fuzzy k-nearest neighbor algorithm. We present experimental results which demonstrate the ability to extract features automatically in handwritten digit recognition. Experiments were performed on a test data set from the CCL/ITRI Database which consists of over 90,390 handwritten numeric digits. A recognition rate of 98.74% is achieved on this database.

AB - A hybrid feature extraction framework for handwritten numeric fields recognition is described. The numeric fields were extracted from binary images of credit card application forms. The images include identity numbers (ID) and telephone numbers. The feature extraction framework utilizes a cascade of multiple Kohonen self-organizing feature maps(SOMs) and sets of membership value generation units. The goal of our feature extraction process is to provide reliable information to the recognition stage. The recognition stage uses the fuzzy feature set as inputs to a multi-layer neural network. The desired outputs for the networks were set using a fuzzy k-nearest neighbor algorithm. We present experimental results which demonstrate the ability to extract features automatically in handwritten digit recognition. Experiments were performed on a test data set from the CCL/ITRI Database which consists of over 90,390 handwritten numeric digits. A recognition rate of 98.74% is achieved on this database.

UR - http://www.scopus.com/inward/record.url?scp=0030378494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030378494&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030378494

SP - 1881

EP - 1883

ER -

Chiang J-H, Gader P. Hybrid fuzzy feature extraction framework for handwritten numeric fields recognition. 1996. 論文發表於 Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3), New Orleans, LA, USA, .