Recognition of strings using Nonstationary Markovian Models: An application in ZIP Code recognition

Djamel Bouchaffra; Venu Govindaraju; Sargur N. Srihari

Recognition of strings using Nonstationary Markovian Models: An application in ZIP Code recognition

Djamel Bouchaffra
, Venu Govindaraju
, Sargur N. Srihari

Research and Economic Development

SUNY Buffalo

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper presents Nonstationary Markovian Models and their application to recognition of strings of tokens, such as ZIP Codes in the US mailstream. Unlike traditional approaches where digits are simply recognized in isolation, the novelty of our approach lies in the manner in which recognitions scores along with domain specific knowledge about the frequency distribution of various combination of digits are all integrated into one unified model. The domain knowledge is derived from postal directory files. This data feeds into the models as n-grams statistics that are seamlessly integrated with recognition scores of digit images. We present the recognition accuracy (90%) achieved on a set of 20,000 ZIP Codes.

Original language	English
Pages (from-to)	174-179
Number of pages	6
Journal	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2
State	Published - 1999
Event	Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Fort Collins, CO, USA Duration: Jun 23 1999 → Jun 25 1999

Cite this

@article{5c2825f6e50d428888c516a60b6c179b,

title = "Recognition of strings using Nonstationary Markovian Models: An application in ZIP Code recognition",

abstract = "This paper presents Nonstationary Markovian Models and their application to recognition of strings of tokens, such as ZIP Codes in the US mailstream. Unlike traditional approaches where digits are simply recognized in isolation, the novelty of our approach lies in the manner in which recognitions scores along with domain specific knowledge about the frequency distribution of various combination of digits are all integrated into one unified model. The domain knowledge is derived from postal directory files. This data feeds into the models as n-grams statistics that are seamlessly integrated with recognition scores of digit images. We present the recognition accuracy (90\%) achieved on a set of 20,000 ZIP Codes.",

author = "Djamel Bouchaffra and Venu Govindaraju and Srihari, \{Sargur N.\}",

year = "1999",

language = "English",

volume = "2",

pages = "174--179",

journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

issn = "1063-6919",

publisher = "IEEE Computer Society",

note = "Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) ; Conference date: 23-06-1999 Through 25-06-1999",

}

TY - JOUR

T1 - Recognition of strings using Nonstationary Markovian Models

T2 - Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99)

AU - Bouchaffra, Djamel

AU - Govindaraju, Venu

AU - Srihari, Sargur N.

PY - 1999

Y1 - 1999

N2 - This paper presents Nonstationary Markovian Models and their application to recognition of strings of tokens, such as ZIP Codes in the US mailstream. Unlike traditional approaches where digits are simply recognized in isolation, the novelty of our approach lies in the manner in which recognitions scores along with domain specific knowledge about the frequency distribution of various combination of digits are all integrated into one unified model. The domain knowledge is derived from postal directory files. This data feeds into the models as n-grams statistics that are seamlessly integrated with recognition scores of digit images. We present the recognition accuracy (90%) achieved on a set of 20,000 ZIP Codes.

AB - This paper presents Nonstationary Markovian Models and their application to recognition of strings of tokens, such as ZIP Codes in the US mailstream. Unlike traditional approaches where digits are simply recognized in isolation, the novelty of our approach lies in the manner in which recognitions scores along with domain specific knowledge about the frequency distribution of various combination of digits are all integrated into one unified model. The domain knowledge is derived from postal directory files. This data feeds into the models as n-grams statistics that are seamlessly integrated with recognition scores of digit images. We present the recognition accuracy (90%) achieved on a set of 20,000 ZIP Codes.

UR - https://www.scopus.com/pages/publications/0032665456

M3 - Conference article

AN - SCOPUS:0032665456

SN - 1063-6919

VL - 2

SP - 174

EP - 179

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 23 June 1999 through 25 June 1999

ER -

Recognition of strings using Nonstationary Markovian Models: An application in ZIP Code recognition

Abstract

Other files and links

Fingerprint

Cite this