Illumination invariant character recognition using binarized gabor features

Siddhaling Urolagin, K. V. Prema, N. V. Subba Reddy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The project of converting Indian language document to Bharti Braille script has many challenges. The illumination invariant character recognition is one of such challenge which is addressed in this paper. The Gabor features provide illumination invariance up to certain extend, but in recent developments such as local binary pattern and binarizing the directional filter's response and then computing features from them have made feature highly tolerant to lighting changes. In this context we are proposing the new idea of binarized Gabor feature which is to binarize the Gabor response then compute directional features using a grid structure. To binarize Gabor response we are proposing a threshold such that most vital part of response is highlighted in its binary form. We are demonstrating the feature extraction technique for numeral recognition. The database consists of 1260 scanned numeral images at different scanning parameters and 12000 generated numeral images with varying intensity. The binarized Gabor features are compared with Gabor features based on classification rates obtained. In all our experimental results better classification rates are observed for the proposed method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007
Pages423-430
Number of pages8
Volume2
DOIs
Publication statusPublished - 31-03-2008
EventInternational Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007 - Sivakasi, Tamil Nadu, India
Duration: 13-12-200715-12-2007

Conference

ConferenceInternational Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007
CountryIndia
CitySivakasi, Tamil Nadu
Period13-12-0715-12-07

Fingerprint

Character recognition
Lighting
Invariance
Feature extraction
Scanning

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Urolagin, S., Prema, K. V., & Subba Reddy, N. V. (2008). Illumination invariant character recognition using binarized gabor features. In Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007 (Vol. 2, pp. 423-430). [4426733] https://doi.org/10.1109/ICCIMA.2007.226
Urolagin, Siddhaling ; Prema, K. V. ; Subba Reddy, N. V. / Illumination invariant character recognition using binarized gabor features. Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007. Vol. 2 2008. pp. 423-430
@inproceedings{130875a156b244acb23295b9efd8d77a,
title = "Illumination invariant character recognition using binarized gabor features",
abstract = "The project of converting Indian language document to Bharti Braille script has many challenges. The illumination invariant character recognition is one of such challenge which is addressed in this paper. The Gabor features provide illumination invariance up to certain extend, but in recent developments such as local binary pattern and binarizing the directional filter's response and then computing features from them have made feature highly tolerant to lighting changes. In this context we are proposing the new idea of binarized Gabor feature which is to binarize the Gabor response then compute directional features using a grid structure. To binarize Gabor response we are proposing a threshold such that most vital part of response is highlighted in its binary form. We are demonstrating the feature extraction technique for numeral recognition. The database consists of 1260 scanned numeral images at different scanning parameters and 12000 generated numeral images with varying intensity. The binarized Gabor features are compared with Gabor features based on classification rates obtained. In all our experimental results better classification rates are observed for the proposed method.",
author = "Siddhaling Urolagin and Prema, {K. V.} and {Subba Reddy}, {N. V.}",
year = "2008",
month = "3",
day = "31",
doi = "10.1109/ICCIMA.2007.226",
language = "English",
isbn = "0769530508",
volume = "2",
pages = "423--430",
booktitle = "Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007",

}

Urolagin, S, Prema, KV & Subba Reddy, NV 2008, Illumination invariant character recognition using binarized gabor features. in Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007. vol. 2, 4426733, pp. 423-430, International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007, Sivakasi, Tamil Nadu, India, 13-12-07. https://doi.org/10.1109/ICCIMA.2007.226

Illumination invariant character recognition using binarized gabor features. / Urolagin, Siddhaling; Prema, K. V.; Subba Reddy, N. V.

Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007. Vol. 2 2008. p. 423-430 4426733.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Illumination invariant character recognition using binarized gabor features

AU - Urolagin, Siddhaling

AU - Prema, K. V.

AU - Subba Reddy, N. V.

PY - 2008/3/31

Y1 - 2008/3/31

N2 - The project of converting Indian language document to Bharti Braille script has many challenges. The illumination invariant character recognition is one of such challenge which is addressed in this paper. The Gabor features provide illumination invariance up to certain extend, but in recent developments such as local binary pattern and binarizing the directional filter's response and then computing features from them have made feature highly tolerant to lighting changes. In this context we are proposing the new idea of binarized Gabor feature which is to binarize the Gabor response then compute directional features using a grid structure. To binarize Gabor response we are proposing a threshold such that most vital part of response is highlighted in its binary form. We are demonstrating the feature extraction technique for numeral recognition. The database consists of 1260 scanned numeral images at different scanning parameters and 12000 generated numeral images with varying intensity. The binarized Gabor features are compared with Gabor features based on classification rates obtained. In all our experimental results better classification rates are observed for the proposed method.

AB - The project of converting Indian language document to Bharti Braille script has many challenges. The illumination invariant character recognition is one of such challenge which is addressed in this paper. The Gabor features provide illumination invariance up to certain extend, but in recent developments such as local binary pattern and binarizing the directional filter's response and then computing features from them have made feature highly tolerant to lighting changes. In this context we are proposing the new idea of binarized Gabor feature which is to binarize the Gabor response then compute directional features using a grid structure. To binarize Gabor response we are proposing a threshold such that most vital part of response is highlighted in its binary form. We are demonstrating the feature extraction technique for numeral recognition. The database consists of 1260 scanned numeral images at different scanning parameters and 12000 generated numeral images with varying intensity. The binarized Gabor features are compared with Gabor features based on classification rates obtained. In all our experimental results better classification rates are observed for the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=41149118069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41149118069&partnerID=8YFLogxK

U2 - 10.1109/ICCIMA.2007.226

DO - 10.1109/ICCIMA.2007.226

M3 - Conference contribution

SN - 0769530508

SN - 9780769530505

VL - 2

SP - 423

EP - 430

BT - Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007

ER -

Urolagin S, Prema KV, Subba Reddy NV. Illumination invariant character recognition using binarized gabor features. In Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007. Vol. 2. 2008. p. 423-430. 4426733 https://doi.org/10.1109/ICCIMA.2007.226