Segmentation of inflected top portions of Kannada characters using Gabor filters

Siddhaling Urolagin, K. V. Prema, R. Jaya Krishna, N. V.Subba Reddy

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

1 Citation (Scopus)

Abstract

Kannada script has large number of characters with similar looking shapes among characters and characters belonging to same class have higher variability across different set of fonts. Moreover, the Kannada characters are formed by combination of basic symbols; recognition of the Kannada character is complex and challenging task. The better approach for recognition is to segment characters into basic symbol and recognize each symbol subsequently. Therefore a character level segmentation method is highly desirable. In the recent years it is found that the multichannel Gabor decomposition represents an excellent tool for image segmentation and texture analysis. At higher frequency, Gabor filters have property to extract edge information. By analyzing such responses we have proposed a novel character segmentation method to segment top vowel modifier portion from an akshara (analogous to characters in English). Experiments are conducted on benchmark database of 1088 samples. Overall accuracy of 96.87% for top row index and 95.49% for consonant row index is observed.

Original languageEnglish
Title of host publicationProceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011
Pages110-113
Number of pages4
DOIs
Publication statusPublished - 18-04-2011
Event2nd International Conference on Emerging Applications of Information Technology, EAIT 2011 - Kolkata, India
Duration: 19-02-201120-02-2011

Conference

Conference2nd International Conference on Emerging Applications of Information Technology, EAIT 2011
CountryIndia
CityKolkata
Period19-02-1120-02-11

Fingerprint

Image texture
Gabor filters
Image segmentation
Decomposition
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Urolagin, S., Prema, K. V., Jaya Krishna, R., & Reddy, N. V. S. (2011). Segmentation of inflected top portions of Kannada characters using Gabor filters. In Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011 (pp. 110-113). [5734929] https://doi.org/10.1109/EAIT.2011.66
Urolagin, Siddhaling ; Prema, K. V. ; Jaya Krishna, R. ; Reddy, N. V.Subba. / Segmentation of inflected top portions of Kannada characters using Gabor filters. Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011. 2011. pp. 110-113
@inproceedings{bc8f759203454c909dcdea4d5c38b447,
title = "Segmentation of inflected top portions of Kannada characters using Gabor filters",
abstract = "Kannada script has large number of characters with similar looking shapes among characters and characters belonging to same class have higher variability across different set of fonts. Moreover, the Kannada characters are formed by combination of basic symbols; recognition of the Kannada character is complex and challenging task. The better approach for recognition is to segment characters into basic symbol and recognize each symbol subsequently. Therefore a character level segmentation method is highly desirable. In the recent years it is found that the multichannel Gabor decomposition represents an excellent tool for image segmentation and texture analysis. At higher frequency, Gabor filters have property to extract edge information. By analyzing such responses we have proposed a novel character segmentation method to segment top vowel modifier portion from an akshara (analogous to characters in English). Experiments are conducted on benchmark database of 1088 samples. Overall accuracy of 96.87{\%} for top row index and 95.49{\%} for consonant row index is observed.",
author = "Siddhaling Urolagin and Prema, {K. V.} and {Jaya Krishna}, R. and Reddy, {N. V.Subba}",
year = "2011",
month = "4",
day = "18",
doi = "10.1109/EAIT.2011.66",
language = "English",
isbn = "9780769543291",
pages = "110--113",
booktitle = "Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011",

}

Urolagin, S, Prema, KV, Jaya Krishna, R & Reddy, NVS 2011, Segmentation of inflected top portions of Kannada characters using Gabor filters. in Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011., 5734929, pp. 110-113, 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011, Kolkata, India, 19-02-11. https://doi.org/10.1109/EAIT.2011.66

Segmentation of inflected top portions of Kannada characters using Gabor filters. / Urolagin, Siddhaling; Prema, K. V.; Jaya Krishna, R.; Reddy, N. V.Subba.

Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011. 2011. p. 110-113 5734929.

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

TY - GEN

T1 - Segmentation of inflected top portions of Kannada characters using Gabor filters

AU - Urolagin, Siddhaling

AU - Prema, K. V.

AU - Jaya Krishna, R.

AU - Reddy, N. V.Subba

PY - 2011/4/18

Y1 - 2011/4/18

N2 - Kannada script has large number of characters with similar looking shapes among characters and characters belonging to same class have higher variability across different set of fonts. Moreover, the Kannada characters are formed by combination of basic symbols; recognition of the Kannada character is complex and challenging task. The better approach for recognition is to segment characters into basic symbol and recognize each symbol subsequently. Therefore a character level segmentation method is highly desirable. In the recent years it is found that the multichannel Gabor decomposition represents an excellent tool for image segmentation and texture analysis. At higher frequency, Gabor filters have property to extract edge information. By analyzing such responses we have proposed a novel character segmentation method to segment top vowel modifier portion from an akshara (analogous to characters in English). Experiments are conducted on benchmark database of 1088 samples. Overall accuracy of 96.87% for top row index and 95.49% for consonant row index is observed.

AB - Kannada script has large number of characters with similar looking shapes among characters and characters belonging to same class have higher variability across different set of fonts. Moreover, the Kannada characters are formed by combination of basic symbols; recognition of the Kannada character is complex and challenging task. The better approach for recognition is to segment characters into basic symbol and recognize each symbol subsequently. Therefore a character level segmentation method is highly desirable. In the recent years it is found that the multichannel Gabor decomposition represents an excellent tool for image segmentation and texture analysis. At higher frequency, Gabor filters have property to extract edge information. By analyzing such responses we have proposed a novel character segmentation method to segment top vowel modifier portion from an akshara (analogous to characters in English). Experiments are conducted on benchmark database of 1088 samples. Overall accuracy of 96.87% for top row index and 95.49% for consonant row index is observed.

UR - http://www.scopus.com/inward/record.url?scp=79953865282&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953865282&partnerID=8YFLogxK

U2 - 10.1109/EAIT.2011.66

DO - 10.1109/EAIT.2011.66

M3 - Conference contribution

SN - 9780769543291

SP - 110

EP - 113

BT - Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011

ER -

Urolagin S, Prema KV, Jaya Krishna R, Reddy NVS. Segmentation of inflected top portions of Kannada characters using Gabor filters. In Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011. 2011. p. 110-113. 5734929 https://doi.org/10.1109/EAIT.2011.66