KANNADA ALPHABETS RECOGNITION with APPLICATION to BRAILLE TRANSLATION

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

Research output: Contribution to journalArticle

Abstract

In this paper, an effort is made to apply optical character recognition (OCR) for Braille translation on Kannada characters. In general, OCR systems for Indian language are more complex due to larger number of vowels, consonants, and conjuncts and Indian languages are inflectional and agglutinative in nature. Specifically, characters of Kannada script have higher similarity in shape and higher variability across fonts, making recognition of characters a difficult task. A decision tree is developed in this research work. The main motivations are that decision trees provide a natural way to incorporate prior knowledge of domain and many Kannada characters have similar looking shapes. The similar looking characters can be grouped and then further partitioned into categories at various levels to effectively create a decision tree. To facilitate this, three modular classifiers are developed based on the nature of Kannada characters. These modular classifiers are employed at nodes of the decision tree. The Braille equivalent of Kannada characters is obtained by translation rules. An overall accuracy of classification and Braille translation of 93.80% is obtained.

Original languageEnglish
Pages (from-to)293-314
Number of pages22
JournalInternational Journal of Image and Graphics
Volume11
Issue number3
DOIs
Publication statusPublished - 01-07-2011

Fingerprint

Decision trees
Optical character recognition
Classifiers

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

@article{f87a38c56f58460baecd664015828e0b,
title = "KANNADA ALPHABETS RECOGNITION with APPLICATION to BRAILLE TRANSLATION",
abstract = "In this paper, an effort is made to apply optical character recognition (OCR) for Braille translation on Kannada characters. In general, OCR systems for Indian language are more complex due to larger number of vowels, consonants, and conjuncts and Indian languages are inflectional and agglutinative in nature. Specifically, characters of Kannada script have higher similarity in shape and higher variability across fonts, making recognition of characters a difficult task. A decision tree is developed in this research work. The main motivations are that decision trees provide a natural way to incorporate prior knowledge of domain and many Kannada characters have similar looking shapes. The similar looking characters can be grouped and then further partitioned into categories at various levels to effectively create a decision tree. To facilitate this, three modular classifiers are developed based on the nature of Kannada characters. These modular classifiers are employed at nodes of the decision tree. The Braille equivalent of Kannada characters is obtained by translation rules. An overall accuracy of classification and Braille translation of 93.80{\%} is obtained.",
author = "Siddhaling Urolagin and Prema, {K. V.} and {Subba Reddy}, {N. V.}",
year = "2011",
month = "7",
day = "1",
doi = "10.1142/S0219467811004159",
language = "English",
volume = "11",
pages = "293--314",
journal = "International Journal of Image and Graphics",
issn = "0219-4678",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "3",

}

KANNADA ALPHABETS RECOGNITION with APPLICATION to BRAILLE TRANSLATION. / Urolagin, Siddhaling; Prema, K. V.; Subba Reddy, N. V.

In: International Journal of Image and Graphics, Vol. 11, No. 3, 01.07.2011, p. 293-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - KANNADA ALPHABETS RECOGNITION with APPLICATION to BRAILLE TRANSLATION

AU - Urolagin, Siddhaling

AU - Prema, K. V.

AU - Subba Reddy, N. V.

PY - 2011/7/1

Y1 - 2011/7/1

N2 - In this paper, an effort is made to apply optical character recognition (OCR) for Braille translation on Kannada characters. In general, OCR systems for Indian language are more complex due to larger number of vowels, consonants, and conjuncts and Indian languages are inflectional and agglutinative in nature. Specifically, characters of Kannada script have higher similarity in shape and higher variability across fonts, making recognition of characters a difficult task. A decision tree is developed in this research work. The main motivations are that decision trees provide a natural way to incorporate prior knowledge of domain and many Kannada characters have similar looking shapes. The similar looking characters can be grouped and then further partitioned into categories at various levels to effectively create a decision tree. To facilitate this, three modular classifiers are developed based on the nature of Kannada characters. These modular classifiers are employed at nodes of the decision tree. The Braille equivalent of Kannada characters is obtained by translation rules. An overall accuracy of classification and Braille translation of 93.80% is obtained.

AB - In this paper, an effort is made to apply optical character recognition (OCR) for Braille translation on Kannada characters. In general, OCR systems for Indian language are more complex due to larger number of vowels, consonants, and conjuncts and Indian languages are inflectional and agglutinative in nature. Specifically, characters of Kannada script have higher similarity in shape and higher variability across fonts, making recognition of characters a difficult task. A decision tree is developed in this research work. The main motivations are that decision trees provide a natural way to incorporate prior knowledge of domain and many Kannada characters have similar looking shapes. The similar looking characters can be grouped and then further partitioned into categories at various levels to effectively create a decision tree. To facilitate this, three modular classifiers are developed based on the nature of Kannada characters. These modular classifiers are employed at nodes of the decision tree. The Braille equivalent of Kannada characters is obtained by translation rules. An overall accuracy of classification and Braille translation of 93.80% is obtained.

UR - http://www.scopus.com/inward/record.url?scp=85073068571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073068571&partnerID=8YFLogxK

U2 - 10.1142/S0219467811004159

DO - 10.1142/S0219467811004159

M3 - Article

AN - SCOPUS:85073068571

VL - 11

SP - 293

EP - 314

JO - International Journal of Image and Graphics

JF - International Journal of Image and Graphics

SN - 0219-4678

IS - 3

ER -