Radon Transform and PCA based feature extraction to design an Assamese Character Recognition system

Author

Sharma, Praveen Kumar ; Deori, Mondira ; Kaur, Baljit ; Dey, Chanchal ; Das, Krishanu

Author_Institution

Dept. of Electron. & Commun. Eng., Don Bosco Coll. of Eng. & Technol., Guwahati, India

fYear

2012

fDate

30-31 March 2012

Firstpage

46

Lastpage

51

Abstract

Character Recognition is a process of understanding a human readable text document by machines. Today many researchers in the academia and industry are interested in this direction. This paper describes a novel method of Character Recognition. The main objective of this is to use the Radon Transform and Principal Component Analysis to obtain a set of invariant features, on basis of which a character will be recognized. The results found from the various experiments prove the effectiveness of the proposed method.

Keywords

Radon transforms; character recognition; feature extraction; natural languages; principal component analysis; Assamese character recognition system; PCA; Radon transform; feature extraction; human readable text document; invariant feature; principal component analysis; Handwriting recognition; Hidden Markov models; Image segmentation; Portable computers; Principal component analysis; Transforms; Vectors; ANN; Character Recognition; HMM; MLP; Principal Component Analysis; Radon Transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Trends and Applications in Computer Science (NCETACS), 2012 3rd National Conference on

Conference_Location

Shillong

Print_ISBN

978-1-4577-0749-0

Type

conf

DOI

10.1109/NCETACS.2012.6203296

Filename

6203296