Isolated text recognition using SVD and HMM

Author

Chandra, Mahesh ; Kumari, Akanksha ; Kumar, Sudhakar

Author_Institution

ECE Dept., BIT Mesra, Ranchi, India

fYear

2014

fDate

8-10 May 2014

Firstpage

1264

Lastpage

1267

Abstract

In this paper, text recognition is implemented using Singular Value Decomposition (SVD) features and Hidden Markov Model (HMM) classifier. SVD features of English digits and alphabets are extracted and HMM technique is used for training and testing purpose. Average recognition efficiency of 48.65%, 72.31% and 75.13% has been obtained for handwritten, independent and dependent English digits respectively. Average recognition efficiency of 9.42%, 63.95% and 79.15% has been also obtained for handwritten, independent and dependent English alphabets respectively.

Keywords

handwritten character recognition; hidden Markov models; image classification; singular value decomposition; HMM classifier; SVD feature extraction; average recognition efficiency; handwritten English alphabets; handwritten English digits; hidden Markov model classifier; independent English alphabets; independent English digits; isolated text recognition; singular value decomposition features; testing purpose; training purpose; Character recognition; Handwriting recognition; Hidden Markov models; Indexes; Training; Training data; Alphabets; Database; Digits; HMM; SVD;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Communication Control and Computing Technologies (ICACCCT), 2014 International Conference on

Conference_Location

Ramanathapuram

Print_ISBN

978-1-4799-3913-8

Type

conf

DOI

10.1109/ICACCCT.2014.7019301

Filename

7019301