Isolated text recognition using SVD and HMM
Mahesh Chandra, Akanksha Kumari, Sanjeev Kumar · 2014
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.