Title: Telugu character recognition for degraded palm leaf documents using optimal feature selection techniques - a 3D approach

Authors: T.R. Vijaya Lakshmi; Panyam Narahari Sastry; T.V. Rajinikanth

Addresses: Department of Electronics and Communication Engineering, Mahatma Gandhi Institute of Technology, Hyderabad, Telangana, India ' Department of Electronics and Communication Engineering, Chaitanya Bharathi Institute of Technology, Hyderabad, Telangana, India ' Department of Computer Science and Engineering, Sreenidhi Institute of Science and Technology, Hyderabad, Telangana, India

Abstract: Palm leaves were used as a medium of recording information about 700 years ago. This work deals with the recognition of Telugu palm leaf characters by acquiring 3D data using a contact-type profiler. A novel concept of using a 3D inherent feature, i.e. depth of incision is proposed to eliminate noise. With the help of this 3D feature, improved recognition accuracy is also reported for various features extracted from the palm leaf characters. Experiments are conducted by implementing optimisation techniques, such as differential evolution and particle swarm optimisation, to find the optimum number of features to reduce the memory needed. With varying feature dimensions, average classification accuracies are reported for combination of feature extraction methods and optimisation techniques.

Keywords: 3d feature; histogram of gradients; optimisation techniques; palm leaf manuscripts.

DOI: 10.1504/IJSISE.2017.10008711

International Journal of Signal and Imaging Systems Engineering, 2017 Vol.10 No.5, pp.223 - 230

Received: 31 May 2016
Accepted: 04 May 2017

Published online: 01 Nov 2017 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article