Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis

Abstract

“MODI lipi” is one of the ancient scripts of Western India. Considerable work has been reported for various other ancient Indian languages except for MODI lipi. Its structural characteristics and non-availability of image database make MODI recognition challenging. The work reported in this paper comprises the creation of an image dataset for MODI handwritten characters and the development of a supervised Transfer Learning (TL)-based classification framework. It makes use of Deep Convolutional Neural Network (DCNN) Alexnet as a pre-trained network to transfer weights to retrain the network. This network is used as a feature extractor to extract features from different layers of the network. A Support Vector Machine (SVM) is trained on activation features to obtain classifier models. These models are investigated further for recognition accuracy and feature analysis. Subjective and objective measures are used to select discriminant deep features. We achieved recognition accuracies of 92.32% and 97.25% for Handwritten MODI character recognition and handwritten Devnagari character recognition, respectively.

KEYWORDS:

• Alexnet
• DCNN
• Handwritten character recognition
• MODI lipi
• SVM
• TL

Additional information

Notes on contributors

Savitri Chandure

Savitri Laxmanrao Chandure received her post-graduate degree from the University of Pune, Pune, Maharashtra, India, in 2009. She is currently working as assistant professor in the School of Electronics and Communication Engineering, MITWPU, Pune. She has 13 years of experience as an academician. She is a member of SAE-India.

Vandana Inamdar

Vandana S Inamdar received her PhD degree from Savitribai Phule Pune University, Pune India. She is currently working as associate professor in the Department of Computer Engineering and Information Technology, College of Engineering, Pune, India. She has 28 years of academic experience and around forty publications to her credit. She is a member of IEEE Signal Processing Society, CSI India, IETE and ISTE. E-mail: [email protected]