Abstract
This paper presents shallow and deep machine learning techniques for recognizing offline handwritten characters of south Dravidian Tulu scripts. Classification and recognition of characters is carried out using shallow learning techniques like Artificial Neural Networks (ANN), Support Vector Machine (SVM), AdaBoost techniques by extracting zone wise density and gradient features and Deep learning technique called Deep Convolution Neural Network (Deep CNN) classifier. Comparative analysis shows that Deep CNN gives higher efficiency of 98.49% compared with shallow learning techniques for isolated Tulu characters from modern documents and 80.49% for isolated character from Tulu palm leaf manuscripts.
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.