Few Shot Learning Approach to Online Malayalam Handwritten Character Recognition

Venugopal Palakkath, Vishnu (2022) Few Shot Learning Approach to Online Malayalam Handwritten Character Recognition. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

In the field of image processing, handwritten character recognition has become one of the most intriguing studies. An image, document, or real-time device like a tablet, tabloid or digitizer can be used as input for the Handwritten character recognition method. The input is subsequently translated into digital text. Online Handwritten Recognition and Offline Handwritten Recognition are the two commonly utilized methods for recognizing handwriting. Writing styles, such as line spacing, word spacing, character sizes, and the shape of each character, can vary from person to person. Feature extraction and character identification are the most time-consuming and difficult parts of OCR since they depend on the language. According to the features of a language, feature extraction can be different for each one. It is the curvy and non-cursive nature of Malayalam characters that distinguish them from other scripts. To understand the recognition of online handwritten characters in Malayalam, this paper compares traditional classification approaches like SVM Kernels that use Histogram of Oriented Gradients as features ,CNN and RNN based deep learning models and CNN based transfer learning models with Siamese Networks.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing P Language and Literature > PL Languages and literatures of Eastern Asia, Africa, Oceania > Dravidian Languages Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	14 Mar 2023 12:46
Last Modified:	14 Mar 2023 12:46
URI:	https://norma.ncirl.ie/id/eprint/6333

Actions (login required)

View Item