A Review on Handwritten Recognition System Using Machine Learning Techniques

Abstract

Marathi language is the most widely spoken language in India, and its script is unique and complex Handwriting recognition of the Marathi language poses a significant challenge due to the variety in writing styles and the script's complexity. Machine learning techniques can help in building Marathi handwriting recognition systems that can accurately recognize handwritten Marathi text. The Devanagari script is the source of Marathi, the official language of Maharashtra. Devanagari script is used for the Marathi language and it has 12 vowels and 36 consonants. Handwritten character recognition in any script is a challenging task for researchers. Nowadays, handwritten Marathi character identification is the hardest problem. Sharing physical documents is a laborious and time-consuming task. Because of the structure, shape, various strokes, and writing styles, handwritten Marathi characters are more difficult to read as well as understand. Marathi handwritten recognition system is very essential in various aspects as further described. Preservation of cultural heritage. The mechanism of recognition facilitates accessibility by making Marathi information more easily accessible to people who are visually impaired or have difficulty with traditional text input techniques. The paper focuses on a review of methods used for the development of handwritten character recognition systems using machine learning approaches, including Sanskrit, Hindi, Marathi, and Maithili languages. Different machine learning classifiers such as Decision Tree, Nearest Centroid, KNN, Extra Trees, and Random Forest were implemented and compared for their performance. Extra Trees and Random Forest showed better accuracy.