Handwritten Manipuri Meetei-Mayek Classification Using Convolutional Neural Network

Abstract

A new technique for classifying all 56 different characters of the Manipuri Meetei-Mayek (MMM) is proposed herein. The characters are grouped under five categories, which are Eeyek Eepee (original alphabets), Lom Eeyek (additional letters), Cheising Eeyek (digits), Lonsum Eeyek (letters with short endings), and Cheitap Eeyek (vowel signs. Two related works proposed by previous researchers are studied for understanding the benefits claimed by the proposed deep learning approach in handwritten Manipuri Meetei-Mayek. (1) Histogram of Oriented (HOG) with SVM classifier is implemented for thoroughly understanding how HOG features can influence accuracy. (2) The handwritten samples are trained using simple Convolutional Neural Network (CNN) and compared with the proposed CNN-based architecture. Significant progress has been made in the field of Optical Character Recognition (OCR) for well-known Indian languages as well as globally popular languages. Our work is novel in the sense that there is no record of work available to date that is able to classify all 56 classes of the MMM. It will also serve as a pre-cursor for developing end-to-end OCR software for translating old manuscripts, newspaper archives, books, and so on.