Recognition of Handwritten Character of Manipuri Script

Abstract

<span style="font-family: Times New Roman; font-size: xx-small;"><span style="font-family: Times New Roman; font-size: xx-small;"><p>In this paper a backpropagation neural network based handwritten characters (Mapum Mayek ) recognition system of Manipuri Script is investigated. This paper presents various steps involved in the recognition process. It begins with thresholding of gray level image into binarised image, then from the binarised image the character pattern is segmented using connected component analysis and from the resized character matrix, its probabilistic features and fuzzy features are extracted. Using these features the network is trained and recognition tests are performed. Experiments indicate that the proposed recognition system performs well with the combined features and is robust to the writing variations that exist between persons and for a single person at different instances, thus being promising for user independent character recognition.</p></span></span&gt

Increasing the effectiveness of handwritten Manipuri Meetei-Mayek character recognition using multiple-HOG-feature descriptors

“…They were able to achieve an overall performance of 85%. Thokchom et al [15] proposed methods for training BP network with probabilistic features, fuzzy features and a combination of both features for recognizing handwritten Meetei-Mayek characters. They were able to achieve an accuracy of 90.3% for the proposed 27-class classifier neural network with a combination of probabilistic and fuzzy features.…”

“…Maring and Dhir [11], on the other hand, proposed a different architecture and used around 6000 and 1200 training and testing samples, respectively, for classifying the same 10 different classes and achieved an accuracy of around 89.58%. Character classification: Thokchom et al [15] developed a technique to categorize all the 27 different main alphabets of the script using around 459 and 135 training and testing samples, respectively. They achieved an overall accuracy of 90.3%.…”

Recognition of Handwritten Meitei Mayek Script Based on Texture Feature

“…However, very few research papers existed in literature for recognition based on Meitei Mayek Script. In 2010, identification of the handwritten character of Meitei Mayek script using Artificial Neural Network was proposed by [2]. The authors have used 594 samples images, out of which 459 have been trained, and the remaining 135 had been used for testing.…”

An OCR system for the Meetei Mayek script

“…However, very few scientific works are reported towards character recognition in the Meetei Mayek script. There is a work on a proposed method for the recognition of handwritten Meetei Mayek characters [3]. Ours is the first report for implementing an OCR for the printed Meetei Mayek document page.…”