Freeman Code Based Online Handwritten Character Recognition for Malayalam using Backpropagation Neural Networks

Abstract

Handwritten character recognition is conversion of handwritten text to machine readable and editable form. Online character recognition deals with live conversion of characters. Malayalam is a language spoken by millions of people in the state of Kerala and the union territories of Lakshadweep and Pondicherry in India. It is written mostly in clockwise direction and consists of loops and curves. The method aims at training a simple neural network with three layers using backpropagation algorithm.Freeman codes are used to represent each character as feature vector. These feature vectors act as inputs to the network during the training and testing phases of the neural network. The output is the character expressed in the Unicode format.

Rajan Transform Based Spectral Analysis of Handwritten Characters

“…Low level features include width, height, curliness, aspect ratio etc., of a character [3]. These alone cannot be used to distinguish one character from another in the character set of a language.…”

“…Amritha Sampath et al (2012) have stated that feature extraction could be carried out using either low level or high level features. Low level features include width, height, curliness, aspect ratio etc., of a character [3].…”

“…Care is taken that the image is fully projected. Projection algorithm involves image resizing and sampling by 8×8 cell array [2,3]. The projected character image is sampled and then the (0-1)-matrix obtained which is also called as 'characteristic matrix' of the projected character.…”

A Study of Handwritten Character Recognition Techniques

“…Where low level elements can incorporate width, tallness, waviness, angle proportion and so on of the characters of a dialect. These alone can't be utilized to separate one character from another in the character set (A. Sampath et al [2]). In this means, there are a variety of other abnormal state elements, for example, number and position of circles, straight lines, features, bends and so forth which ought to likewise be incorporated.…”

Online Handwritten Text Recognition for Indian Scripts

“…Practical applications of online handwriting recognition are: (i) Pen based form filling, (ii) Word processing, (iii) Natural language processing, and (iv)Usage of online handwriting recognition in conjunction with speech synthesis, to empower people with vocal disability to communicate with others [46]. Various Designers have been actively involved in developing online Handwritten character recognition systems for Indian scripts (N Joshi et al [6,27]; A Sharma et al [11,51], R.K Sharma et al [11,14,15,16], Sachan and Lehal et al [12,13] ,U. Bhattacharya et al [17,19,20], A G. Ramkrishnan etal. [6,27,30,31,32,33,34,43,44,46], R. Kunwar et al [30,31,44]).…”