Machine recognition of online handwritten Devanagari characters

Abstract

consonant modified by vowel sound) and CVM (M is a modifier that modifies the nature of the preceding In this paper, we describe a system for the automatic vowel, e.g. nasalization). Other Tare forms were recognition of isolated handwritten Devanagari omitted for the Purpose of this study. Given ICl = 35, characters obtained by linearizing consonant IVI = 11, IN\ = 10, /MI = 4, andreshcting ourselves to conjuncts. Owing to the large number of characters valid combinations, we are left with a total of 1487 and resulting demands on data acquisition, we use characters to recognize-Some examples of each of structural reconnition techniques to reduce some these categories of characters are shown in Figure 1.characters to others. The residual characters are then classiJied using the subspace method. Finally the results of structural recognition and feature-based matching are mapped to give final output. The proposed system is evaluated for the writer dependent scenario.

Recognize Online Handwritten Bangla Characters Using Hausdorff Distance-Based Feature

“…In this way, people not only save extra time but also this procedure minimizes the chance of mistyping that may arise when writing with a keyboard. Though some good research works are found in the literature for Devenagari script [1][2][3][4][5][6][7][8], the same cannot be said for the Bangla script. The presence of limited research materials in the literature proves the truthfulness of the statement.…”

An Online Character Recognition System to Convert Grantha Script to Malayalam

“…[2], [3], [4], [5], [6] (ii) Characters may be viewed as compositions of C, C', V and M graphemes [7] (iii) character can be viewed as indivisible units. [8].…”

Online Handwritten Text Recognition for Indian Scripts

“…They have used combination of Hidden Microwave Model and Nearest Neighbor Classifier for classification and capturing different levels of offline and online features yielding a classification accuracy of 86.5%. Joshi et al [6] have developed a system for automatic recognition of isolated handwritten devanagari character obtained by linearizing consonant conjuncts. Resampling and low pass filtering are used as preprocessing techniques.…”

“…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]).…”