In this paper, we describe the design and implementation of a unifi ed word processing system to handle handwritten characters for Indian languages.It uses XML [1] based document format to store the strokes written by the user.It provides fi Iters to export the native document into other standards like InkML (Ink Markup Language) [2] and LDF (Lekhak Data Format). It integrates shape feature based recognition engine to recognise the whole document and spell checker to correct the wrongly recognised words. It includes the support to send the document as an attachment with E-mail without the need for recognition. © 2007 IEEE.

Srinivasa Chakravarthy

Department Of Biotechnology

Electronic mail

Natural language processing systems

Pattern Recognition

Program documentation

Standards

User interfaces

DATA FORMAT

Indian languages

RECOGNITION ENGINE

SPELL CHECKER

Word processing

IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

PATRAM: A Unified Word Processing System for Handwritten Characters in Indian Languages

Proceedings - International Conference on Computing: Theory and Applications, ICCTA 2007

A system for online recognition of handwritten Tamil characters is presented. A handwritten character is constructed by executing a sequence of strokes. A structure- or shape-based representation of a stroke is used in which a stroke is represented as a string of shape features. Using this string representation, an unknown stroke is identified by comparing it with a database of strokes using a flexible string matching procedure. A full character is recognized by identifying all the component strokes. Character termination, is determined using a finite state automaton. Development of similar systems for other Indian scripts is outlined. © 2004 IEEE.

Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR

Online handwriting recognition for Tamil

In this paper, we present PATRAM, a comprehensive handwritten wordprocessing system specially designed for Indian languages. In typical existing ink capture programs, handwriting is entered in a 'paint-on-a-wall' style without any syntactical structure imposed on the handwritten text. The PATRAM document page is classified into text (ruled space) and drawing (unruled space) areas. While inking the text region, the writer stays within the lines. The drawing region does not have such a restriction. While this arrangement accomodates unconstrained inking (in drawing area), it provides a more intuitive and convenient editing style for the text area. The standard operations including Insert, Cut, Copy, Paste, Delete, Select, Justify etc. are defined which operate on text or drawing objects in characteristic fashion. The document is saved in a specific format (.pat) which makes off-line character recognition possible. We finally demonstrate recognition capability in Tamil language. © 2004 IEEE.

PATRAM - A handwritten word processor for Indian languages

Benezit Dictionary of Artists

Aspell, S. B. (Miss)

IEEE Transactions on Pattern Analysis and Machine Intelligence

Online and off-line handwriting recognition: a comprehensive survey

Proceedings of the 12th IAPR International Conference on Pattern Recognition (Cat. No.94CH3440-5)

UNIPEN project of on-line data exchange and recognizer benchmarks

PATRAM: A unifi ed word processing system for handwritten characters in Indian languages

Journal	Proceedings - International Conference on Computing: Theory and Applications, ICCTA 2007
Open Access	No