Home | Biodata | Biography | Photo Gallery | Publications | Tributes

Character Recognition


On Character Recognition

Dr. Gift Siromoney had varied interests from archaeology to Theoretical Computer Science. He believed more in application than in theory. As Newton discovered the gravitational force by observing an apple falling down, Dr. Gift always started from the application and proposed theory based on that. Dr.Gift Siromoney, Dr.M.Chandrasekaran, and myself were travelling from Tambaram by an electric train to catch a train to Calcutta to attend an International Conference on Recent Trends and Developments in Pattern Recognition held at the Indian Statistical Institute in the year 1977. When nearing Pallavaram Hills, Dr. Gift Siromoney had hit upon a novel method of feature extraction from two-level digital pictures containing 0's for the background and 1's for the area covered by the letter, which he immediately told us. During the travel from Chennai Central to Howrah, we had almost finalized the procedure in the train itself. He said that the machine should be made to work like a machine. He proposed a scheme of encoding rows and columns in two-level digital pictures in terms of the number of runs of 1's. This resulted in a pair of feature strings for a digital picture. Normally, in pattern recognition problems, thinning the given pattern is carried out as a preprocessing method, before the feature extraction takes place. However, condensing or shrinking the feature string by replacing a substring of a symbol by a single occurrence of that symbol, really made the condensed feature strings independent of magnification and elongation of the digital pictures. This invariant property was very useful in recognizing various characters belonging to different languages. Whenever ties were observed, they were resolved by considering special coding schemes for the rows and columns that had a single run of 1's. This method of encoding two-level digital pictures resulted in a pair of very small strings, one corresponding to the rows and the other to columns,  called 'The Condensed Run Method'.

The Condensed Run Methods were successfully applied first to the Printed Tamil Characters, and then to the characters belonging to multiple fonts. The subsequent study of the problem of hand-printed characters met with great success. Later, the problems of computer recognition of printed numerals and automatic recognition of printed mridangam (a leather-based musical drum) mnemonics were taken up and solved. As we were also working on the ancient Tamil writings during that period, computer recognition of an ancient Chola script of the medieval period was considered and implemented. After that, character recognition of the Brahmi script (circa 300 B.C.) was taken up and completed. The department of Electronics Commission of India sanctioned a project to implement the automatic recognition of Tamil, Malayalam and Devanagari scripts which was successfully completed. Apart from pattern recognition, dating of medieval Tamil inscriptions and writer identification were also taken up for study.

- R. Chandrasekaran (B.Sc. and M.Sc. 1972-76, Ph.D, 1982)
Current Affiliation: Professor, Department of Statistics, Madras Christian College.

Publications

  1. Computer methods of dating medieval Tamil inscriptions
    STAT-26/76,  paper presented at the Third Annual Congress of the Epigraphical Society of India at Udupi, March 1978, (with Chandrasekaran, M. and Chandrasekaran, R.).  
  2. Computer methods of writer identification: an application to Tamil handwriting
    STAT-28/77, 1977 - paper presented at the All India Interdisciplinary Symposium on Digital Techniques and Pattern Recognition, Indian Statistical Institute, Calcutta, February 1977, (with Chandrasekaran, M. and Chandrasekaran, R.)  READ
  3. Computer recognition of printed Tamil characters
    STAT-32/77, October 1977, paper presented at the Annual Conference of the Computer Society of India, February 1978 and in Pattern Recognition, Vol. x No. 4, pp. 243-247, 1978, (with Chandrasekaran, M. and Chandrasekaran, R.)  
  4. Computer recognition and transliteration of mridangam mnemonics
    STAT-33/77, Decembar 1977, paker presented at the fiftyfirst annual conference of the Music Academy, Madras, Also, Quarterly Journal of the National Centre for the Performing Arts, vii, pp11-17, 1978 (with Chandrasekaran, M. and Chandrasekaran, R.)  READ
  5. Computer recognition of an ancient Tamil script of the Chola period
    Journal of the Epigraphical Society of India, Vol. vi, pp 18-19, 1978, (with Chandrasekaran, M. and Chandrasekaran, R.)  READ
  6. Computer recognition of printed numerals: A study in artificial intelligence
    MCC Mag.  Vol. xlviiI, 1978 (with Chandrasekaran, M. and Chandrasekaran, R.)  READ   
  7. Computer recognition of an ancient common Indian Script
    STAT-36/78, March 1978, paper presented at the Symposium on the Use of Indian Languages in  Computer based Information Systems, New Delhi, April 1978
  8. Computer recognition of South Indian musical scores
    MCC Mag., Vol. xlix, 1980 (with Chandrasekaran, R. and Chandrasekaran, M.)  READ
  9. Machine recognition of hand printed Tamil musical notation
    STAT-41/80 also paper presented at the Annual Conference of the Computer Society of India. February 1980, Bombay (with Chandrasekaran, M. and Chandrasekaran, R.)  READ
  10. Computer methods of dating Tamil inscriptions
    STAT-43/80, January 1980, Proceedings of Fifth International Tamil Conference held at Madurai, January 1981, pp2. 7-2.13, The Hindu, Friday, January 9, 1981(with Chandrasekaran, M. and Chandrasekaran, R.)
  11. Computer translation of South Indian music into staff notation
    Proceedings of the International Symposium on Microwaves and Communication, IIT Kharagpur, 29-30,December 1981, pp. 170-173(with Chandrasekaran, M. and Chandrasekaran, R.)  READ  
  12. Computer dating of medieval inscriptions: South Indian Tamil
    Computer and the Humanities, Vol. 17, 1983, pp. 199-208 (with Chandrasekaran, M. and Chandrasekaran, R.)  READ
  13. Context-dependent recognizer for hand printed Tamil characters
    Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Bombay-New Delhi, Vol. II, 1983, pp 786-790, (with Chandrasekaran, M. and Chandrasekaran, R.) 
  14. Computer recognition of Tamil, Malayalam and Devanagari characters
    Journal of the Institution of Electronics and Telecommunication Engineers, Vol. 30, No.6, pp150-154b, 1984, (with Chandrasekaran, M. and Chandrasekaran, R.)  
  15. Machine recognition of hand-printed Tamil characters
    Advances in Information Sciences and Technology, (Ed. Dutta Majumder), Vol. I, pp 147-154, 1984, (with Chandrasekaran, M. and Chandrasekaran, R.)  
Go to the top of the page

Home | Biodata | Biography | Photo Gallery | Publications | Tributes