, Volume 19, Issue 2, pp 257–270 | Cite as

Script recognition



This paper describes an approach for word-based on-line and off-line recognition of handwritten cursive script composed of English lower-case letters. The system uses simple and easily extractable features such as the direction of movement and curvature and the relative locations of regions where these suffer discontinuities.

Our approach was evolved based on our concept of ‘shape vectors’ introduced earlier. We visualise script characters as having shapes which are composed of comparatively straight segments alternating with regions of relatively high curvature. We derive the shape vectors from each script character essentially by identifying regions of least curvature and approximating these by straight lines. That these shape vectors carry adequate information about the identity of the character is established by showing that the original character can be faithfully reconstructed from the shape vectors.

We thus use slopes of the shape vectors and relative locations of points of maximum curvature (both highly quantised) as parameters for recognition. The system extracts parameters for individual characters from single specimens written in isolation and uses these to construct feature matrices for words in the vocabulary. These are used for matching with the feature matrices of test words during the recognition phase.

The advantage of the system is that it does not require elaborate training. Recognition scores are in the neighbourhood of 94% for vocabulary sizes of 200 words. The approach has been extended for off-line information as well and performs quite well even in this case.


Character synthesis cursive script feature matrices on-line and off-line recognition overlapping segments script recognition shape vectors tract segments quantisation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bozinovic R M, Srihari S N 1989 Off-line cursive script word recognition.IEEE Trans. Pattern Anal. Machine Intell. PAMI-2: 68–83CrossRefGoogle Scholar
  2. Ehrich W, Koeheler K J 1975 Experiments in the contextual recognition of cursive script.IEEE Trans. Comput. EC-24: 182–195CrossRefGoogle Scholar
  3. Farag R F H 1979 Word-level recognition of cursive script.IEEE Trans. Comput. EC-28: 172–175CrossRefGoogle Scholar
  4. Kundu A, He Y, Bahl P 1989 Recognition of hand-written word: first and second order hidden Markov model based approach.Pattern Recogn. 22: 283–297CrossRefGoogle Scholar
  5. Mantas J 1986 An overview of character recognition methodologies.Pattern Recogn. 19: 425–430CrossRefGoogle Scholar
  6. Mermelstein P, Eden M 1964a A system for automatic recognition of handwritten words.Fall Joint Comput. Conf., AFIPS Conf. Proc. 25Google Scholar
  7. Mermelstein P, Eden M 1964b Experiments on computer recognition of connected handwritten words.Inf. Control. 7: 255–270MATHCrossRefGoogle Scholar
  8. Ramasubramanian V, Rao P V S 1988 Connected script synthesis by character concatenation — An overlap and weighted average formulation.Comput. Sci. Inf. 19: 1–10Google Scholar
  9. Rao P V S 1993 Shape vectors: an efficient parametric representation for the synthesis and recognition of hand script characters.Sādhanā 18: 1–15Google Scholar
  10. Rao P V S, Ramasubramanian V 1991 Connected script synthesis by character concatenation — A Bezier curve based formation.Inst. Electron. Telecommun. Eng. 37: 485–493Google Scholar
  11. Riseman E M, Ehrich R W 1971 Contextual word recognition using binary diagrams.IEEE Trans. Comput. C-20: 397–403CrossRefGoogle Scholar
  12. Sayre K M 1973 Machine recognition of handwritten words: A project report.Pattern Recogn. 5: 213–228CrossRefGoogle Scholar

Copyright information

© Indian Academy of Sciences 1994

Authors and Affiliations

  1. 1.Computer Systems and Communications GroupTata Institute of Fundamental ResearchBombayIndia

Personalised recommendations