A Use of Continuity in Character Recognition
- 1 May 1974
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. SMC-4 (3), 294-300
- https://doi.org/10.1109/tsmc.1974.5409136
Abstract
Within any given recognition class of handprinted characters, many pairs of characters are related to each other by continuous distortion. It has been usual to exploit this fact by using sequential recognition techniques that would not work if the predominant distortions were discontinuous. This paper introduces a new and highly parallel method of exploiting continuity. This method is shown experimentally to yield lower error rates than a comparable method of recognition that does not take account of continuity.Keywords
This publication has 11 references indexed in Scilit:
- Recognition of printed chinese characters by automatic pattern analysisComputer Graphics and Image Processing, 1972
- A Class of Algorithms for Fast Digital Image RegistrationIEEE Transactions on Computers, 1972
- Automatic recognition of print and scriptProceedings of the IEEE, 1972
- Algorithm for matching 1-dimensional patterns in multidimensional space, with application to automatic speech recognitionElectronics Letters, 1969
- The condensed nearest neighbor rule (Corresp.)IEEE Transactions on Information Theory, 1968
- Experiments with Highleyman's DataIEEE Transactions on Computers, 1968
- Parallel recognition of idealised line charactersKybernetik, 1965
- On-Line Computer Recognition of Handprinted CharactersIEEE Transactions on Electronic Computers, 1964
- A New Method for Automatic Character RecognitionIEEE Transactions on Electronic Computers, 1963
- Recognition of sloppy, hand-printed charactersPublished by Association for Computing Machinery (ACM) ,1960