Handwritten Word Recognition Using Multi-view Analysis
This paper brings a contribution to the problem of efficiently recognizing handwritten words from a limited size lexicon. For that, a multiple classifier system has been developed that analyzes the words from three different approximation levels, in order to get a computational approach inspired on the human reading process. For each approximation level a three-module architecture composed of a zoning mechanism (pseudo-segmenter), a feature extractor and a classifier is defined. The proposed application is the recognition of the Portuguese handwritten names of the months, for which a best recognition rate of 97.7% was obtained, using classifier combination.
KeywordsHide Markov Model Perceptual Feature Word Context Word Image Forward Algorithm
- 1.Schomaker, L., Segers, E.: A Method for the Determination of Features used in Human Reading of Cursive Handwriting. In: IWFHR 1998, The Netherlands, pp. 157–168 (1998)Google Scholar
- 5.Madhvanath, S., Govindaraju, V.: The Role of Holistic Paradigms in Handwritten Word Recognition. IEEE Trans. on PAMI 23(2), 149–164 (2001)Google Scholar
- 7.de Almendra Freitas, C.O., Bortolozzi, F., Sabourin, R.: Handwritten Isolated Word Recognition: An Approach Based on Mutual Information for Feature Set Validation. In: ICDAR 2001, Seattle - USA, pp. 665–669 (2001)Google Scholar
- 8.Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On Combining Classifiers. IEEE Trans. on PAMI 20(3), 226–239 (1998)Google Scholar