A Cognitive Model of Character Recognition Using Support Vector Machines

In the present study, a support vector machine (SVM) learning approach to character recognition is proposed. Simple feature detectors, similar to those found in the human visual system, were used in the SVM classifier. Alphabetic characters were rotated to 8 different angles and using the proposed cognitive model, all characters were recognized with 100% accuracy and specificity. These same results were found in psychiatric studies of human character recognition.

Authors:

• K. Freedman

Keywords:

• Character recognition
• cognitive model
• support vector machine learning.

References:

[1] V. K. Govindan, "Character recognition- a review," Pattern
Recognition, vol. 23, no. 7, pp. 671-683, 1990.
[2] J. Cao, M. Ahmadi, and M. Shridhar, "Recognition of handwritten numerals with multiple feature and multistage classifier," Pattern
Recognition, vol. 28, no. 2, pp. 153-160, 1995.
[3] A. Shoeb, H. Edwards, J. Connelly, B. Bourgeois, S. Treves, and J. Guttag, "Patient-specific seizure onset detection," Epilepsy & Behavior, vol. 5, no. 4, pp. 483-498, 2004.
[4] M. Corballis, J. Zbrodoff, L. Shetzer, and P. Butler, "Decisions about
identity and orientation of rotated letters and digits," Memory and Cognition, vol. 6, no. 2, pp. 98-107, 1978.
[5] A. Koriat, J. Norman, and R. Kimchi, "Recognition of rotated letters:
extracting invariance across successive and simultaneous stimuli," Journal of Experimental Psychology, vol. 17, no. 2, pp. 444-458, 1991.
[6] D. Parish and G. Sperling, "Object spatial frequencies, retinal spatial frequencies, noise, and the efficiency of letter discrimination," Vision
Research, vol. 31, no. 7, pp. 1399-1415, 1991.
[7] P. Series, J. Lorenceau, and Y. Fregnac, "The "silent" surround of V1 receptive fields: theory and experiments," Journal of Physiology, vol. 97, pp. 453-474, 2003.