The effect of the inhibition-compensation learning scheme on n-tuple based classifier performance

The inhibition-compensation learning scheme (ICLS) has been proposed as a way of enhancing the performance of the moving window classifier. In the paper the effect of ICLS on three n-tuple based classification techniques has been investigated. Pre-segmented handwritten characters from the NIST database have been used as the pattern data. Results show that approximately 2-6% gain in classification accuracy can be achieved in the OCR task domain with no adverse effect on the classification throughput.