A Review of Feature Extraction Methods for Handwritten Character Recognition

Exploring Feature Extraction Methods for Handwritten Character Recognition

Abstract

This work provides a survey of feature extraction strategies for recognizing segmented (decontextualized)characters when no internet connection is available. Perhaps the most crucial steptoward optimal recognition performance in character recognition systems is settling on a suitablefeature extraction strategy. Each of the many possible character representations from solid binarycharacters to character contours to skeletons (thinned characters) to gray-level subimages of eachcharacter requires a unique set of feature extraction algorithms. We address the invariance qualities,reconstructability, and predicted distortions and variability of the characters of the various featureextraction approaches. The challenge of knowing which feature extraction technique to use when isalso covered. Once a few of interesting feature extraction approaches have been found, they must beexperimentally examined to determine which is best for the specific application at hand.