Hierarchical approach for character recognition

This research mainly focuses on recognizing the handwritten character. Several efficient algorithms have been developed by us so far to separate: the handwritten characters from printed text character, the lines, the words, and each character. In this thesis, we concentrate on how to increase the efficiency of recognition of segmented handwritten characters. Certain characters share common features unique to each other, different from the rest of characters. These subsets of characters with common features are then further analyzed by the classifier thereby reducing the number of comparisons that are required. This results increasing the speed of character recognition