2002 · 11 citations · 7 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDocument Image AnalysisPattern RecognitionRule-based RepresentationWord RecognitionCharacter ClassificationFuzzy Logic ClassificationHandwriting RecognitionHandwritten Character RecognitionOff-line AnalysisTranslation Invariance
This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this approach, the character image is partitioned into a fixed number of sub images called boxes. The features consist of normalized vector distance (/spl gamma/) and angle (/spl alpha/) from each box to a fixed point. The recognition schemes used are back propagation neural network (BPNN) and fuzzy logic. The recognition rate is found to be around 100% with the fuzzy based approach on the standard database.
7