A Novel Fuzzy Classifier using Fuzzy LVQ to Recognize Online Persian Handwriting

Fuzzy logic is a powerful tool to represent imprecise and irregular patterns. This paper presents a novel fuzzy approach for recognizing online Persian (Farsi) handwriting. In this approach, a fuzzy classifier is introduced that uses a combination of the fuzzy LVQ learning model and the expert knowledge. This method applies an FLVQ network to distinguish between the similar tokens that appear at the end of the strokes. For other tokens, fuzzy linguistic terms are used to describe their features. The purposed method was run on a database of Persian isolated handwritten characters and achieved a high recognition rate compared to other available approaches