FUZZY BASED RECOGNITION OF HANDWRITTEN ARABIC NUMERALS

Human generated patterns like handwritten characters are found to be fuzzy in nature upto certain extent. Thispresented work proposes a fuzzy conceptual approach to classify Handwritten Arabic Numerals based on invariant momentsfeatures and the divisions of numeral image into several parts. The Moment invariants features are well known forindependence of size, slant, orientation, translation and other variations of handwritten characters. A database, created byAmerican University in Cairo, of 7000 samples of each number from 700 different writers is used. Each image is normalized to40X40 pixel size. Seven central invariant moments are evaluated for each image and its parts by dividing it by three differentways, i.e. three feature groups. The algorithm is experimented for 500 samples of each numeral image and 161 features wereevaluated corresponding to each image. The performance rate of the method is found to be 95.14%.