Representation of hand written English characters by a sequence of fuzzy sets

In this paper, we describe how to represent lower-case English letters by a sequence of one to seven fuzzy sets. Each fuzzy set represents an arc segment of the character and is a Cartesian product of four fuzzy sets: the first set represents the direction of the arc segment, the second represents the shape of the segment, the third represents the arc length and the fourth represents the direction of change from the previous segment. Starting from a gray-scale image of a character, we describe procedures for thinning the image, extracting a curve describing the writing sequence, smoothing the curve and determining which fuzzy sets it belongs to.