RING-PROJECTION-WAVELET-FRACTAL SIGNATURES - A NOVEL-APPROACH TO FEATURE-EXTRACTION

In this brief, we present a novel approach to optical character recogn ition that utilizes ring-projection-wavelet-fractal signatures (RP-WFS ). In particular, the proposed approach reduces the dimensionality of a 2-D pattern by way of a ring-projection method and, thereafter, perf orms Daubechies' wavelet transformation on the derived 1-D pattern to generate a set of wavelet transformation subpatterns, namely, curves t hat are nonself-intersecting. Further, from the resulting nonself-inte rsecting curves, the divider dimensions are readily computed. These di vider dimensions constitute a new feature vector for the original 2-D pattern, defined over the curves' fractal dimensions. We have conducte d several experiments in which a set of printed alphanumeric symbols o f varying fonts and orientation were classified, based on the formulat ion of our new feature vector. The results obtained from these experim ents have consistently shown the character recognition approach with t he proposed feature vector can yield an excellent classification rate of 100%.