From Pixels to Features III: Frontiers in Handwriting Recognition
Stefano Vittorio Impedovo, Jean Claude Simon · 1992
An algorithm for the recognition of unconstrained handwritten words is proposed. Based on an analysis of writing styles, it is shown that techniques for isolated character recogiritioIi,Segmeni:attOri, as well · ai cursive script recogmtion are needed to achieve a robust solution to handwritten word recognition. A combination of these algorithms is proposed in which the decisions of each method are combined to generate a single consensus ranking of a dictionary of word alternatives. Preliminary results of the implementation of this methodology are given along with future research directions. 1.