The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—We present an approach to automatic construction of structural models incorporating discontinuous transformations, with emphasis on application to unconstrained handwritten character recognition. We consider this problem as constructing <it>inductively, from the data set</it>, some shape descriptions that tolerate certain types of <it>shape transformations</it>. The approach is based on the exploration of complete, systematic, high-level models on the effects of the transformations, and the generalization process is controlled and supported by the high-level transformation models. An analysis of the a priori effects of commonly occurring discontinuous transformations is carried out completely and systematically, leading to a small, tractable number of distinct cases. Based on this analysis, an algorithm for the inference of <it>super-classes</it> under these transformations is designed. Furthermore, through examples and experiments, we show that the proposed algorithm can generalize unconstrained handwritten characters into a small number of classes, and that one class can represent various deformed patterns.</p>
Character recognition, handwriting recognition, learning, shape analysis, shape transformation, structural model.

H. Nishida, "Automatic Construction of Structural Models Incorporating Discontinuous Transformations," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 18, no. , pp. 400-411, 1996.
92 ms
(Ver 3.3 (11022016))