Zoning invariant holistic recognizer for hybrid recognition of handwriting

As human handwriting is immensely variable, no single recognition approach appears capable of uniformly good performance. Combining results of multiple recognition approaches gives improved recognition rates. Recognizers used in such a hybrid approach need to be different, so that their results are complementary. Segmentation-based and wholistic recognition approaches are methods which are different in principle. This paper describes a wholistic recognizer developed for use in a hybrid recognition system. The recognizer uses information about the word shape. As this information is strongly related to word zoning, care is taken to avoid limitations resulting from the inaccuracy of zoning detection. The recognizer uses a very simple set of features and a fuzzy set based pattern matching technique. This aims to increase its robustness, but also causes problems with disambiguation of the results. A verification mechanism, using letter alternatives as compound features, is introduced. Letter alternatives are obtained from the segmentation based recognizer coexisting in the hybrid system. The wholistic recognizer is found capable of outperforming the segmentation based one, despite the remaining disambiguation problems. When working together in a hybrid system, the results are significantly higher than that of the individual recognizers. Recognition results are reported and compared.