GRADIENT-BASED CONTOUR ENCODING FOR CHARACTER-RECOGNITION

We describe novel methods of feature extraction for recognition of sin gle isolated character images. Our approach is flexible in that the sa me algorithms can be used, without modification, for feature extractio n in a variety of OCR problems. These include handwritten, machine-pri nt, grayscale, binary and low-resolution character recognition. We use the gradient representation as the basis for extraction of low-level, structural and stroke-type features. These algorithms require a few s imple arithmetic operations per image pixel which makes them suitable for real-time applications. A description of the algorithms and experi ments with several data sets are presented in this paper. Experimental results using artificial neural networks are presented. Our results d emonstrate high performance of these features when tested on data sets distinct from the training data. Copyright (C) 1996 Pattern Recogniti on Society.