Character Recognition Without Segmentation

A segmentation-free approach to OCR is presented as part of a knowledge-based word interpretation model. This new method is based on the recognition of subgraphs homeomorphic to previously defined prototypes of characters [16]. Gaps are identified as potential parts of characters by implementing a variant of the notion of relative neighborhood used in computational perception. In the system, each subgraph of strokes that matches a previously defined character prototype is recognized anywhere in the word even if it corresponds to a broken character or to a character touching another one. The characters are detected in the order defined by the matching quality. Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternatives of interpretation of the features in the feature graph. A path in the net represents a consistent succession of characters in the word. The method allows the recognition of characters that overlap or that are underlined. A final search for the optimal path under certain criteria gives the best interpretation of the word features. The character recognizer uses a flexible matching between the features and a flexible gronping of the individual features to be matched. Broken characters are recognized by looking for gaps between features that may be interpreted as part of a character. Touching characters are recognized because the matching allows nonmatched adjacent strokes. The recognition results of this system for over 24,OOO printed numeral characters belonging to a USPS database and on some hand-printed words confirmed the method’s high robustness level. Index Tenns-Character recognition without segmentation, broken character recognition, touching character recognition, homeomorphic subgraph matching, relative neighborhood graph.