Issue No. 09 - September (1995 vol. 17)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.406657
<p><it>Abstract</it>—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 [<ref rid="BIBP090316" type="bib">16</ref>]. 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 grouping of the individual features to be matched. Broken characters are recognized be 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 24,000 printed numeral characters belonging to a USPS database and on some hand-printed words confirmed the method’s high robustness level.</p>
Character recognition without segmentation, broken character recognition, touching character recognition, homeomorphic subgraph matching, relative neighborhood graph.
J. Rocha and T. Pavlidis, "Character Recognition Without Segmentation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 17, no. , pp. 903-909, 1995.