Issue No. 11 - November (2002 vol. 24)
<p><b>Abstract</b>—A modular system to recognize handwritten numerical strings is proposed. It uses a segmentation-based recognition approach and a Recognition and Verification strategy. The approach combines the outputs from different levels such as segmentation, recognition, and postprocessing in a probabilistic model. A new verification scheme which contains two verifiers to deal with the problems of oversegmentation and undersegmentation is presented. A new feature set is also introduced to feed the oversegmentation verifier. A postprocessor based on a deterministic automaton is used and the global decision module makes an accept/reject decision. Finally, experimental results on two databases are presented: numerical amounts on Brazilian bank checks and NIST SD19. The latter aims at validating the concept of modular system and showing the robustness of the system using a well-known database.</p>
Handwritten numerical string recognition, segmentation and recognition of numerals, recognition and verification, feature extraction, probabilistic model.
C. Y. Suen, F. Bortolozzi, R. Sabourin and L. S. Oliveira, "Automatic Recognition of Handwritten Numerical Strings: A Recognition and Verification Strategy," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 24, no. , pp. 1438-1454, 2002.