Automatic recognition of handwritten numerical strings: a recognition and verification strategy
Authors:
- F. BortolozziFBF. Bortolozzi
- C.Y. SuenCSC.Y. Suen
- 1 November 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 24 (11) , 1438-1454
Abstract
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.Keywords
This publication has 25 references indexed in Scilit:
- Reject option with multiple thresholdsPattern Recognition, 2000
- Segmentation of single- or multiple-touching handwritten numeral string using background and foreground analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Automated Reading of Cheque AmountsPattern Analysis and Applications, 2000
- Integrated segmentation and recognition of handwritten numerals with cascade neural networkIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 1999
- Integration of structural and statistical information for unconstrained handwritten numeral recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Off-line handwritten numeral string recognition by combining segmentation-based and segmentation-free methodsPattern Recognition, 1998
- Off-line, handwritten numeral recognition by perturbation methodIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Document image decoding using Markov source modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991
- Recognition of isolated and simply connected handwritten numeralsPattern Recognition, 1986