An implicit segmentation-based method for recognition of handwritten strings of characters

/in , , /by
An implicit segmentation-based method for recognition of handwritten strings of characters

Cavalin, Paulo Rodrigo and De Souza Britto, Alceu and Bortolozzi, Flávio and Sabourin, Robert and Oliveira, Luiz E.Soares

Proceedings of the ACM Symposium on Applied Computing 2006

Abstract : This paper describes an implicit segmentation-based method for recognition of strings of characters (words or numerals). In a two-stage HMM-based method, an implicit segmentation is applied to segment either words or numeral strings, and in the verification stage, foreground and background features are combined to compensate the loss in terms of recognition rate when segmentation and recognition are performed in the same process. A rigorous experimental protocol shows the performance of the proposed method for isolated characters, numeral strings, and words. Copyright 2006 ACM.

You might also like
Modified feedback linearization controller for pneumatic system with non negligible connection port restriction
Evaluating the conventional and class-modular architectures feedforward neural network for handwritten word recognition
A Classifier-free Ensemble Selection Method based on Data Diversity in Random Subspaces
An off-line signature verification method based on SVM classifier and graphometric features
Constrained-CNN Losses for Weakly Supervised Segmentation
Improving Signature-Based Biometric Cryptosystems Using Cascaded Signature Verification-Fuzzy Vault (SV-FV) Approach
Discriminative sampling of proposals in self-supervised transformers for weakly supervised object localization
An extended-shadow-code based approach for off-line signature verification. I. Evaluation of the bar mask definition