A two-stage HMM-based system for recognizing handwritten numeral strings

/in , , /by
A two-stage HMM-based system for recognizing handwritten numeral strings

De Britto, Alceu S. and Sabourin, Robert and Bortolozzi, Flavio and Suen, Ching Y.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 2001

Abstract : In this paper we propose a handwritten numeral string recognition method composed of two HMM-based stages. The first stage uses an implicit segmentation strategy based on string contextual information to provide multiple segmentation-recognition paths. These paths are verified and re-ranked by using a Verification stage based on a digit classifier. It allows the use of two sets of features and numeral models: one taking into account of both segmentation and recognition aspects in an implicit segmentation based strategy, and another considering just recognition aspects of isolated digits. The two system stages have shown to be complementary in the sense that the Verification stage has shown to be a promising idea to deal with the loss in terms of recognition performance brought by the necessary tradeoff between segmentation and recognition carried out in the first system stage.

You might also like
Mixup-privacy: A simple yet effective approach for privacy-preserving segmentation
Combining Hidden Markov Models for improved anomaly detection
Keypoint transfer segmentation
Unsupervised feature learning for environmental sound classification using weighted cycle-consistent generative adversarial network
A partition constrained minimization scheme for efficient multiphase level set image segmentation
Classification of cancerous cells based on the one-class problem approach
Optimization of HVAC control system strategy using two-objective genetic algorithm
Unsupervised domain adaptation in the dissimilarity space for person re-identification