Fast Convolutional OCR with the Scanning N-Tuple Grid
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Identity Management in Face Recognition Systems
Biometrics and Identity Management
Orientational features with the SNT-grid
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Human face analysis: from identity to emotion and intention recognition
ICEB'10 Proceedings of the Third international conference on Ethics and Policy of Biometrics and International Data Sharing
| Hi-index | 0.00 |
The Scanning N-Tuple classifier (SNT) is a fast and accurate method for classifying sequences.Applications include both on-line and off-line hand-written character recognition.SNTs have conventionally been trained using maximum likelihood parameter estimation.This paper describes a disciminative training rule that can be applied to ensembles of SNTs.Results demonstrate a significant improvement for the discriminative ensemble method.For comparison purpose we also implemented a Support Vector Machine (SVM) operating in the sequence domain.We tested each method on a chain-coded version of the MNIST hand-written digit dataset.The SNT is not quite as accurate as the SVM, but is much faster both in training and recognition.