Local context in non-linear deformation models for handwritten character recognition
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 511-514 Vol.4
- https://doi.org/10.1109/icpr.2004.1333823
Abstract
We evaluate different two-dimensional non-linear deformation models for handwritten character recognition. Starting from a true two-dimensional model, we derive pseudo-two-dimensional and zero-order deformation models. Experiments show that it is most important to include suitable representations of the local image context of each pixel to increase performance. With these methods, we achieve very competitive results across five different tasks, in particular 0.5% error rate on the MNIST task.Keywords
This publication has 13 references indexed in Scilit:
- Best practices for convolutional neural networks applied to visual document analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Handwritten character recognition using elastic matching based on a class-dependent deformation modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Classification of Medical Images Using Non-linear Distortion ModelsPublished by Springer Nature ,2004
- Eigen-deformations for elastic matching based handwritten character recognitionPattern Recognition, 2003
- A monotonic and continuous two-dimensional warping based on dynamic programmingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Training Invariant Support Vector MachinesMachine Learning, 2002
- Experiments with an extended tangent distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Probabilistic Principal Component AnalysisJournal of the Royal Statistical Society Series B: Statistical Methodology, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Keyword spotting in poorly printed documents using pseudo 2-D hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994