Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields
International Journal of Computer Vision
Neocognitron and the Map Transformation Cascade
Neural Networks
Neocognitron trained with winner-kill-loser rule
Neural Networks
Invariance analysis of modified C2 features: case study—handwritten digit recognition
Machine Vision and Applications
| Hi-index | 0.00 |
The Neocognitron and its related hierarchical models have been shown to be competitive in recognizing handwritten digits and objects. However, the tolerance of these models to several types of noise can be low. We will start by briefly overviewing some previous results regarding the tolerance of these models. Afterwards, we report the higher noise tolerance of the winner-take-all response in a hierarchical model over related models. We provide an analysis and interpretation of this tolerance under Bayesian decision theory. Finally, we report on how to further improve recognition for extremely noisy patterns.