Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition

Authors:
Hubert Cecotti;Abdel Belad
Affiliations:
LORIA/CNRS Campus Scientifique, France;LORIA/CNRS Campus Scientifique, France
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 5
Cited 3

A Neural Network for Visual Pattern Recognition

Computer
Optimizing Error-Reject Trade off in Recognition Systems

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Rejection Strategies for Offline Handwritten Sentence Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Rejection Strategies for Handwritten Word Recognition

IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition

A novel cascade ensemble classifier system with a high recognition performance on handwritten digits

Pattern Recognition
A novel hybrid CNN-SVM classifier for recognizing handwritten digits

Pattern Recognition
Random subspace support vector machine ensemble for reliable face recognition

International Journal of Biometrics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a rejection strategy for convolutional neural network models. The purpose of this work is to adapt the network's topology in function of the geometrical error. A self-organizing map is used to change the links between the layers leading to a geometric image transformation occurring directly inside the network. Instead of learning all the possible deformation of a pattern, ambiguous patterns are rejected and the network's topology is modified in function of their geometric errors thanks to a specialized self-organizing map. Our objective is to show how an adaptive topology, without a new learning, can improve the recognition of rejected patterns in the case of handwritten digits.