95 articles 

inria-00104310, version 1

Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network

Harold Mouchère () a1, Eric Anquetil () b1

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

Abstract: Different problems of generalization of outlier rejection exist depending of the context. In this study we firstly define three different problems depending of the outlier availability during the learning phase of the classifier. Then we propose different solutions to reject outliers with two main strategies: add a rejection class to the classifier or delimit its knowledge to better reject what it has not learned. These solutions are compared with ROC curves to recognize handwritten digits and reject handwritten characters. We show that delimiting knowledge of the classifier is important and that using only a partial subset of outliers do not perform a good reject option.

  • a –  CNRS
  • b –  Institut National des Sciences Appliquées de Rennes
  • 1:  IMADOC (IRISA)
  • Institut National des Sciences Appliquées (INSA) - Rennes – CNRS : UMR6074 – Université de Rennes 1
  • Domain : Computer Science/Computer Vision and Pattern Recognition
    Computer Science/Document and Text Processing
  • Keywords : Reject options – distance rejection – handwritten symbol recognition
  • Comment : http://www.suvisoft.com
  • inria-00104310, version 1
  • oai:hal.inria.fr:inria-00104310
  • From: 
  • Submitted on: Friday, 6 October 2006 11:48:08
  • Updated on: Wednesday, 14 March 2007 08:56:51