Rejection Strategies and Confidence Measures for a k- NN Classifier in an OCR Task

In Handwritten Character Recognition, the rejection of extraneous patterns, like image noise, strokes or corrections, can improve significantly the practical usefulness of a system. In this paper, a combination of two confidence measures defined for a k-nearest neighbors classifier is proposed. Experiments are presented comparing the performance of the same system with and without the new rejection rules.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: Javier Cano, Joaquim Arlandis, Juan Carlos Pérez-Cortes
• Keywords: Computer Vision, Handwritten Character Recognition, ICPR 2002, K-nearest Neighbors