DMCA
Class-noise Tolerant Classification Based on a Probabilistic Noise Model
| Citations: | 1 - 0 self |
BibTeX
@MISC{Li_class-noisetolerant,
author = {Yunlei Li and Lodewyk F. A. Wessels and Marcel J. T. Reinders},
title = {Class-noise Tolerant Classification Based on a Probabilistic Noise Model},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Class noise usually means the erroneous labeling of the training examples. In pattern recognition problems, class noise occurs frequently and deteriorates the classifier derived from the noisy dataset. For instance, in some adaptive image segmentation system, the class labels of the training pixels are assigned automatically and sometimes contain errors. Since image segmentation plays a crucial role as a preliminary step for high level image processing, the class noise problem needs to be addressed. This paper presents several possible solutions to this problem based on a probabilistic noise model (LSA). These solutions include the Clustering-based Probabilistic
Keyphrases
probabilistic noise model class-noise tolerant classification class noise crucial role noisy dataset class noise problem class label preliminary step image segmentation several possible solution training pixel clustering-based probabilistic adaptive image segmentation system pattern recognition problem contain error training example erroneous labeling high level image processing
