Share Email Print

Proceedings Paper

Statistical learning with imbalanced training set in a machine vision application: improve the false alarm rate and sensitivity simultaneously
Author(s): Jonathan Qiang Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We studied the statistical learning methods with imbalanced training data sets. Imbalanced training sets are very common in industrial machine vision applications. The minority class contains the defects or anomalies we try to catch. The majority class contains the "regular" objects. We need a method that performs well at both false positive and false negative error rates. Traditional methods such as classification tree yield unsatisfactory results. We propose a two-stage classification scheme. We first use a subset selection method to remove redundant examples from the majority class. As a result, the training sample becomes more balanced without losing critical boundary information. The computation-intensive methods such as boosted classification trees are then applied to further improve both error rates.

Paper Details

Date Published: 9 February 2006
PDF: 5 pages
Proc. SPIE 6070, Machine Vision Applications in Industrial Inspection XIV, 607002 (9 February 2006); doi: 10.1117/12.643444
Show Author Affiliations
Jonathan Qiang Li, Agilent Technologies, Inc. (United States)

Published in SPIE Proceedings Vol. 6070:
Machine Vision Applications in Industrial Inspection XIV
Fabrice Meriaudeau; Kurt S. Niel, Editor(s)

© SPIE. Terms of Use
Back to Top