Synthetic Infrared Data For Target…

Summary

The performance of infrared (IR) target identification classifiers, trained on randomly selected subsets of target chips taken from larger databases of either synthetic or measured data, is shown to improve rapidly with increasing subset size and it is shown that subset of data selected with advanced knowledge can significantly outperform randomly selected sets.

Keywords

Classifier (UML), Training set, Computer science, Artificial intelligence, Pattern recognition (psychology)

References

Comparable performance for classifier trained on real or synthetic IR-imagesBruce A. Weber, Joseph Penn — 2001

Cited by

Infrared collects of scale models for automatic target recognitionJacob Ross, Rajith Weerasinghe, Justin Lastrapes — 2024

Related papers

Improved target identification using synthetic infrared imagesBruce A. Weber, Joseph Penn — 2002
A new deterministic validation method for classifier success: Give & TakeBayram Çetişli, Habil Kalkan — 2014
Improving classification with automated selection of a combined classifierM.A. Corona-Nakamura, R. Ruelas — 2002
Empirical comparison of robustness of classifiers on IR imageryPeng Zhang, Jing Peng, Kun Zhang — 2005
An adaptive classifier design for high-dimensional data analysis with a limited training data setQ. Jackson, D. A. Landgrebe — 2001
Better classifier calibration for small datasetsTuomo Alasalmi, Jaakko Suutala, Juha Röning — 2020

Synthetic Infrared Data For Target Identification Training and Testing

Summary

Keywords

References

Cited by

Related papers