A Modular NMF Matching Algorithm for Radiation Spectra

Melissa Koudelka, Daniel J. Dorsey; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 18-23

Abstract


In real-world object identification systems, the operational mission may change daily. For example, a target recognition system may search for heavy armor one day, and surface-to-air assets the next, or a radiation detection system may be detecting medical isotopes in one instance, and special nuclear material in another. To accommodate this "mission of the day" scenario, the underlying object database must be able to adjust to changing target sets. Traditional dimensionality reduction algorithms rely on a single unifying basis set that is derived from the complete set of objects of interest, making mission-specific adjustment a significant task. We describe a method that instead uses limited-size individual basis sets to represent objects of interest. We demonstrate the modular identification system on the problem of identifying radioisotopes from their gamma ray spectra using nonnegative matrix factorization.

Related Material


[pdf]
[bibtex]
@InProceedings{Koudelka_2016_CVPR_Workshops,
author = {Koudelka, Melissa and Dorsey, Daniel J.},
title = {A Modular NMF Matching Algorithm for Radiation Spectra},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}