AFSSI-C: the Adaptive Feature-Specific Spectral Imaging Classifier

AFSSI-C uses adaptive kernels with probabilistically-weighted PCA for spectral imaging classification, reducing error rates by orders of magnitude in simulations.

M.J. Dunlop, Peter A. Jansen, Dathon R. Golish, Michael E. Gehm

Published 20122 citationsPaper ↗

45%

OverallNiche pick

OverallNiche pickVote to see the score

Readers

–

Only vote on papers you've read. Sign in to vote.

AI panel0/20reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Abstract

We have developed an architecture for spectral classification in spectral imaging. Adaptive kernels are designed using probabilistically-weighted principal component analysis. Simulation predicts orders-of-magnitude reduction in error rates, and a prototype system is currently under construction.