October 2009
Spotlight Summary by
Efficient estimation of ideal-observer performance in classification tasks involving high-dimensional complex backgrounds
The use of the Bayesian ideal observer approach to image quality assessment can be highly advantageous but has been hampered by computational complexity for real-life statistics. The current procedure develops a fast Markov-chain model for real-time estimation of channelized ideal observer computations.
You must log in to add comments.
Add Comment
You must log in to add comments.
Article Information
Efficient estimation of ideal-observer performance in classification tasks involving high-dimensional complex backgrounds
Subok Park and Eric Clarkson
J. Opt. Soc. Am. A 26(11) B59-B71 (2009) View: Abstract | HTML | PDF