Photon-limited image denoising by inference on multiscale models

Lefkimmiatis, S; Papandreou, G; Maragos, P

dc.contributor.author	Lefkimmiatis, S	en
dc.contributor.author	Papandreou, G	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:45:44Z
dc.date.available	2014-03-01T02:45:44Z
dc.date.issued	2008	en
dc.identifier.issn	15224880	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32356
dc.subject	Bayesian inference	en
dc.subject	Expectation-Maximization algorithm	en
dc.subject	Hidden Markov tree	en
dc.subject	Photon-limited imaging	en
dc.subject	Poisson	en
dc.subject.other	Bayesian inference	en
dc.subject.other	Expectation-Maximization algorithm	en
dc.subject.other	Hidden Markov tree	en
dc.subject.other	Photon-limited imaging	en
dc.subject.other	Poisson	en
dc.subject.other	Algorithms	en
dc.subject.other	Bayesian networks	en
dc.subject.other	Edge detection	en
dc.subject.other	Image segmentation	en
dc.subject.other	Imaging systems	en
dc.subject.other	Inference engines	en
dc.subject.other	Maximum likelihood estimation	en
dc.subject.other	Maximum principle	en
dc.subject.other	Mixtures	en
dc.subject.other	Optimization	en
dc.subject.other	Photons	en
dc.subject.other	Poisson equation	en
dc.subject.other	Poisson distribution	en
dc.title	Photon-limited image denoising by inference on multiscale models	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2008.4712259	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2008.4712259	en
heal.identifier.secondary	4712259	en
heal.publicationDate	2008	en
heal.abstract	We present an improved statistical model of Poisson processes, with applications to photon-limited imaging. We build on previous work, adopting a multiscale representation of the Poisson process in which the ratios of the underlying Poisson intensities (rates) in adjacent scales are modeled as mixtures of conjugate parametric distributions. Our main novel contributions are (1) a rigorous and robust regularized Expectation-Maximization (EM) algorithm for maximum-likelihood estimation of the rate-ratio density parameters directly from the observed Poisson data (counts); (2) extension of the method to work under a scale-recursive Hidden Markov Tree model (HMT) which couples the mixture label assignments in consecutive scales, thus modeling inter-scale coefficient dependencies in the vicinity of edges; and (3) exploration of a fully 2-D quad-tree image partitioning, involving Dirichlet-mixture rate-ratio densities, instead of the conventional separable binary image partitioning involving Beta-mixture rate-ratio densities. Experimental intensity estimation results on standard images with artificially simulated Poisson noise and photon-limited images with real shot noise demonstrate the effectiveness of the proposed approach. © 2008 IEEE.	en
heal.journalName	Proceedings - International Conference on Image Processing, ICIP	en
dc.identifier.doi	10.1109/ICIP.2008.4712259	en
dc.identifier.spage	2332	en
dc.identifier.epage	2335	en