OSA's Digital Library

Journal of the Optical Society of America A

Journal of the Optical Society of America A

| OPTICS, IMAGE SCIENCE, AND VISION

  • Editor: Franco Gori
  • Vol. 29, Iss. 10 — Oct. 1, 2012
  • pp: 2181–2189

Spectral recovery of outdoor illumination by an extension of the Bayesian inverse approach to the Gaussian mixture model

Shahram Peyvandi, Seyed Hossein Amirshahi, Javier Hernández-Andrés, Juan Luis Nieves, and Javier Romero  »View Author Affiliations


JOSA A, Vol. 29, Issue 10, pp. 2181-2189 (2012)
http://dx.doi.org/10.1364/JOSAA.29.002181


View Full Text Article

Enhanced HTML    Acrobat PDF (787 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

The Bayesian inference approach to the inverse problem of spectral signal recovery has been extended to mixtures of Gaussian probability distributions of a training dataset in order to increase the efficiency of estimating the spectral signal from the response of a transformation system. Bayesian (BIC) and Akaike (AIC) information criteria were assessed in order to provide the Gaussian mixture model (GMM) with the optimum number of clusters within the spectral space. The spectra of 2600 solar illuminations measured in Granada (Spain) were recovered over the range of 360–830 nm from their corresponding tristimulus values using a linear model of basis functions, the Wiener inverse (WI) method, and the Bayesian inverse approach extended to the GMM (BGMM). A model of Gaussian mixtures for solar irradiance was deemed to be more appropriate than a single Gaussian distribution for representing the probability distribution of the solar spectral data. The results showed that the estimation performance of the BGMM method was better than either the linear model or the WI method for the spectral approximation of daylight from the three-dimensional tristimulus values.

© 2012 Optical Society of America

OCIS Codes
(000.5490) General : Probability theory, stochastic processes, and statistics
(100.3190) Image processing : Inverse problems
(330.1690) Vision, color, and visual optics : Color
(330.1730) Vision, color, and visual optics : Colorimetry

ToC Category:
Vision, Color, and Visual Optics

History
Original Manuscript: May 23, 2012
Revised Manuscript: July 29, 2012
Manuscript Accepted: August 13, 2012
Published: September 21, 2012

Citation
Shahram Peyvandi, Seyed Hossein Amirshahi, Javier Hernández-Andrés, Juan Luis Nieves, and Javier Romero, "Spectral recovery of outdoor illumination by an extension of the Bayesian inverse approach to the Gaussian mixture model," J. Opt. Soc. Am. A 29, 2181-2189 (2012)
http://www.opticsinfobase.org/josaa/abstract.cfm?URI=josaa-29-10-2181

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited