Deakin University
Browse

File(s) under permanent embargo

Multiple illuminant color estimation via statistical inference on factor graphs

journal contribution
posted on 2016-11-01, 00:00 authored by Lawrence Mutimbu, Antonio Robles-KellyAntonio Robles-Kelly
This paper presents a method to recover a spatially varying illuminant color estimate from scenes lit by multiple light sources. Starting with the image formation process, we formulate the illuminant recovery problem in a statistically data-driven setting. To do this, we use a factor graph defined across the scale space of the input image. In the graph, we utilize a set of illuminant prototypes computed using a data driven approach. As a result, our method delivers a pixelwise illuminant color estimate being devoid of libraries or user input. The use of a factor graph also allows for the illuminant estimates to be recovered making use of a maximum a posteriori inference process. Moreover, we compute the probability marginals by performing a Delaunay triangulation on our factor graph. We illustrate the utility of our method for pixelwise illuminant color recovery on widely available data sets and compare against a number of alternatives. We also show sample color correction results on real-world images.

History

Journal

IEEE transactions on image processing

Volume

25

Pagination

5383-5396

Location

Piscataway, N.J.

ISSN

1057-7149

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Copyright notice

2016, IEEE

Issue

11

Publisher

Institute of Electrical and Electronics Engineers