Separating reflections from images by use of independent component analysis
- 1 September 1999
- journal article
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 16 (9), 2136-2145
- https://doi.org/10.1364/josaa.16.002136
Abstract
The image of an object can vary dramatically, depending on lighting, specularities, reflections, and shadows. It is often advantageous to separate these incidental variations from the intrinsic aspects of an image. We describe a method for photographing objects behind glass and digitally removing the reflections from the surface of the glass, leaving the image of the objects behind the glass intact. We describe the details of this method, which employs simple optical techniques and independent component analysis and show its efficacy with several examples.Keywords
This publication has 9 references indexed in Scilit:
- Liquid crystal polarization cameraIEEE Transactions on Robotics and Automation, 1997
- Separation of Reflection Components Using Color and PolarizationInternational Journal of Computer Vision, 1997
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Separation of independent sources from correlated inputsIEEE Transactions on Signal Processing, 1992
- Constraining object features using a polarization reflectance modelIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Polarization-based material classification from specular reflectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- The measurement of highlights in color imagesInternational Journal of Computer Vision, 1988
- Using color to separate reflection componentsColor Research & Application, 1985
- On visual detection of light sourcesBiological Cybernetics, 1976