|Opponent Color Revisited|
|Sabine Süsstrunk, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland|
According to the efficient coding hypothesis, the goal of the visual system should be to encode the information presented to the retina with as little redundancy as possible. From a signal processing point of view, the first step in removing redundancy is de-correlation, which removes the second order dependencies in the signal. This principle was explored in the context of trichromatic vision by Buchsbaum and Gottschalk (1) and later Ruderman et al. (2) who found that linear de-correlation of the LMS cone responses matches the opponent color coding in the human visual system.
And yet, there is comparatively little research in image processing and computer vision that explicitly model and incorporate color opponency into solving imaging tasks. A common perception is that “colors” are redundant and/or too correlated to be of any interest, or that they are too complex to deal with.
In this talk I will illustrate with several simple algorithms, such as saliency and super-pixels, that considering opponent colors can significantly improve image processing and computer vision tasks not only in image enhancement but also image segmentation, image ranking, etc. We have additionally extended the concept of “color opponency” to include near-infrared for applications such as scene recognition, object segmentation, and semantic image labeling.
Prof. Sabine Süsstrunk leads the Images and Visual Representation Lab (IVRL) in the School of Computer and Communication Sciences (IC) at EPFL since 1999. Her main research areas are in computational photography, color image processing and computer vision, multimedia, and image quality. She has a BS in Scientific Photography from ETH Zürich, Switzerland, a MS in Electronic Publishing from the Rochester Institute of Technology (RIT), Rochester, NY, USA, and a PhD on computing chromatic adaptation from the School of Computing Sciences, University of East Anglia (UEA) in Norwich, UK.
From 2003-2004, Sabine was a Visiting Scholar in the Computational Color Reproduction Group at Hewlett-Packard Labs in Palo Alto, CA, USA. From 1995-1999, she was the Principle Imaging Researcher at Corbis Corporation in Seattle, WA, USA. From 1991-1995, she was a Visiting Assistant Professor in the School of Photographic Arts and Sciences at the Rochester Institute of Technology (RIT).
Sabine has authored and co-authored over 140 publications, of which 6 have received best paper/demo awards, and holds 8 patents. She served as chair or committee member in many international conferences on color imaging, digital photography, and image systems engineering (General Chair for the IS&T/SPIE Annual Symposium on Electronic Imaging in 2011, Area Chair for IEEE CVPR 2011, Area Chair for IEEE ICIP 2008, 2009, etc.). She was an Associate Editor for the IEEE Transactions on Image Processing from 2007-2011, the Technical Secretary of the International Color Consortium (ICC) from 2000-2001, Vice-President of IS&T, the Society of Imaging Science and Technology, from 1999-2003 and Conference Vice-President from 2011-2014, Director of CIE Division 8 (Commission Internationale de l'Eclairage, Imaging Technology) from 2007-2011, and member of the ACM E.L. Lawler Award Committee for Humanitarian Contributions within Computer Science and Informatics from 2004-2014.
Sabine is a Fellow of IS&T, senior member of IEEE and ACM, and a member of SPIE and OSA. She is President and member of the board of the EPFL-WISH (Women in Science and Humanities) Foundation. She received the IS&T/SPIE 2013 Electronic Imaging Scientist of the Year Award for her contributions to color imaging, computational photography, and image quality.