In this tutorial we address theory and techniques to optimally exploit available color information from the digital camera processing pipeline up to high-level color image understanding. The aim is to provide attendees with basics on color theory and a practical set of techniques which allow to effectively use color information in computer vision applications. We will show that color information is a powerful tool for image understanding.
Tentative List of Topics
The course is divided into three parts. First, this tutorial addresses key technical challenges to imaging pipeline design presented by demands such as shrinking device footprints, increasing throughput, and enhancing color fidelity. Next, the fundamentals of color image processing will be outlined, such as color representation and reflection models, photometric invariance, color constancy, and color saliency. The third part of the course will focus on the practical usage of color in computer vision applications. We will show examples from a number of relevant application areas, such as edge detection, image segmentation, motion detection and object tracking, object recognition, image and video retrieval, and scene classification.
I. Introduction and Color Image Acquisition in Practice (1hr)
- Color Image Sensor.
- Chrominance/luminance decompositions and demosaicking algorithms.
- Approaches to denoising before, during, and after demosaicking.
- Color fidelity issues due to noise and crosstalk.
II. Color Image Processing fundamentals(1hr)
- Dichromatic Reflection model.
- Photometric Invariance Color Features.
- Color Constancy.
- Color Saliency.
- Color Image Segmentation.
- Color in Motion and Tracking.
- Color for Object Recognition.
- Color in Image/video Classification.
SLIDES: A pdf-version of the slides
is available for Part II and III.
LINKS: Relevant color research related to the research of the organizers:
- applied in winning VOC PASCAL 2008 image classification challenge.
- links and software.
- Some matlab for color image processing.
- on color image and video processing.
- The workshop on Color in Photometry in Computer Vision Workshop (CPCV) at ICCV 2011.
Biography : Theo Gevers
Theo Gevers is an associate professor of
computer science at the University of Amsterdam,
The Netherlands, where he is also the
teaching director of the MSc in Artificial Intelligence.
He currently holds a VICI Award (for
research excellence) from the Dutch Organisation
for Scientific Research. His main research
interests are in the fundamentals of contentbased
image retrieval, color image processing,
and computer vision, specifically in the theoretical
foundation of geometric and photometric invariants. He is the chair
for various conferences and is an associate editor for the IEEE
Transactions on Image Processing. Further, he is a program committee
member for a number of conferences, and an invited speaker at major
conferences. He is a lecturer delivering postdoctoral courses given at
various major conferences (CVPR, ICPR, SPIE, and CGIV).
biography : Keigo Hirakawa
Keigo Hirakawa has been involved with camera and sensor development efforts at Hewlett-Packard, Agilent Technologies, Sony, Texas Instruments, Air Force Research Laboratories, and Draper Laboratories. The AHD demosaicking algorithm that he developed is one of the most popular and widely used methods by photo enthusiasts today. Recognitions for his work in digital camera research include the IEEE ICIP 2007 DoCoMo paper award and keynote speeches at IS&T CGIV, PSCJ 2009, and IAPR CCIW 2011. Dr. Hirakawa has received the B.S. degree from Princeton University in 2000; the M.S. and Ph.D degrees from Cornell University in 2003 and 2005, respectively; and the M.M. in Jazz Performance from the New England Conservatory of Music in 2006. He was a research fellow at Harvard University from 2006 to 2009 before joining University of Dayton as an assistant professor in 2010.
biography : Joost van de Weijer
Joost van de Weijer is a Ramon y Cajal fellow in the Color in Context group (CIC) in the Computer Vision Center in Barcelona. He received his M.Sc. degree in applied physics at Delft University of Technology in 1998. In 2005, he obtained the Ph.D. degree at the University of Amsterdam. From 2005-2007 he was a Marie Curie Intra-European Fellow in the LEAR team at INRIA Rhone-Alpes in France. His main research is usage of color information in computer vision application. He has published in the fields of color constancy, color feature extraction and detection, color image filtering, color edge detection, and color naming.