DAGM 2010

Tutorial at DAGM 2010 on Color in Image and Video Processing

21/09/2010, 9:00 - 13:00

This tutorial provides an overview of recent color understanding developments in computer vision. The aim is to provide attendees with a theoretical framework and a set of techniques which allows them to effectively use color information in their applications.

The tutorial is divided into two parts. First, the theoretical foundations of color information will be outlined, such as photometric invariance, color constancy, discriminative power, and color saliency. This will also include a discussion of human color vision and an overview of appropriate color spaces. The second part will focus on the practical usage of color in image and video processing. We will show examples from a number of relevant application areas, such as edge detection, image segmentation, motion detection, object recognition, image and video retrieval, and genre classification. Among others, the results will include Pascal Challenge VOC 2009 image classification results, in which color information plays a pivotal role.

Introduction (30 min)
Theoretical foundations:
a) human color vision
b) color representation and color spaces
c) photometric invariance
d) color constancy
e) color saliency detection
f) color feature detection and description
II. Practical Applications:
a) color image segmentation
b) color for photo editing applications
c) color object recognition (+ PASCAL challenge)
d) color image/video classification.

Organizers:

Joost van de Weijer, Color in Context group (CIC), Computer Vision Center in Barcelona, associated to the Universitat Autònoma de Barcelona

Curriculum Vitae:

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.