Date: Monday, March 18th 2013
Intelligent and Interactive SystemsInstitut für Informatik, Innsbruck
Room: 5161.0267 (Bernoulliborg)
Computational modeling of the visual cortex for object recognition
Computational models of visual processes are of interest in fields such as cybernetics, robotics, computer vision and others. Biological inspiration - and even biological realism - is currently of great interest in the computer vision community. In the past decade we have seen a resurgence of interest in shape and surface representation and analysis in the object recognition literature. An example of this is the special section on Shape Analysis in the April 2010 issue of the IEEE transactions on Pattern Analysis and Machine Intelligence. At the same time, an important number of influential studies in neuroscience have shed new light into how the human brain performs the analysis of visual objects. Due to the latter, several models have appeared which are inspired in a higher or lower degree on how neurons achieve object recognition. By understanding how specific simple objects are analyzed by the brain, we may construct subsystems that emulate that behavior. In a not so far away future, by combining those subsystems we may recognize objects "like" a human.
This seminar will cover some of the advances in neurophysiology over the last few decades and how they relate into building systems and models that can perform object recognition, i.e. what type of visual information and how it is anlayzed in the visual cortex. We will look into how several models achieve this mimicking of the visual cortex flow of information.
References:Pasupathy, A. and Connor, C. (2002). Population coding of shape in area V4. Nature Neuroscience, 5(12):1332-1338.Yamane, Y., Carlson, E., Bowman, K., Wang, Z., and Connor, C. (2008). A neural code for three-dimensional object shape in macaque inferotemporal cortex. Nature Neuroscience, 11(11):1352-1360.Serre, T., Wolf, L., Bileschi, S., and Riesenhuber, M. (2007). Robust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(3):411-426.Rodríguez-Sánchez, AJ and Tsotsos, JK (2012), The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape. PLoS ONE 7 (8), pp. 1-13.
Colloquium coordinators are Prof.dr. M. Aiello (e-mail : M.Aiello rug.nl) and
Prof.dr. M. Biehl (e-mail: M.Biehl rug.nl)
Effective immediately, UG-authors are entitled to a discount when publishing open access in one of the 271 journals from publisher MDPI. Corresponding authors from the UG will receive a 10% discount on the article processing charge. The only...
This year, the University of Groningen has submitted four research projects to compete for the national Klokhuis Science Prize. The aim of this prize is to introduce a young and wide audience to academic research. The winning project will be...
Non-executive directors (hereafter: directors) have to take a critical stance towards the top managers they supervise. This has been the dominant perspective among researchers and the media after the financial crisis of 2008 and recent major...