Bayesian Perceptual Grouping: Competence and Performance
Dr. Jacob Feldman
Tuesday, March 27, 2012, 01:00pm - 02:00pm
Rutgers University, Department of Psychology and Center for Cognitive Science
Perceptual grouping is the process by which the visual system organizes the image into distinct clusters or units. In this talk I'll sketch a Bayesian approach to grouping, formulating it as an inverse inference problem in which the goal it to estimate the organization that best explains the observed configuration of visual elements. We formulate the problem as an instance of mixture modeling, in which the image configuration is assumed to have been generated by a set of distinct data-generating components or sources (``objects''), whose locations and structure we seek to estimate. I'll separately describe the competence theory (theory of the computation), which formally identifies the grouping interpretation that the visual system selects; and steps towards a performance theory, which lays out a computational strategy for effectively approximating that interpretation with available computational mechanisms, including local evidential support and neural connectivity.
Joint work with Manish Singh, Vicky Froyen, Seha Kim, and John Wilder.
Note: If you would like to receive email announcements about the colloquium series, please contact the Business Office to have your name added to our announce lists at firstname.lastname@example.org.