B O S T O N   U N I V E R S I T Y
                      Computer Science Department
                          C O L L O Q U I U M
				and
	  		     PhD Defense 

                   Tuesday, January 23, 2007, 3 pm
                        Seminar Room / MCS 135


                            Jingbin Wang

            Boston University Computer Science Department
               


 
	     Object Segmentation with Shape Constraints


Abstract:

Segmenting and recognizing objects from images in the presence of
noise, clutter and occlusions is an important and challenging problem
in computer vision. Strict low-level, bottom-up techniques that
address this problem cannot provide good interpretations of images for
the purpose of object identification. A solution strategy is to
incorporate high-level prior knowledge, such as shape constraints,
into existing low-level visual routines, a methodology that this
thesis investigates. 
The thesis provides three approaches that are based on variational
approximation, stochastic sampling and dynamic programming,
respectively. The first method applies a shape-based curve-growing
model to segment the major pulmonary fissures on thin-section computed
tomography. 
The employed curve-growing process is influenced by both image
features and prior knowledge of the shape of the fissures. An adaptive
regularization mechanism effectively balances these influences using
an entropy measure. The second method identifies target objects in
images by using prior information about object shape, represented in a
multi-scale curvature form, and by grouping oversegmented image
regions. 
The problem is formulated in a unified probabilistic framework, and
image segmentation and object identification are accomplished
simultaneously by a stochastic Markov Chain Monte Carlo mechanism. The
third method employs Hidden State Shape Models, a variant of Hidden
Markov Models, for detecting instances of object classes that exhibit
variable shape structure. The term "variable shape structure" is used
to characterize object classes in which some object parts can be
repeated an arbitrary number of times, some parts can be optional, and
some parts can have several alternative appearances. 
The thesis presents a detection method for finding instances of object
classes based on dynamic programming. Experimental results for the
three proposed methods suggest that effective object segmentation can
be achieved by introducing shape constraints. 

Committee:
Peter Gacs, Boston University, Committee Chair Margrit Betke, Boston
University, First Reader and Advisor Stan Sclaroff, Boston University,
Second Reader Dimitris N. Metaxas, Rutgers University, Third Reader
Pedro F. Felzenszwalb, University of Chicago, Fourth Reader 

Host:  Margrit Betke