--------------------------------------------------------------------------------------------------------------------
My Research At Stanford University
Salih
Burak Göktürk
Stanford University
--------------------------------------------------------------------------------------------------------------------
In this talk, I will present some highlights of the research that I
conducted during my PhD at Stanford University. The main theme of my
thesis is the recognition process. Recognition is one of the main tasks
of both human and computer vision. We address the recognition process
by a combination of two tasks: feature estimation and statistical
classification. My projects fit in this framework, while we use different
features for various applications.
The first project that I will discuss is the face-tracking project.
We designed a model-based monocular face tracking system that tracks the
pose and deformations of face in 3D. The output of the tracking system is
a shape vector, which is used as the feature for a facial expression
recognition system. These features are fed to a support vector machine
classifier for the classification of the facial expressions.
The second project of this talk is the recognition of 3D shapes from
computed tomography (CT) with application to detection of various cancers.
For the feature estimation stage of this project, we designed a new 3D
shape representation, called Random Orthogonal Shape Sections (ROSS)
descriptor. This descriptor utilizes a random set of triples of mutually
orthogonal planar sections through the shape. The statistics obtained
over a sufficiently large number of random triples provides invariant and
diagnostic descriptors (representation) of the shape. The descriptors
are used as features by a support vector machine classifier for the
recognition of various cancerous tissues.
Information about these projects and various publications can be found at:
http://robotics.Stanford.edu/~gokturkb