Computer vision
Researchers at Penn State span the gamut of vision research, ranging from development of high-level mathematical models for pattern perception to implementation of fast low-level algorithms for real-time video analysis. Particular strengths of the program include medical image analysis, human- computer interaction, video surveillance, texture/pattern analysis, and retrieval from large visual databases.
Aristotle defined vision as the act of knowing what is where by looking. Likewise, the goal of computer vision is to help computers see and interact with the world. Computer vision systems bring together imaging devices, computers, mathematical formalisms and algorithms for solving applied problems in areas such as industrial inspection, medicine, document analysis, autonomous navigation, and remote sensing.
Research Labs/Areas
The Laboratory for Perception, Action and Cognition (LPAC) - Co-Directors: Professors Collins and Liu
LPAC covers a wide range of research topics, including low-level motion
perception, real-time control of active sensors, design of multi-sensor
surveillance networks, analysis of human body motion, recognition of
activities and events, and mathematical modeling of machine and human
texture perception for image understanding and manipulation, dynamic
near-regular texture tracking, and texture-based localization. Current
application areas include moving object detection and tracking from
unmanned air vehicles, recognition of human identity and action within
smart spaces, real-time stereo motion analysis for autonomous
navigation, quantified 3D/4D facial asymmetry for gender/expression
classification, computer aided diagnosis, large biomedical image
database indexing and retrieval, and analysis and synthesis of active
crowds or near-regular textures on deformable media such as cloth or
through transparent fluids.
Multidimensional Image Processing Laboratory (MIPL) - Lead Faculty: Professor Higgins
This lab spans many areas in the general field of imaging science:
digital image processing, computer vision, scientific visualization,
and virtual reality. The group is particularly driven by problems in
high-resolution 3D medical image processing, with a current focus on
virtual endoscopy, image-guided endoscopy, and 3D Micro-CT analysis.
Fifty students have received degrees within the lab. The lab maintains
active collaborations with the Penn State Hershey Medical Center and
the Mayo Clinic (Rochester, MN).
Mathematical Models of Pattern Perception - Investigators: Professors Liu and Li
Much of the visual complexity of the real-world is due to texture. Researchers at Penn State are developing models to analyze and synthesize textures ranging from stochastic to regular, using powerful mathematical tools from group theory and statistics. Applications include image segmentation, classification, compression, texture synthesis, and graphical pattern replacement.
