By Professor Ganesh Sundaramoorthi (KAUST)
During the past century, engineers have made tremendous progress in constructing devices and algorithms for collecting, storing and transmitting data in the form of images. Such devices and algorithms have out-paced the development of algorithms to automatically understand and interpret the underlying scene that the images capture. The latter is the goal of Computational Vision. Computational Vision remains a challenge of this century, and a significant bottleneck in enabling applications such self-driving cars, virtual reality, scientific data understanding, among many others. Computational Vision remains a challenging problem due to the tremendous variability exhibited in shape and appearance of real-world objects. The problem is further exacerbated by the process of image formation, which adds to the variability in shape and appearance of objects in images. In this talk, I will focus on the fundamental problem of object segmentation, the problem of marking each pixel in the image as belonging to distinct objects of interest. I will show that developing mathematical tools for the processing of shape is a fundamental aspect of segmentation and therefore all of Computational Vision. I will then highlight some of my group’s results in the past years, addressing the construction of shape analysis tools. I will show our state-of-the-art solutions to many segmentation problems, and finally highlight some of our results in applications.
Prof. Ganesh Sundaramoorthi is currently Assistant Professor of Electrical Engineering and jointly Applied Mathematics within CEMSE at King Abdullah University of Science & Technology (KAUST). He is also a member of the Visual Computing Center. His research interests include computer vision and its mathematical foundations. Prior to joining KAUST in 2011, he was a postdoctoral researcher at the University of California, Los Angeles (UCLA), USA in the computer science department. He obtained his PhD in Electrical & Computer Engineering from Georgia Institute of Technology, USA in 2008. He also received the BS in Computer Engineering and BS in Mathematics from Georgia Tech in 2003.
For more info contact: Prof. Ganesh Sundaramoorthi: email: Ganesh.Sundaramoorthi@kaust.edu.sa
Date: Sunday 19th Feb 2017
Time:02:00 PM - 03:00 PM
Location: Location: Building 9, Hall I Room 2322
Refreshments: Refreshments will be available at 1:45 PM