Fall 2012 GRASP Seminar - Petros Maragos, National Technical University Of Athens, "Morphological And Variational Methods In Image Analysis And Vision"

Presenter: Petros Maragos (Homepage)

Event Dates:
  Friday October 5, 2012 from 11:00am to 12:00pm

This talk presents an overview of some advances in two broad research directions in image analysis and computer vision that share in common the properties of being nonlinear and geometric. The first is based on morphological image operators and their lattice-theoretic generalizations which have a rich algebraic structure. The second approach uses nonlinear PDEs some of which are related to morphological operators and/or are derived from a variational formulation.  Both approaches and often their combination are useful for multiscale edge-preserving smoothing, feature detection, image simplification, structure+texture decomposition, segmentation, and shape analysis.  After a brief synopsis of morphological operators on images and graphs,  we shall continue with their PDE and variational formulation. First we focus on a class of multiscale connected operators with a combined local and global action where the PDE and the lattice approach can harmoniously work together, the first to provide continuous-scale isotropic-growth models with global constraints and the second to study discrete algorithms for numerical implementations. Then, we describe their usage for image simplification, structure+texture decomposition, and PDE-based image segmentation implemented by levelset curve evolution and driven both by watershed flooding and a texture oscillation energy. In an alternative scheme, this energy approach and a modulation image model help us develop an efficient unsupervised segmentation approach using region competition and weighted curve evolution based on probabilistic cue integration. If time permits, we shall also summarize some ongoing work in patch-based PDEs for tensor-based image diffusions using a variational framework.

Presenter's Biography:

Petros Maragos received the Diploma in E.E.  from the National Technical University of Athens (NTUA) in 1980 and the MSc and PhD degrees from Georgia Tech, Atlanta, in 1982 and 1985. In 1985, he joined the faculty of the Division of Applied Sciences at Harvard University, where he worked for eight years as professor of electrical engineering. In 1993, he joined the faculty of the School of ECE at Georgia Tech. Since 1998, he has been working as a professor at the NTUA School of ECE. His research and teaching interests include signal processing, systems theory, pattern recognition, and their applications to image processing and computer vision, speech and language processing, and cognitive systems. He has served as:  Associate Editor for the IEEE Transactions on Acoustics, Speech, and Signal Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence, and editorial board member for the journals Signal Processing, Visual Communications and Image Representation, Mathematical Imaging and Vision; cochair or co-organizer of several conferences and workshops, including VCIP'92, ISMM'96, VLBV'01, MMSP'07, ECCV'10, EUSIPCO'12; member of the IEEE technical committees on DSP, IMDSP and MMSP.

His research has received several awards, including a 1983 Sigma Xi best MSc thesis award, a 1987 National Science Foundation Presidential Young Investigator Award, the 1988 IEEE SPS Young Author Best Paper Award for the paper `Morphological Filters',the 1994 IEEE SPS Senior Best Paper Award and the 1995 IEEE W.R.G. Baker Prize Award for the paper `Energy Separation in Signal Modulations with Application to Speech Analysis', the 1996 Pattern Recognition Society's Honorable Mention Award for the paper `Min-Max Classifiers', the European Association for Signal Processing (EURASIP)’s 2007  Technical Achievement Award for contributions to nonlinear signal, image and speech processing, and the Best Paper Award of the IEEE CVPR-2011 Gesture Workshop.  He was elected a Fellow of IEEE in 1995 and of EURASIP in 2010 for his research contributions.