🚀 go-pugleaf

See:  http://amp.ece.cmu.edu/ECESeminar/
      Prof. Tsuhan Chen, Host 2000 ECE Seminar Series                   
        


                          Department of Electrical and Computer Engineering
                                             Seminar Series

                               --------------------------------------
                                     THURSDAY, APRIL 6, 2000
                                             4:00 PM
                                      Refreshments 3:30 PM
                                 Scaife Hall Auditorium, Room 125
                               --------------------------------------


                   ``New Directions for Correlation Based Pattern Recognition''

                                      Dr. Abhijit Mahalanobis
                                 Raytheon Missile Systems Company


                                           ABSTRACT

Correlation filters have proven to be very successful for finding targets in a
variety of sensor imagery such as IR, SAR and LADAR. Consequently, they
have been extensively used for automatic target recognition (ATR). In
this talk, we will 
present a broad overview of the traditional ATR applications and recent
performance results obtained using correlation filters. In addition to
ATR however, correlation filters offer distinct advantages in many novel
application. As an example, one key benefit of correlation filters is
that as linear systems, they are highly compatible
with the subband/wavelet filtering process. This enables a seamless operation
in which pattern recognition and data compression may be viewed as
continuations of
the same process. These concepts will be illustrated using preliminary results
obtained on a subset of the public release MSTAR data.

Another area of potential interest is the application of correlation
filters for
recognizing humans. As part of this talk, we will present a realtime
demonstration
of correlation based face recognition using a closed loop camera system
and COTS processors. 

                                             BIO
                    
Dr. Abhijit Mahalanobis is a Senior Principle Systems Engineer in the
Electro-Optics department at Raytheon. He is currently the technical
head for ATR programs at Raytheon in Tucson. His main interests are in
multi-sensor automatic target recognition, pattern recognition, and
image processing. He has over 80 journal and conference publications in
this area. He has pioneered new approaches in the field of correlation
pattern
recognition which are being pursued by many research groups in the US
and abroad. Abhijit completed his B.S. degree with Honors at the
University of California, Santa Barbara in 1984. He then joined the
Carnegie Mellon University and received the MS. and Ph.D. degrees in
1985 and 1987, respectively. Prior to joining Raytheon, Abhijit worked
at Martin Marietta,Orlando, and was a faculty member at the University
of Arizona. Abhijit is an associate editor for the journal of the
Pattern Recognition Society. He is a frequent reviewer of papers for OSA
and IEEE journals, and serves on the organizing committee for the SPIE
conference in Orlando. Abhijit received the Hughes Business unit Patent
Award in 1998, and was elected a Fellow of SPIE in 1997 for his work on
automatic target recognition. He was also recognized as the Innovator of
the Year by the State of Arizona in 1999, and was elected to the
Raytheon Honors program for distinguished technical contribution and
leadership. He is also listed in the Marquis Who-is-Who in Science and
Engineering.