Vijayakumar Bhagavatula
U.A. and Helen Whitaker Professor, Electrical and Computer Engineering
Affiliated Faculty, DSSC
Director, CMU - Africa
Download Hi-res Photo
Bio
Vijayakumar (Kumar) Bhagavatula is the U.A. and Helen Whitaker Professor of Electrical and Computer Engineering. He received a B.Tech. degree in electrical engineering from the Indian Institute of Technology, Kanpur in 1975, an M.Tech. degree in electrical engineering, also from the Indian Institute of Technology, Kanpur in 1977, and a Ph.D. in electrical engineering from Carnegie Mellon University in 1980. He joined the faculty of Electrical and Computer Engineering in 1982. He has served as interim dean for the College of Engineering and as acting department head of Electrical and Computer Engineering.
Education
Ph.D., 1980
Electrical Engineering
Carnegie Mellon University
MTech, 1977
Electrical Engineering
Indian Institute of Technology, Kanpur
BTech, 1975
Electrical Engineering
Indian Institute of Technology, Kanpur
Research
Pattern Recognition for Biomerics
One way of matching live biometric signatures (e.g., face images, iris images) with stored templates is to correlate the two. Professor Kumar and his students are developing several spatial frequency-domain methods to perform these correlations in the presence of significant appearance variability (e.g., due to illumination changes, expression differences, etc.) in the biometric signatures. These correlation filters have performed very well in the recent Face Recognition Grand Challenge (FRGC) and Iris Challenge Evaluation (ICE) conducted by US National Institute of Standards and Technology (NIST).
Coding & Signal Processing for Data Storage
As we attempt to increase the densities of data storage systems, bits and tracks come much closer, causing increased intersymbol interference and noise. Advanced coding and signal-processing methods are being developed to provide reliable (i.e., low bit error rate) detection of the digital data stored on various media. Professor Kumar's research considers timing recovery methods and the equalization and detection of data recorded on high-density magnetic tape recording systems, holographic data storage systems and optical storage systems. His group is also investigating the use of low density parity check (LDPC) codes for data storage systems.
Keywords
- Coding and signal processing for data storage
- Biometrics
- Pattern recognition
- Computer vision
- Data mining
- Data storage systems
- Machine learning