Baba C. Vemuri, Ph.D.
Wilson and Marie Collins Professor in Engineering
My research interests span: Statistics on Manifolds, Medical Image Computing, Computer Vision and Graphics, Statistical Learning, Information Geometry and Applied Mathematics. Most of my research these days is concerned with efficient recursive computation of statistics on Riemannian manifolds with applications to atlas (reference template) construction, clustering, data retrieval in Medical Imaging and Computer VIsion and Machine Learning. Further, I have also been developing dynamical systems on matrix manifolds e.g., manifold of symmetric positive definite matrices for real-time tracking applications in Computer Vision. Another interesting problem I have performed extensive research on is mapping out the neuronal fiber tracks from diffusion MR scans of human and vertebrate brains.
I have been involved in developing algorithms and software for the past 15+ years in the field of diffusion MRI analysis with applications to neurodegenerative disorders such as Epilepsy, Parkinson’s, Alzheimers diseases. In Computer Vision, my collaborators and I have developed state-of-the-art face recognition and face relighting algorithms. My earlier work (in the 90’s) was focused on level-set segmentation methods, and my collaborators (Ravi Malladi and James Sethian) and I introduced the geometric active contours in a level-set framework to the field of Computer Vision (SPIE’93, ECCV’94, PAMI’95). My students and I developed fast preconditioned Conjugate Gradient Algorithms for a suite of problems in Computer Vision e.g. surface reconstruction with discontinuities from sparse range data sets, shape from shading, optical flow etc. For more details, I invite you to visit my homepage.
Primary Research Area
Computer Vision & Medical Image Computing
Computer Vision & Medical Image Computing, Image and Signal Analysis
Ph.D., University of Texas at Austin
Rudrasis Chakraborty, Soren Hauberg and Baba C. Vemuri, "Intrinsic Grassmann Averages for Online Linear and Robust Subspace Learning ", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii.
Hyunwoo J. Kim, Nagesh Adluru, Heemanshu Suri, Baba C. Vemuri, Sterling C. Johnson, Vikas Singh, "Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii.
Salem Said, Hatem Hajri, Lionel Bombrun, Baba C. Vemuri, "Gaussian distributions on Riemannian symmetric spaces: statistical learning with structured covariance matrices", IEEE Transactions on Information Theory, 2017.
Monami Banerjee, Bing Jian and Baba C. Vemuri, "Robust Fréchet Mean and PGA on Riemannian Manifolds with Applications to Neuroimaging", International Conference on Information Processing in Medical Imaging (IPMI), 2017, pp. 3-15.
Yuanxiang Wang, Hesamoddin Salehian, Guang Cheng, Baba C. Vemuri, "Tracking on the Product Manifold of Shape and Orientation for Tractography from Diffusion MRI", IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014, pp.3051-3056. [PDF]
Yan Deng, Anand Rangarajan, Stephan J. Eisenschenk, Baba C. Vemuri, "A Riemannian framework for matching point clouds represented by the Schrodinger distance transform", IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014, pp.3756-3761. [PDF]
Hyunwoo J. Kim, Nagesh Adluru, Barbara B. Bendlin, Sterling C. Johnson, Baba C. Vemuri, Vikas Singh, " Canonical Correlation Analysis on Riemannian Manifolds and Its Applications", European Conf. on Computer Vision (ECCV), 2014, pp.251-267. [PDF]
Hesamoddin Salehian, David Vaillancourt, Baba C. Vemuri, "iPGA: Incremental Principal Geodesic Analysis with Applications to Movement Disorder Classification", Intl. Conf. on Medical Image Computing and Computer Aided Intervention (MICCAI), 2014, pp.765-772. [PDF]
Guang Cheng and Baba C Vemuri, "A Novel Dynamic System in the Space of SPD Matrices with Applications to Appearance Tracking", SIAM Journal of Imaging Science vol. 6(1), 2013, pp.592-615. [PDF]
Jeffrey Ho, Guang Cheng, Hesamoddin Salehian and Baba C. Vemuri, "Recursive Karcher Expectation Estimators And Geometric Law of Large Numbers", International Conference on Artificial Intelligence and Statistics (AISTATS'13), 2013, pp.325-332. [PDF]
Dohyung Seo, Jeffrey Ho and Baba C. Vemuri, "Computing Diffeomorphic Paths for Large Motion Interpolation", CVPR , 2013, pp.1227-1232. [PDF]
Dohyung Seo, Jeffrey Ho and Baba C. Vemuri, "Computing Dieomorphic Paths with Applications to Cardiac Motion Analysis", MICCAI Workshop, Mathematical Foundations of Computational Anatomy, 2013, pp.. [PDF]
Yuchen Xie, Jeffrey Ho, Baba C. Vemuri, "Multiple atlas construction from a heterogeneous brain MR image collection", IEEE Trans. on Medical Imaging vol. 32(3), 2013, pp.628-635. [PDF]
Awards & Distinctions
- Best Poster Award, International Conference on Information Processing in Medical Imaging, 2021
- UF Term Professorship, 2021
- Wilson and Marie Collins Professor in Engineering, 2017
- IEEE Computer Society Technical Achievement Award, 2017
- ACM Fellow, 2009
- IEEE Fellow, 2001
- UF Research Foundation Professor 2003-06
- Best Paper IAPR’92
- Best Peer Reviews ECCV’94
- Best poster award IPMI’01 & IPMI’05
- Best paper MICCAI’11