- David and Lucille Packard Professor of Computer Science and Professor of Biomedical Engineering
Computational vision is at the heart of robotics and biomedicine but is still quite primitive when compared with our own visual sense. We effortlessly demonstrate enormous flexibility and generality, which hides its staggering complexity: more than one-third of the primate brain processes visual information. How do we characterize the function of billions of neurons in algorithmic terms? Steven Zucker is putting the requirements of vision systems together with insights from neurophysiology to develop an abstract theory of computational vision. Based on differential geometry, it leads to methods of curve detection, shading and texture analyses, and generic shape description. The key to studying and modeling vision is an interdisciplinary perspective, integrating computation, neuroscience, and mathematics.
Specialized Terms: Computational Neuroscience; Computational Vision
- Coifman, R.R., Maggioni, M., Zucker, S.W., and Kevrekidis, I.G. (2005). Geometric diffusions for the analysis of data from sensor networks. Curr. Opin. Neurobiol. (5):576-84.
- Ben-Shahar, O. and Zucker, S.W. (2004). Hue geometry and horizontal connections. Neural Netw. 17(5-6):753-71.
- Computer Vision
Canada, Italy (2007-Present)
Professor Zucker has collaborations with international colleagues in the area of computer vision, in particular in the mathematical and computational description of visual shape.
McGill University, McGill University, University of Venice Ca' Foscari, University of Venice Ca' Foscari