Projects / Some projects we are working on

Back to Home »

Reverse Engineering the Visual System

Humans recognize visual objects with such ease that it is easy to overlook what an impressive computational feat this represents. Any given object in the world can cast an effectively infinite number of different images onto the retina, depending on its position relative to the viewer, the configuration of light sources, and the presence of other objects in the visual field. In spite of this extreme variation, biological visual systems are able to effortlessly recognize at least hundreds of thousands of distinct object classes—a feat that no current artificial system can come close to achieving.

Biologically-Inspired Artificial Vision

We’re interested in reverse engineering biological visual systems. However, we would argue that any serious effort to reverse engineer a system should also include a component of forward engineering. For our purposes, this entails attempting to take principles we’ve learned from natural systems and build them into working artificial computer vision systems.

Methods Development

Half of the fun of doing science is devising new tools with which to measure things.

Interested in joining us?

We periodically have openings for Post-Doctoral Fellows, Research Assistants and Summer Students. Contact us for more information.

This site was created to facilitate dissemination of scientific information to the public. Any opinions expressed herein do not necessarily reflect those of Harvard University.

These pages were programmatically generated using the nanoc static site compiler package. For more information about how this site was constructed, see it's source on GitHub.

Recent News

2012-6-15 12:01 Moving on (sort of)

2012-5-20 12:01 Machine learning-based GPU autotuning (new paper)

2011-7-21 11:01 Radio interview on Face Recognition and Privacy on NPR

2011-5-1 12:01 Workshop on Biologically Consistent Computer Vision @ CVPR

2011-3-15 12:01 New Face Recognition Results