We are interested in the computational foundations of vision. This knowledge helps us design machine vision systems with applications to science, conservation, consumer products, entertainment, manufacturing, and defense. We also study the human visual system using psychophysical experiments and build models of its function. At the moment, we are mostly studying visual recognition: How can we recognize frogs, cell phones, sail boats and many other categories in cluttered pictures? How can we learn these categories in the first place? Can we endow machines with the same ability? Can we create a visual interface to Wikipedia, a Visipedia, where pictures are first-class citizens alongside text?
Want to know more about what we do? See our publications on Google Scholar.
Need a letter of reference from Prof. Perona? Use this email address to cc: his assistant profperona.rec.letters@caltech.edu
Interested in applying? See our current openings.
Can’t find the code or data you’re looking for?