Pietro PeronaPietro Perona
Allen E. Puckett Professor of Electrical Engineering and Computation and Neural Systems.

Bio: Professor Perona's research focusses on vision: how do we see and how can we build machines that see.

Professor Perona is currently interested visual recognition, more specifically visual categorization. He is studying how machines can learn to recognize frogs, cars, faces and trees with minimal human supervision, and how machines can learn from human experts. His project `Visipedia' has produced two smart device apps (iNaturalist and Merlin Bird ID) that anyone can use to recognize the species of plants and animals from a photograph.

In collaboration with Professors Anderson and Dickinson, Professor Perona is building vision systems and statistical techniques for measuring actions and activities in fruit flies and mice. This enables geneticists and neuroethologists to investigate the relationship between genes, brains and behavior.

Professor Perona is also interested in studying how humans perform visual tasks, such as searching and recognizing image content. One of his recent projects studies how to harness the visual ability of thousands of people on the web.

Research Group:Computational Vision Laboratory

Research interests:
Computer vision: Recognition, Navigation, Human-Computer interfaces, Texture analysis, Multiresolution image analysis, Diffusions.
Human vision: Perception of shape-from-shading, perception of texture. Models of early vision.

phone: 626.395.2084   office: 104 Moore   address: 1200 E. California Blvd.   mail code: 136-93

Research Projects
Selected Publications
Fall - CNS 187, Neural Computation
Winter - CNS 186, Introduction to Vision
Spring - EE/CS/CNS 148b, Advanced Topics in Computer Vision

Information for prospective post-docs and graduate students

Advising students in the following PhD programs:
Electrical Engineering
Computation and Neural Systems
Computer Science

Control and Dynamical Systems
Computing and Mathematical Sciences

Reaching me by email:
Email is the best way to reach me; unfortunately, I am not terribly efficient in reading all the email I receive.
Sometimes you do not need to reach me directly:

  • for scheduling appointments and time-sensitive issues mail to assistant@vision.caltech.edu
  • for direct communication use perona@caltech.edu. Please summarize the main points of your message in the first paragraph. I only pay attention to the first few lines of each message, so it is best to send separate messages with appropriate titles if you wish to communicate on independent topics.
  • prospective graduate students please read our 'contact' page