Visit Your Local PBS Station PBS Home PBS Home Programs A-Z TV Schedules Watch Video Donate Shop PBS Search PBS
SAF Archives  search ask the scientists in the classroom cool science
scientists from previous shows
cool careers in science
ask the scientists
PREVIOUS SCIENTISTS

Photo of Prof. Picard ROSALIND PICARD

Rosalind Picard is NEC Development Professor of Computers and Communications Associate Professor of Media Technology. Her research interests are: Affective Computing (Newest Area); Texture and Pattern Modeling; and Video and Image Libraries: Browsing, Retrieval, Annotation.

Here are descriptions of Picard's current research projects:


Affective Computing

Emotions are a natural and significant part of human interaction; moreover, recent neurological evidence indicates that emotions are not a luxury, but play a critical role in intelligent and rational decision-making. Whether used to indicate like/dislike or interest/disinterest, emotion plays a key role in multimedia information retrieval, user-preference modeling, and human-computer interaction. Affective computing is computing that relates to, arises from, or deliberately influences emotions. The focus of this research is on giving computers the ability to recognize, express, and have emotions. An example is computers (or other "smart things") that detect the interest, frustration, or pleasure of their user.

Smart Clothes
(Project with Professor Alex Pentland)

Smart Clothes act like human assistants. By building microprocessors, cameras, microphones, and wireless communication into clothing we can help users get around in the world. We have already built demonstrators that can help you remember people's names and help you find your way around town. We are now working with clothing designers to make these devices not only helpful, but also fashionable and attractive.

Smart Desks
(Project with Professor Alex Pentland and Professor Pattie Maes)

Smart Desks are a type of Smart Room, but specialized for the business environment. The goal of the Smart Desk project is to develop a desk that acts like a good office assistant. Such a desk should know your work habits and preferences, remember where you put things, know when you are feeling frustrated or tired, and know enough about your work to anticipate many of your needs. The Smart Desks project will try to accomplish this by using cameras, microphones, and biosensors to monitor you as you work, and active agents technology to figure out how to help.

Video and Image Libraries: Representation and Retrieval

This project aims to give computers the ability to "see" the content of image and video, enabling them to help in tasks such as annotation, retrieval, browsing, and editing of large collections of imagery. For example, a computer might "find another video clip like this one, but shot from another angle," or "find a video clip of me on the beach." Recent results include a smart browsing system and a system that assists people in annotating image and video by learning associations between content and labels they provide.

Learning Subjectivity

How do people prefer to browse digital libraries of image and video? There does not seem to be one answer, but rather, there are many reasonable paths people take. This work focuses on new learning algorithms that interact with people and the data that interests them, learning associations where they are helpful.

WearCam: Video Orbits for Visual Memory

We are building a wearable, wireless, head-mounted video camera (WearCam) for diverse uses such as a hands-free sports camera or a system for augmenting visual memory. However, the digital video processing problems are immense. This research explores combinations of physiological signals from "Affective Computing" with signal processing algorithms from "Video Orbits" for reducing the amount of video that must be processed, and assisting the user in deciding what video should be "remembered."

Perceptual Similarity Measures Memory

People are great at identifying similar patterns in pictures, sound, or human behavior. But how they do this remains a mystery. Based on results from tests that determine how humans recognize visual patterns, we are building computer models to mimic recognition of perceptual similarity. Particular attention is given to how humans interpret directionality, periodicity, randomness, contrast, translation, rotation, perspective, and scale in natural scenes. The results have provided us with models good for image and video segmentation, retrieval, and content analysis.

Virtual Bellows for Video

Artists exercise viewpoint freedom with cubism and collage, and photographers flex their camera bellows; both desire to express what they see from multiple perspectives. This research harnesses the power of perspective mathematically, allowing one to extract and modify perspective in video. Applications include image mosaicing, high-resolution digital cameras, high-resolution printing, and recognition of video scene changes and camera motion.

Education

Sc.D., EECS Massachusetts Institute of Technology, 1991
S.M., EECS Massachusetts Institute of Technology, 1986
B.E.E., Georgia Institute of Technology, 1984
Computer Engineering Certificate, Georgia Institute of Technology, 1984


Selected Publications

Forthcoming: "Does HAL Cry Digital Tears?: Computers and Emotions," a chapter in Hal's Legacy , a book on science fiction's favorite computer (who was also the most emotional character in Kubrick & Clarke's 2001: A Space Odyssey). Edited by David Stork, for general audiences, this book contains chapters by Raymond Kurzweil, Roger Schank, Douglas Lenat, Azriel Rosenfeld, Don Norman, Daniel Dennett, and other leading experts in areas of science where Hal has inspired research. It also contains a great interview with Marvin Minsky (technical advisor to the film), and of course a forward by Arthur C. Clarke.

Look for a new book, AFFECTIVE COMPUTING, by R. W. Picard, to appear in 1997, published by MIT Press.

For more information: http://www.media.mit.edu/~picard

See Rosalind Picard's answers to Ask the Scientists questions.




 

Scientific American Frontiers
Fall 1990 to Spring 2000
Sponsored by GTE Corporation,
now a part of Verizon Communications Inc.