Jitendra Malik
University of California, Berkeley
|
Primary Section: 34, Computer and Information Sciences Secondary Section: 32, Applied Mathematical Sciences Membership Type:
Member
(elected 2015)
|
Biosketch
Jitendra Malik studies computer vision. He develops models and algorithms that given an image, infer properties of the objects, people, and places in the world that gave rise to the image. He is also interested in the computational modeling of human vision. With colleagues, he has helped develop concepts and techniques such as anisotropic diffusion for image de-noising, normalized cuts for clustering and segmentation, high dynamic range imaging, ecological statistics of perceptual grouping, and machine learning approaches to visual recognition. Jitendra was born in Mathura, India in 1960. After a Bachelors degree in Electrical Engineering from IIT Kanpur in 1980 and a PhD in Computer Science from Stanford University in 1985, he joined UC Berkeley where he is currently the Arthur J. Chick Professor in the Computer Science Division, Department of EECS, and serves on the faculty of the department of Bioengineering, and the Cognitive Science and Vision Science groups. Jitendra Malik received the Distinguished Researcher Award from IEEE PAMI-TC and the K.S. Fu Prize of the International Association of Pattern Recognition. He is a member of both the National Academy of Sciences and the National Academy of Engineering, and a Fellow of the American Academy of Arts and Sciences.
Research Interests
Jitendra Malik studies computer vision. In the course of this work, he has drawn on and contributed to various areas of applied mathematics. His collaborators and he have developed techniques that enable one to reconstruct three-dimensional models of objects in the world from images, and then produce photo-realistic renderings from novel viewpoints or in novel lighting. Other research has been on methods for segmenting images and video into groups that correspond to objects or parts of objects. Jitendra’s group has devised novel learning based approaches to visual recognition, such as for finding instances of object categories such faces, giraffes, the digit 5, or chairs, and actions such as running, jumping, or riding a horse. They have developed algorithms, which can detect people in images and identify their body part configurations, or track and count cars in traffic video. Jitendra’s approach to computer vision draws inspiration and insight from the work of psychologists and neuroscientists, and contributes to computational modeling of biological vision. His group has also done experimental work in perception, e.g. for evaluating models of texture analysis and visual recognition. A key application area for his research is on biological image analysis, where contributions include image denoising techniques, ways of building atlases of gene expression to aid developmental biologists, and automating analysis of electron microscope images.
