“The Three R’s of Computer Vision” by Dr. Jitendra Malik

Radhakrishna Dasari

As a part of University at Buffalo Distinguished speaker series 2013, Dr. Jitendra Malik, Professor at EECS, UC Berkeley was invited today for a talk on computer vision. The talk started citing Computer Vision as a problem of Recognition, Reconstruction and Reorganization (a substitute word for Segmentation for set of 3 R’s!). Prof. Malik emphasized that computer vision should be taught with the paradigm of 3 R’s rather than starting with Image Processing techniques to segmentation and then going to Pattern Recognition. These problems should not be worked in isolation. He predicted that the interactions between them will influence the future of computer vision research. The talk continued with a note on the history of computer vision. He explained that the aim of computer vision research is to match with the performance of human vision, for which research of Fei Fei Li et al was cited as a reference. The…

View original post 190 more words

About Khuram Ali

Programming... Programming and Programming...!!!

Posted on May 6, 2013, in Artificial Intelligence, Computer Vision. Bookmark the permalink. Leave a comment.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: