Dense error correction via L1 minimization

Wednesday, October 29, 2008 - 3:55pm - 4:45pm
EE/CS 3-180
Yi Ma (University of Illinois at Urbana-Champaign)
It is know that face images of different people lie on multiple low-dimensional subspaces. In this talk,
we will show that these subspaces are tightly bundled together as a bouquet. Precisely due to this
unique structure, it allows extremely robust reconstruction and recognition of faces despite severe
corruption or occlusion. We will show that if the image resolution and the size of the face database
grow in proportion to infinity, computer can correctly and efficiently recover or recognize a face image
with almost 100% of its pixels randomly and arbitrarily corrupted, a truly magic ability of L1-minimization.

This is joint work with John Wright of UIUC.
MSC Code: