Efficient Point-to-Subspace Query in ℓ1 with Application to Robust Face Recognition

Articles:

Title:: Efficient Point-to-Subspace Query in ℓ1 with Application to Robust Face Recognition
Author(s):: Zhang, Yuqian
Wright, John N.
Sun, Ju
Date:: 2012
Type:: Articles
Department:: Electrical Engineering
Permanent URL:: http://hdl.handle.net/10022/AC:P:14959
Part Number:: 7575
Book/Journal Title:: Computer Vision -- ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012: Proceedings, Part IV
Book Author:: Schmid, Cordelia
Publisher:: Springer
Publisher Location:: New York
Abstract:: Motivated by vision tasks such as robust face and object recognition, we consider the following general problem: given a collection of low-dimensional linear subspaces in a high-dimensional ambient (image) space, and a query point (image), efficiently determine the nearest subspace to the query in ℓ1 distance. We show in theory this problem can be solved with a simple two-stage algorithm: (1) random Cauchy projection of query and subspaces into low-dimensional spaces followed by efficient distance evaluation (ℓ1 regression); (2) getting back to the high-dimensional space with very few candidates and performing exhaustive search. We present preliminary experiments on robust face recognition to corroborate our theory.
Subject(s):: Artificial intelligence
Computer science
DOI:: http://dx.doi.org/10.1007/978-3-642-33765-9_30