Sparse Representations for Image Decomposition with Occlusions

We study the problem of how to detect \interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis, and also account for occlusions, where the basis superposition principle is no longer valid. Since the basis (a library of image templates) is over-redundant, there are in nitely many ways to decompose I. We are motivated to select a sparse/compact representation of I, and to account for occlusions and noise. We then study a greedy and iterative \weighted Lp Matching Pursuit" strategy, with

• Type: Conference
• Year: 1996
• Where: CVPR
• Authors: Michael J. Donahue, Davi Geiger, Tyng-Luh Liu, Robert A. Hummel
• Keywords: Basis Superposition Principle, Computer Vision, CVPR 1996, Function Approximation Problem, Over-redundant Basis