(1) Courant Institute, New York University, New York NY, 10012, USA;(2) Institute of Information Science, Academia Sinica, 115 Taipei, Taiwan;(3) IMA, University of Minnesota, Minneapolis, MN 55455, USA
Abstract:
International Journal of Computer Vision - We are given an image I and a library of templates ${mathcal{L}}$ , such that ${mathcal{L}}$ is an overcomplete basis for I. The templates can...