July 22, 2010 @ 4:30pm : Jean Ponce

Willow Team
Ecole Normale Superieure, Paris

Sparse Coding and Dictionary Learning for Image Analysis

Sparse coding—that is, modelling data vectors as sparse linear combinations of dictionary elements—is widely used in machine learning, neuroscience, signal processing, and statistics. This talk addresses the problem of learning the dictionary, adapting it to specific data and image understanding tasks. In particular, I will present a fast on-line approach to unsupervised dictionary learning and more generally sparse matrix factorization, and demonstrate its applications in image restoration tasks such as denoising, demosaicking, and inpainting. I will also present a general formulation of supervised dictionary learning adapted to tasks such as classification and regression. We have developed an efficient algorithm for solving the corresponding optimization problem, and I will demonstrate its application to handwritten digit classification, image deblurring and digital zooming, inverse half toning, and the detection of fake artworks.

Joint work with Julien Mairal and Francis Bach.

seminars/seminaritems/2010-07-22-1630.txt · Last modified: 2010/09/17 09:23 by koray