Learning sparse multiscale image representations Export

@misc{citeulike:2885090, abstract = {We describe a method for learning sparse multiscale image representations using a sparse prior distribution over the basis function coe\#cients. The prior consists of a mixture of a Gaussian and a Dirac delta function, and thus encourages coe\#cients to have exact zero values. Coe\#cients for an image are computed by sampling from the resulting posterior distribution with a Gibbs sampler. The learned basis is similar to the Steerable Pyramid basis, and yields slightly higher SNR for the...}, author = {Sallee, P. and Olshausen, B.}, citeulike-article-id = {2885090}, citeulike-linkout-0 = {http://citeseer.ist.psu.edu/702292.html}, citeulike-linkout-1 = {http://citeseer.lcs.mit.edu/702292.html}, citeulike-linkout-2 = {http://citeseer.ifi.unizh.ch/702292.html}, citeulike-linkout-3 = {http://citeseer.comp.nus.edu.sg/702292.html}, keywords = {sparse-coding}, posted-at = {2008-06-12 03:53:45}, priority = {3}, title = {Learning sparse multiscale image representations}, url = {http://citeseer.ist.psu.edu/702292.html}, year = {2003} }

TY - GEN ID - citeulike:2885090 L3 - citeulike-article-id:2885090 N2 - We describe a method for learning sparse multiscale image representations using a sparse prior distribution over the basis function coe#cients. The prior consists of a mixture of a Gaussian and a Dirac delta function, and thus encourages coe#cients to have exact zero values. Coe#cients for an image are computed by sampling from the resulting posterior distribution with a Gibbs sampler. The learned basis is similar to the Steerable Pyramid basis, and yields slightly higher SNR for the... TI - Learning sparse multiscale image representations KW - sparse-coding AU - Sallee, P AU - Olshausen, B PY - 2003/// UR - http://citeseer.ist.psu.edu/702292.html ER -