Sorry, you need to enable JavaScript to visit this website.

Dcitionary Learning for Poisson Compressed Sensing

Citation Author(s):
Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade
Submitted by:
sukanya patil
Last updated:
19 March 2016 - 1:06pm
Document Type:
Poster
Document Year:
2016
Event:
Presenters Name:
Sukanya Patil and Ajit Rajwade

Abstract 

Abstract: 

Imaging techniques involve counting of photons striking a detector. Due to fluctuations in the counting process, the measured photon counts are known to be corrupted by Poisson noise. In this paper, we propose a blind dictionary learning framework for the reconstruction of photographic image data from Poisson corrupted measurements acquired by a \emph{compressive} camera. We exploit the inherent non-negativity of the data by modeling the dictionary as well as the sparse dictionary coefficients as non-negative entities, and infer these directly from the compressed measurements in a Poisson maximum likelihood framework. We experimentally demonstrate the advantage of this \emph{in situ} dictionary learning over commonly used sparsifying bases such as DCT or wavelets, especially on color images.

up
0 users have voted:

Dataset Files

ICASSP_final_poster.pdf

(474)