TY - GEN
T1 - Dictionary learning from sparsely corrupted or compressed signals
AU - Studer, Christoph
AU - Baraniuk, Richard G.
PY - 2012
Y1 - 2012
N2 - In this paper, we investigate dictionary learning (DL) from sparsely corrupted or compressed signals. We consider three cases: I) the training signals are corrupted, and the locations of the corruptions are known, II) the locations of the sparse corruptions are unknown, and III) DL from compressed measurements, as it occurs in blind compressive sensing. We develop two efficient DL algorithms that are capable of learning dictionaries from sparsely corrupted or compressed measurements. Empirical phase transitions and an in-painting example demonstrate the capabilities of our algorithms.
AB - In this paper, we investigate dictionary learning (DL) from sparsely corrupted or compressed signals. We consider three cases: I) the training signals are corrupted, and the locations of the corruptions are known, II) the locations of the sparse corruptions are unknown, and III) DL from compressed measurements, as it occurs in blind compressive sensing. We develop two efficient DL algorithms that are capable of learning dictionaries from sparsely corrupted or compressed measurements. Empirical phase transitions and an in-painting example demonstrate the capabilities of our algorithms.
KW - compressive sensing
KW - Dictionary learning
KW - in-painting
KW - signal restoration
KW - sparse approximation
UR - http://www.scopus.com/inward/record.url?scp=84867618670&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867618670&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2012.6288631
DO - 10.1109/ICASSP.2012.6288631
M3 - Conference contribution
AN - SCOPUS:84867618670
SN - 9781467300469
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3341
EP - 3344
BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Y2 - 25 March 2012 through 30 March 2012
ER -