TY - GEN
T1 - Dictionary transfer for image denoising via domain adaptation
AU - Chen, Gang
AU - Xiong, Caiming
AU - Corso, Jason J.
PY - 2012
Y1 - 2012
N2 - The idea of using overcomplete dictionaries with prototype signal atoms for sparse representation has found many applications, among which image denoising is considered as an active research topic. However, the standard process to train a new dictionary for image denoising requires the whole image (or most parts) as input, which is costly; training the dictionary on just a few patches would result in overfitting. We instead propose a dictionary learning approach for image denoising via transfer learning. We transfer the source domain dictionary to a target domain for image denoising via a dictionary- regularization term in the energy function. Thus, we have a new dictionary that is trained from only a few patches of the target noisy image. We measure the performance on various corrupted images, and show that our method is fast and comparable to the state of the art. We also demonstrate cross-domain transfer (photo to medical image).
AB - The idea of using overcomplete dictionaries with prototype signal atoms for sparse representation has found many applications, among which image denoising is considered as an active research topic. However, the standard process to train a new dictionary for image denoising requires the whole image (or most parts) as input, which is costly; training the dictionary on just a few patches would result in overfitting. We instead propose a dictionary learning approach for image denoising via transfer learning. We transfer the source domain dictionary to a target domain for image denoising via a dictionary- regularization term in the energy function. Thus, we have a new dictionary that is trained from only a few patches of the target noisy image. We measure the performance on various corrupted images, and show that our method is fast and comparable to the state of the art. We also demonstrate cross-domain transfer (photo to medical image).
KW - Dictionary learning
KW - domain adaptation
KW - image denoising
KW - sparse representations
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=84875818365&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875818365&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2012.6467078
DO - 10.1109/ICIP.2012.6467078
M3 - Conference contribution
AN - SCOPUS:84875818365
SN - 9781467325332
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1189
EP - 1192
BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
T2 - 2012 19th IEEE International Conference on Image Processing, ICIP 2012
Y2 - 30 September 2012 through 3 October 2012
ER -