A weighted discriminative approach for image denoising with overcomplete representations

Abstract : We present a novel weighted approach for shrinkage functions learning in image denoising. The proposed approach optimizes the shape of the shrinkage functions and maximizes denoising performance by emphasizing the contribution of sparse overcomplete representation components. In contrast to previous work, we apply the weights in the overcomplete domain and formulate the restored image as a weighted combination of the post-shrinkage overcomplete representations. We further utilize this formulation in an offline Least Squares learning stage of the shrinkage functions, thus adapting their shape to the weighting process. The denoised image is reconstructed with the learned weighted shrinkage functions. Computer simulations demonstrate superior shrinkage-based denoising performance.
Type de document :
Communication dans un congrès
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, Mar 2010, Dallas, United States. pp.782 -785, 2010, 〈10.1109/ICASSP.2010.5494973〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00569053
Contributeur : Jules Espiau de Lamaestre <>
Soumis le : jeudi 24 février 2011 - 10:51:10
Dernière modification le : jeudi 24 février 2011 - 10:51:10

Identifiants

Collections

Citation

Amir Adler, Yacov Hel-Or, Michael Elad. A weighted discriminative approach for image denoising with overcomplete representations. Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, Mar 2010, Dallas, United States. pp.782 -785, 2010, 〈10.1109/ICASSP.2010.5494973〉. 〈inria-00569053〉

Partager

Métriques

Consultations de la notice

70