Abstract | ||
---|---|---|
Markov Random Fields (MRFs) are one of the most widely used probabilistic graphic model in image restoration. However, MRFs still require designing of clique potential function and lack of a canonical parameter learning method. To overcome these disadvantages of MRFs, we propose a novel image restoration architecture leveraging Convolutional Neural Networks (CNNs). The central point shown here is that CNNs can be viewed as generalized MRFs, which gives a novel explanation for CNNs's excellent performance from a statistical perspective. Furthermore, all ingredients for image restoration via CNNs are presented in this paper. Specifically, a learning framework and reconstruction method are constituted through minimizing KL-divergence and half-quadratic regularization respectively. Finally, simulations show that the proposed method, referred as Image Restoration based on CNNs (IR-CNNs), outperforms the state-of-the-art image restoration methods based on MRFs. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/CISS.2018.8362260 | 2018 52nd Annual Conference on Information Sciences and Systems (CISS) |
Keywords | Field | DocType |
Convolutional Neural Networks,Markov Random Fields,Image Restoration | Iterative reconstruction,Mathematical optimization,Clique,Pattern recognition,Computer science,Convolutional neural network,Markov chain,Feature extraction,Regularization (mathematics),Artificial intelligence,Image restoration,Probabilistic logic | Conference |
ISBN | Citations | PageRank |
978-1-5386-0580-6 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xinjie Lan | 1 | 1 | 1.70 |
Kenneth E. Barner | 2 | 812 | 70.19 |