A Fast Algorithm for Learning the Overcomplete Image Prior

In this letter, we learned overcomplete filters to model rich priors of nature images. Our approach extends the Gaussian Scale Mixture Fields of Experts (GSM FOE), which is a fast approximate model based on Fields of Experts (FOE). In these previous image prior model, the overcomplete case is not considered because of the heavy computation. We introduce the assumption of quasi-orthogonality to the GSM FOE, which allows us to learn overcomplete filters of nature images fast and efficiently. Simulations show these obtained overcomplete filters have properties similar with those of Fields of Experts', and denoising experiments also show the superiority of our model.

[1]  Erkki Oja,et al.  A class of neural networks for independent component analysis , 1997, IEEE Trans. Neural Networks.

[2]  Geoffrey E. Hinton,et al.  Learning Sparse Topographic Representations with Products of Student-t Distributions , 2002, NIPS.

[3]  Erkki Oja,et al.  A fast algorithm for estimating overcomplete ICA bases for image windows , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[4]  Terrence J. Sejnowski,et al.  Edges are the Independent Components of Natural Scenes , 1996, NIPS.

[5]  Martin J. Wainwright,et al.  Image denoising using scale mixtures of Gaussians in the wavelet domain , 2003, IEEE Trans. Image Process..

[6]  Christopher K. I. Williams,et al.  Products of Gaussians and Probabilistic Minor Component Analysis , 2002, Neural Computation.

[7]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[8]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[10]  Yiannis Aloimonos,et al.  Who killed the directed model? , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Song-Chun Zhu,et al.  Prior Learning and Gibbs Reaction-Diffusion , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  William T. Freeman,et al.  What makes a good model of natural images? , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.