Abstract
A variety of approaches have been proposed for addressing different image restoration challenges. Recently, deep generative models were one of the mostly used ones. In this paper, a new Restricted Boltzmann Machines (RBM) training algorithm for addressing corrupted data has been proposed. RBMs can be trained both supervised and unsupervised, however they are very sensitive to noise and occlusion. The proposed algorithm enables the RBM to be robust against corruptions. Using the new algorithm, we have given the RBM a posterior knowledge about desired or clean data. Despite other methods, the proposed algorithm works fine without changing the architecture of the model or adding any regularization term. Concretely, the RBM can be used as a robust feature extractor, even for unclean data. By creating different corrupted versions for each image instance, and using the original version in the reconstruction phase, the RBM can learn the desired probability distribution of data. Experimental results confirm the robustness of the model against different types of corruption.
Similar content being viewed by others
References
Basu S, Karki M, Ganguly S, DiBiano R, Mukhopadhyay S, Gayaka S, Kannan R, Nemani R (2017) Learning sparse feature representations using probabilistic quadtrees and deep belief nets. Neural Process Lett 45 (3):855–867
Bengio Y, Delalleau O (2009) Justifying and generalizing contrastive divergence. Neural Comput 21(6):1601–1621
Chan T, Esedoglu S, Park F, Yip A (2005) Recent developments in total variation image restoration. Mathematical Models of Computer Vision 17 (2):17–31
Choo S, Lee H (2018) Learning framework of multimodal gaussian–bernoulli rbm handling real-value input data. Neurocomputing 275:1813–1822
Dabov K, Foi A, Katkovnik V, Egiazarian K (2008) Image restoration by sparse 3d transform-domain collaborative filtering. In: International society for optics and photonics. vol. 6812, p 681207, Image Processing: Algorithms and Systems VI
Dong C, Deng Y, Change Loy C, Tang X (2015) Compression artifacts reduction by a deep convolutional network. In: Proceedings of the IEEE international conference on computer vision, pp 576–584
Dong W, Zhang L, Shi G, Wu X (2011) Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans Image Process 20(7):1838–1857
Elad M, Aharon M (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15 (12):3736–3745
Fischer A, Igel C (2014) Training restricted boltzmann machines: An introduction. Pattern Recogn 47(1):25–39
Fu B, Zhao X, Li Y, Wang X, Ren Y (2019) A convolutional neural networks denoising approach for salt and pepper noise. Multimed Tool Appl 78(21):30707–30721
Gao J, Guo Y, Yin M (2013) Restricted boltzmann machine approach to couple dictionary training for image super-resolution. In: 2013 IEEE international conference on image processing. IEEE, pp 499–503
Gondara L (2016) Medical image denoising using convolutional denoising autoencoders. In: 2016 IEEE 16th International conference on data mining workshops (ICDMW). IEEE, pp 241–246
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, Cambridge
Hershey JR, Olsen PA (2007) Approximating the kullback leibler divergence between gaussian mixture models. In: 2007 IEEE international conference on acoustics, speech and signal processing-ICASSP’07, vol 4. IEEE, pp IV–317
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800
Hinton GE (2007) Learning multiple layers of representation. Trends Cogn Sci 11(10):428–434
Hinton GE (2012) A practical guide to training restricted boltzmann machines. In: Neural networks: Tricks of the trade. Springer, Berlin, pp 599–619
Hore A, Ziou D (2010) Image quality metrics: Psnr vs. ssim. In: 2010 20th International conference on pattern recognition. IEEE, pp 2366–2369
Jain V, Seung S (2009) Natural image denoising with convolutional networks. In: Advances in neural information processing systems, pp 769–776
Jansen C, Mackowiak R, Hezel N, Ufer M, Altstädt G, Barthel KU (2015) Reconstructing missing areas in facial images. In: 2015 IEEE International symposium on multimedia (ISM). IEEE, pp 323–326
Krizhevsky A, Hinton G, et al. (2010) Factored 3-way restricted boltzmann machines for modeling natural images. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 621–628
Le Roux N, Heess N, Shotton J, Winn J (2011) Learning a generative model of images by factoring appearance and shape. Neural Comput 23 (3):593–650
Mao X-J, Shen C, Yang Y-B (2016) Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv:1606.08921
Melchior J, Wang N, Wiskott L (2017) Gaussian-binary restricted boltzmann machines for modeling natural image statistics. PloS one 12(2):e0171015
Mu Y, Ferrie F, Dimitrakopoulos R (2015) Sparse image reconstruction by two phase rbm learning: application to mine planning. In: 2015 14th IAPR international conference on machine vision applications (MVA). IEEE, pp 316–320
Mu Y, Ferrie F, Dimitrakopoulos R (2015) Sparse image reconstruction by two phase rbm learning: Application to mine planning. In: 2015 14th IAPR international conference on machine vision applications (MVA). IEEE, pp 316–320
Oliveira JP, Bioucas-Dias JM, Figueiredo MA (2009) Adaptive total variation image deblurring: a majorization–minimization approach. Signal Process 89(9):1683–1693
Pires RG, Santos DFS, Pereira LAM, De Souza GB, Levada ALM, Papa JP (2017) A robust restricted boltzmann machine for binary image denoising. In: 2017 30th SIBGRAPI conference on graphics, patterns and images (SIBGRAPI). IEEE, pp 390–396
Selvi AS, Kumar KPM, Dhanasekeran S, Maheswari PU, Ramesh S, Pandi SS (2019) De-noising of images from salt and pepper noise using hybrid filter, fuzzy logic noise detector and genetic optimization algorithm (hfgoa). Multimedia Tools and Applications (79), pp. 4115–4131
Tang Y, Salakhutdinov R, Hinton G (2012) Robust boltzmann machines for recognition and denoising. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 2264–2271
Wang N, Melchior J, Wiskott L (2012) An analysis of gaussian-binary restricted boltzmann machines for natural images. In: ESANN
Wang X, Zheng Z, He Y, Yan F, Zeng Z, Yang Y (2020) Progressive local filter pruning for image retrieval acceleration. arXiv:2001.08878
Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. In: Advances in neural information processing systems, pp 341–349
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Zhang N, Ding S, Zhang J, Xue Y (2018) An overview on restricted boltzmann machines. Neurocomputing 275:1186–1199
Zheng Z, Yang X, Yu Z, Zheng L, Yang Y, Kautz J (2019) Joint discriminative and generative learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2138–2147
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fakhari, A., Kiani, K. A new restricted boltzmann machine training algorithm for image restoration. Multimed Tools Appl 80, 2047–2062 (2021). https://doi.org/10.1007/s11042-020-09685-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09685-w