Residual encoder-decoder network introduced for multisource SAR image despeckling

Synthetic Aperture Radar (SAR) image is disturbed by multiplicative noise known as speckle. In this paper, based on the power of deep fully convolutional network, an encoding-decoding framework is introduced for multisource SAR image despeckling. The network contains a series of convolution and deconvolution layers, forming an end-to-end non-linear mapping between noise and clean SAR images. With addition of skip connection, the network can keep image details and accomplish the strategy for residual learning which solves the notorious problem of vanishing gradients and accelerates convergence. The experimental results on simulated and real SAR images show that the introduced approach achieves improvements in both despeckling performance and time efficiency over the state-of-the-art despeckling methods.

[1]  Jian Yang,et al.  MemNet: A Persistent Memory Network for Image Restoration , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Samuel Foucher,et al.  SAR Image Filtering Via Learned Dictionaries and Sparse Representations , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Vishal M. Patel,et al.  SAR Image Despeckling Using a Convolutional Neural Network , 2017, IEEE Signal Processing Letters.

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Xiaoshuang Ma,et al.  Learning a Dilated Residual Network for SAR Image Despeckling , 2017, Remote. Sens..

[9]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[11]  Alin Achim,et al.  SAR image denoising via Bayesian wavelet shrinkage based on heavy-tailed modeling , 2003, IEEE Trans. Geosci. Remote. Sens..

[12]  Yu-Bin Yang,et al.  Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections , 2016, NIPS.

[13]  Jong-Sen Lee,et al.  Digital Image Enhancement and Noise Filtering by Use of Local Statistics , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Florence Tupin,et al.  Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based Weights , 2009, IEEE Transactions on Image Processing.

[17]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[18]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.