Reduction of Compression Artifacts Using a Densely Cascading Image Restoration Network

Since high quality realistic media are widely used in various computer vision applications, image compression is one of the essential technologies to enable real-time applications. Image compression generally causes undesired compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a densely cascading image restoration network (DCRN), which consists of an input layer, a densely cascading feature extractor, a channel attention block, and an output layer. The densely cascading feature extractor has three densely cascading (DC) blocks, and each DC block contains two convolutional layers, five dense layers, and a bottleneck layer. To optimize the proposed network architectures, we investigated the trade-off between quality enhancement and network complexity. Experimental results revealed that the proposed DCRN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed joint photographic experts group (JPEG) images compared to the previous methods.

[1]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[2]  Yunjin Chen,et al.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Liangpei Zhang,et al.  A super-resolution reconstruction algorithm for surveillance images , 2010, Signal Process..

[4]  Changhoon Yim,et al.  Quality Assessment of Deblocked Images , 2011, IEEE Transactions on Image Processing.

[5]  Yang Liu,et al.  An Adaptive and Robust Edge Detection Method Based on Edge Proportion Statistics , 2020, IEEE Transactions on Image Processing.

[6]  Jiun-In Guo,et al.  An Energy-Aware IP Core Design for the Variable-Length DCT/IDCT Targeting at MPEG4 Shape-Adaptive Transforms , 2005, IEEE Trans. Circuits Syst. Video Technol..

[7]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

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

[9]  Jan Kautz,et al.  Loss Functions for Image Restoration With Neural Networks , 2017, IEEE Transactions on Computational Imaging.

[10]  Yanzhu Hu,et al.  An Improved Enhancement Algorithm Based on CNN Applicable for Weak Contrast Images , 2020, IEEE Access.

[11]  S Peled,et al.  Superresolution in MRI: Application to human white matter fiber tract visualization by diffusion tensor imaging , 2001, Magnetic resonance in medicine.

[12]  Ming Yang,et al.  BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Karen O. Egiazarian,et al.  Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images , 2007, IEEE Transactions on Image Processing.

[14]  Fan Zhou,et al.  Implicit Dual-Domain Convolutional Network for Robust Color Image Compression Artifact Reduction , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Jani Lainema,et al.  Adaptive deblocking filter , 2003, IEEE Trans. Circuits Syst. Video Technol..

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

[17]  Yun Fu,et al.  Residual Dense Network for Image Restoration , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Eunjun Rhee,et al.  Single Image Super-Resolution Method Using CNN-Based Lightweight Neural Networks , 2021, Applied Sciences.

[19]  Chiou-Shann Fuh,et al.  ICEBIN: Image Contrast Enhancement Based on Induced Norm and Local Patch Approaches , 2021, IEEE Access.

[20]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[21]  Dongsan Jun,et al.  Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network , 2021, Sensors.

[22]  Daniel Rueckert,et al.  Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch , 2013, MICCAI.

[23]  S. Aruna Mastani,et al.  New Approach of Estimating PSNR-B For De-blocked Images , 2013, ArXiv.

[24]  Hong Yan,et al.  Blocking artifacts suppression in block-coded images using overcomplete wavelet representation , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[25]  Peter M. Atkinson,et al.  Sub‐pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super‐resolution pixel‐swapping , 2006 .

[26]  Syed Mahfuzul Aziz,et al.  Energy Efficient Image Transmission in Wireless Multimedia Sensor Networks , 2013, IEEE Communications Letters.

[27]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[28]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

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

[30]  C.-C. Jay Kuo,et al.  Review of Postprocessing Techniques for Compression Artifact Removal , 1998, J. Vis. Commun. Image Represent..

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Kankanala Srinivas,et al.  Exposure-Based Energy Curve Equalization for Enhancement of Contrast Distorted Images , 2020, IEEE Transactions on Circuits and Systems for Video Technology.

[33]  Ronen Basri,et al.  On Detection of Faint Edges in Noisy Images , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.