基于深度神经网络的块压缩感知图像重构

doi:10.11896/jsjkx.210900118

摘要/Abstract

摘要： 压缩感知(CS)是根据由信号的线性投影获得的少量测量值有效地重建信号的一种信号处理框架,用低的采样率重构出高质量图像,是基于CS的计算成像实用化的持续挑战。图像重构模型的改进多是在信号稀疏约束下加入更多稀疏先验,其迭代优化过程复杂且耗时。神经网络作为深度学习的应用模型,可实现对任意复杂函数的逼近,为图像高质量实时重构提供了新的技术路线。文中用深度神经网络(DNN)进行重构,避免了CS繁杂的算法求解过程,且通过分块处理缩短了重构时间以及减少了网络节点数目,通过对上万幅不同类型的图像进行训练以得到DNN模型,再将分块CS的测量和DNN非线性求解联合来实现高效重构。结果表明,所提方法与6种不同的重构方法相比,图像的峰值信噪比(PSNR)和结构相似度(SSIM)都有不同程度的提高。与先进的CS算法相比,不仅重构质量能与之媲美,而且DNN极大减少了时间复杂度,重构时间在3s内。当采样率低至0.01时,该方法仍能较清晰地重构图像而其他算法难以恢复。当采样率为0.1时,该方法与先进的残差网络方法相比,PSNR最大(小)增益达到6.7(1.97)dB,SSIM最大(小)增益达到0.354(0.122)。

关键词: 图像处理, 分块压缩感知, 重构算法, 深度学习, 神经网络

Abstract: Compressed sensing(CS) is a signal processing framework for effectively reconstructing signal from a small number of measurements obtained by linear projections of the signal.It’s an ongoing challenge for the practicality of computational imaging based on CS.The improvement of image reconstruction model is to incorporate more prior constraints under the signal sparse constraint,and the iterative optimization process is complex and time-consuming.Neural networks,as the application models of deep learning,can realize the approximation of any complex function,which provides a new technical route for high-quality and real-time image reconstruction.In this paper,deep neural network(DNN) is used for reconstruction and the block processing is used to reduce the reconstruction time and the number of network nodes,which avoids the complicated algorithm solving process of CS.The DNN model is obtained by training a large number of different types of images,and then the block CS measurement and DNN nonlinear solution are combined jointly to achieve efficient reconstruction.Experimental results show that,compared with six different reconstruction algorithms,the peak signal-to-noise ratio(PSNR) and structure similarity(SSIM) of images are improved in different degrees.Compared with the advanced CS algorithm,not only the reconstruction quality is comparable,but also the time complexity of DNN is greatly reduced and the reconstruction time is less than 3s.When sampling rate is as low as 0.01,the proposed approach can still reconstruct the image clearly while other algorithms fail.When sampling rate is 0.1,compared with the recent residual network method,the maximum(minimum) gain of PSNR is 6.7(1.97) dB,and the maximum(minimum) gain of SSIM is 0.354(0.122).

Key words: Image processing, Block-based compressed sensing, Reconstruction algorithm, Deep learning, Neural network

中图分类号:

TP391

潘泽民, 覃亚丽, 郑欢, 王荣芳, 任宏亮. 基于深度神经网络的块压缩感知图像重构[J]. 计算机科学, 2022, 49(11A): 210900118-9. https://doi.org/10.11896/jsjkx.210900118

PAN Ze-min, QIN Ya-li, ZHENG Huan, WANG Rong-fang, REN Hong-liang. Block-based Compressed Sensing of Image Reconstruction Based on Deep Neural Network[J]. Computer Science, 2022, 49(11A): 210900118-9. https://doi.org/10.11896/jsjkx.210900118

参考文献

[1]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[2]CANDES E J,WAKIN M B.An introduction to compressivesampling[J].IEEE Signal Processing Magazine,2008,25(2):21-30.
[3]ROMBERG J.Imaging via compressive sampling[J].IEEE Signal Processing Magazine,2008,25(2):14-20.
[4]DUARTE M F,DAVENPORT M A,TAKHAR D,et al.Single-pixel imaging via compressive sampling[J].IEEE Signal Processing Magazine,2008,25(2):83-91.
[5]POTTER L C,ERTIN E,PARKER J T,et al.Sparsity andcompressed sensing in radar imaging[J].Proceedings of the IEEE,2010,98(6):1006-1020.
[6]SCHIFFNER M F,SCHMITZ G.Fast image acquisition inpulse-echo ultrasound imaging using compressed sensing[C]//Proc of the IEEE Int Ultrasonics Symp(IUS).Dresden,Germany,2012:1944-1947.
[7]WU L B,WANG Y.Compressive sensing based indoor occupancy positioning using a single thermopile point detector with a coded binary mask[J].IEEE Sensors Letters,2019,3(12):1-4.
[8]LIU J,HUANG K Y,YAO X H.Common-innovation subspace pursuit for distributed compressed sensing in wireless sensor networks[J].IEEE Sensors Journal,2019,19(3):1091-1103.
[9]HUGGINS P S,ZUCKER S W.Greedy basis pursuit[J].IEEE Transactions on Signal Processing,2007,55(7):3760-3772.
[10]CHARTRAND R,YIN W T.Iteratively reweighted algorithms for compressed sensing[C]//2008 IEEE International Confe-rence on Acoustics,Speech and Signal Processing.Las Vegas,NV,USA,2008.
[11]TROPP J A,GILBERT A C.Signal recovery from randommeasurements via orthogonal matching pursuit[J].IEEE Transactions on Information Theory,2007,53(12):1-17.
[12]GAN L.Block compressed sensing of natural images[C]//2007 15th International Conference on Digital Signal Processing.Cardiff,UK,2007:403-406.
[13]MUN S,FOWLER J E,TRAMEL E W.Block-based com-pressed sensing of images and video[J].Foundations and Trends in Machine Learning,2012,4(4):297-416.
[14]MUN S,FOWLER J E.Block compressed sensing of imagesusing directional transforms[C]//2009 16th IEEE International Conference on Image Processing(ICIP).Cairo,Egypt,2009:3021-3024.
[15]FOWLER J E,MUN S,TRAMEL E W.Multiscale block compressed sensing with smoothed projected Landweber reconstruction[C]//Proceedings of the European Signal Processing Conference.Barcelona,Spain,2011:564-568.
[16]MARIO A T F,ROBERT D N,STEPHEN J W.Gradient Projection for Sparse Reconstruction:Application to Compressed Sensing and Other Inverse Problems[J].IEEE Journal of Selec-ted Topics in Signal Processing,2007,1(4):586-597.
[17]SHI W Z,JIANG F,LIU S H,et al.Multi-scale deep networks for image compressed Sensing[C]//2018 25th IEEE International Conference on Image Processing(ICIP).Athens,Greece,2018.
[18]MUDULI P R,GUNUKULA R R,MUKHERJEE A.A deep learning approach to fetal-ECG signal reconstruction[C]//2016 Twenty Second National Conf on Communication(NCC).Guwahati,India,2016.
[19]XIA Q,LI S,HAO A M,et al.Deep Learning for Digital Geo-metry Processing and Analysis:A Review[J].Journal of Compu-ter Research and Development,2019,56(1):155-182.
[20]TIAN X,WANG L,DING Q.Review of image semantic segmentation based on deep learning[J].Journal of Software,2019,30(2):440-468
[21]TOMOYOSHI S,YUTAKA E,TAKASHI N,et al.Computa-tional ghost imaging using deep learning[J].Optics Communications,2018,413:147-151.
[22]CAO Y,LI H,WANG T B.A survey of research on target detection algorithms based on deep learning[J].Computer and Modernization,2020(5):63-69
[23]ZHAO F,LI J,ZHANG L,et al.Muli-view face recognitionusing deep neural networks[J].Future Generation Computer Systems,2020,111:375-380.
[24]CUI L,ZHANG P,CHE J.Overview of deep neural based classification algorithms for remote images[J].Computer Science,2018,45(z1):50-53
[25]MOUSAVI A,PATEL A B,BARANIUK R G.A deep learning approach to structured signal recovery[C]//2015 53rd Annual Allerton Conf on Communication,Control,and Computing(Allerton).Monticello,IL,USA,2015:1336-1343.
[26]LIU Y H,LIU S Y,FU F X.Optimization of Compressed Sen-sing Reconstruction Algorithms Based on Convolutional Neural Network[J].Computer Science,2020,47(3):143-148.
[27]KULKARNI K,LOHIT S,TURAGA P,et al.ReconNet:Non-iterative reconstruction of images from compressively sensed random measurements[C]//2016 IEEE Conf on Computer Vision and Pattern Recognition(CVPR).Las Vegas,NV,USA,2016:449-458.
[28]XIE X M,WANG Y X,SHI G M,et al.Adaptive measurement network for CS image reconstruction[C]//Proc of the China Conf on Computer Vision.2017.
[29]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2016:770-778.
[30]YAO H T,DAI F,ZHANG S L,et al.DR2-Net:Deep residual reconstruction network for image compressive sensing[J].Neurocomputing,2019,359:483-493.
[31]ADLER A,BOUBLIL D,ZIBULEVSKY M.Block-based com-pressed sensing of images via deep learning[C]//2017 IEEE 19th Int Workshop on Multimedia Signal Processing(MMSP).Luton,UK,2017.
[32]ZENG C Y,YE J X,WANG Z F,et al.Survey of compressed sensing reconstruction algorithms in deep learning framework[J].Computer Engineering and Applications,2019,55(17):1-8.
[33]RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323:533-536.
[34]NAIR V,HINTON G E.Rectified linear units improve restric-ted boltzmann machines[C]//Proc of the 27th International Conference on Machine Learning(ICML-10).Haifa,Israel,2010:807-814.
[35]CUI J F,LI Y P,WANG S X,et al.Directional preparation of anticoagulantactive sulfated polysaccharides from Enteromorpha prolifera using artificial neural networks[J].Scientific Reports,2018,8(3062).
[36]GUI W X,LU Q,SU M L.A firewoks algorithm-back propagation fault diagnosis algorithm for system-level fault diagnosis[J].Journal of Electronics and Information Technology,2020,42(5):1102-1109.
[37]RUSSELL B C,TORRALBA A,Murphy K P,et al.Labelme:a database and web-based tool for image annotation[J].International Journal of Computer Vision,2008,77(1/2/3):157-173.
[38]DUCHI J,HAZAN E,SINGER Y.Adaptive subgradient me-thods for online learning and stochastic optimization[J].Journal of Machine Learning Research,2011,12:2121-2159.
[39]CHEN H,QIN Y L,REN H L,et al.Adaptive weighted high frequency iterative algorithm for fractional-order total variation with nonlocal regularization for image reconstruction[J].Electronics,2020,9(7).

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[3]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[5]	宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[6]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[7]	王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[8]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[9]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[10]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[11]	郭拯危, 付泽文, 李宁, 白澜. 高分辨率斜视聚束SAR回波仿真加速算法研究 Study on Acceleration Algorithm for Raw Data Simulation of High Resolution Squint Spotlight SAR 计算机科学, 2022, 49(8): 178-183. https://doi.org/10.11896/jsjkx.210600066
[12]	檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[13]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[14]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[15]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed