基于迭代收缩阈值与深度学习的压缩感知图像重构网络  

A compressive sensing image reconstruction network based on iterative shrinkage thresholding and deep learning

作　　者：徐雯 于瓅[1] XU Wen;YU Li(School of Computer Science and Engineering,Anhui University of Science&Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001

出　　处：《计算机工程与科学》2025年第3期485-493,共9页Computer Engineering & Science

基　　金：安徽省重点研究与开发计划(202104d07020010)。

摘　　要：针对基于深度学习的压缩感知重构算法中存在的图像重构细化程度低、网络泛化能力弱的问题,提出基于迭代收缩阈值与深度学习的压缩感知图像重构网络模型EH-ISTANet。该模型由采样子网、初始化子网和增强重构子网3部分组成,添加注意力机制并配合邻近映射模块将得到的特征送入增强模块中对重构图像的边缘和纹理进行增强。重构阶段模仿传统迭代收缩阈值算法的展开过程,每个阶段可以灵活地模拟测量矩阵,并在梯度下降步骤中动态地调整步长。经验证,该模型在不同数据集、不同采样率下的峰值信噪比均有所提升,表明其在提高泛化能力和重构精度方面优于其他模型。压缩感知比率为10%时,该模型在5种测试集上的平均信噪比比CSNet、AMP-Net和AMP-Net-BM模型平均提高了1.69 dB、4.36 dB和1.93 dB。Aiming at the problems of low refinement of image reconstruction and weak network generalization ability in compressive sensing reconstruction algorithms based on deep learning,a compressive sensing image reconstruction network(EH-ISTANet)based on iterative shrinkage thresholding and deep learning is proposed.The model consists of three parts:extraction subnetwork,initialization subnetwork and enhancement reconstruction subnetwork.It adds the attention mechanism and cooperates with the neighborhood mapping module to send the obtained features to the enhancement module,so as to enhance the edge and texture of the reconstructed image.The reconstruction stage mimics the unfolding process of the traditional iterative shrinkage thresholding algorithm,and each stage can flexibly model the measurement matrix and dynamically adjust the step size in the gradient descent step.It is verified that the peak signal-to-noise ratio of the model is improved in different datasets with different sampling rates.It is demonstrated that the model outperforms other models in improving generalization ability and reconstruction accuracy.When the compressive sensing rate is 10%,the average signal-to-noise ratio of this model on five testsets is improved by 1.69 dB,4.36 dB and 1.93 dB compared with CSNet,AMP-Net,and AMP-Net-BM models.

关 键 词：压缩感知 深度学习 注意力机制 特征增强 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]