人工神经网络
微波成像
计算机科学
均方误差
子空间拓扑
噪音(视频)
微波食品加热
相似性(几何)
均方根
人工智能
高斯噪声
高斯分布
算法
模式识别(心理学)
图像(数学)
数学
物理
电信
统计
量子力学
作者
Chien‐Ching Chiu,Tsai Hua Kang,Po‐Hsiang Chen,Hao Jiang,Y. K. Chen
标识
DOI:10.1080/09205071.2022.2113444
摘要
U-Net and Object-Attentional Super-Resolution Network (OASRN) neural network for electromagnetic imaging are compared and investigated in this paper. The outcome shows that though under limited training data, the regeneration capability is still highly reliable. We first transmit the electromagnetic waves to the scatterer and use the received scattered field information to calculate the estimated permittivity distribution by Green's function, subspace method and Dominant Current Scheme (DCS). The estimation technique can effectively reduce the training process of the neural network modules. Next, we train the U-Net and OASRN modules for real-time images. Lastly, we used Root Mean Square Error (RMSE) and Structural Similarity Index Measure (SSIM) to compare and analyze the reconstructed images of the two neural networks. Numerical results show that the reconstructed image by OASRN is better than that by U-net with 5% or 20% Gaussian noise for different dielectric constant distributions.
科研通智能强力驱动
Strongly Powered by AbleSci AI