.png){kind=icon}
返回
Lensless Computational Imaging Technology Using Deep Convolutional Network
.png){kind=icon}
OA
AI
DOI：10.3390/s20092661.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Within the framework of Internet of Things or when constrained in limited space, lensless imaging technology provides effective imaging solutions with low cost and reduced size prototypes. In this paper, we proposed a method combining deep learning with lensless coded mask imaging technology. After replacing lenses with the coded mask and using the inverse matrix optimization method to reconstruct the original scene images, we applied FCN-8s, U-Net, and our modified version of U-Net, which is called Dense-U-Net, for post-processing of reconstructed images. The proposed approach showed supreme performance compared to the classical method, where a deep convolutional network leads to critical improvements of the quality of reconstruction.
Keyword:
lensless
lens-free
computational imaging
deep learning
FCN (Fully Convolutional Networks)
U-Net
Dense-U-Net
image reconstruction
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.3W
被引数:
21.2W
机构
引用论文
Quantifying Loss to the Economy Using Interrupted Time Series Models: An Application to the Wholesale and Retail Sales Industries in South Africa.png)
Economies
OAAI
EconomiesIF0
OAAI分享收藏Demonstration of Asymmetric Gate-Oxide Thickness Four-Terminal FinFETs Having Flexible Threshold Voltage and Good Subthreshold Slope演示具有灵活阈值电压和良好亚阈值摆率的非对称栅氧厚度四端FinFET器件
PREAI
分享收藏DONeRF: Towards Real‐Time Rendering of Compact Neural Radiance Fields using Depth Oracle NetworksOAAI
OAAI分享收藏分享收藏
查看更多内容