Compressive sensing imaging with periodic perturbation induced caustic lens masks in a ripple tank

IF 1.7 4区 工程技术 Q2 COMPUTER SCIENCE, THEORY & METHODS
Doğan Tunca Arık, Asaf Behzat Şahin, Özgün Ersoy
{"title":"Compressive sensing imaging with periodic perturbation induced caustic lens masks in a ripple tank","authors":"Doğan Tunca Arık, Asaf Behzat Şahin, Özgün Ersoy","doi":"10.1007/s11045-024-00890-6","DOIUrl":null,"url":null,"abstract":"<p>Terahertz imaging presents immense potential across many fields but the affordability of multiple-pixel imaging equipment remains a challenge for many researchers. To address this, the adoption of single-pixel imaging emerges as a lower-cost option, however, the data acquisition process necessary for reconstructing images is time-intensive. Compressive Sensing, which allows for generation of images using a reduced number of measurements than Nyquist's theorem demands, presents a promising solution but long processing times are still issue particularly large-sized images. Our proposed solution to this issue involves using caustic lens effect induced by perturbations in a ripple tank as a sampling mask. The dynamic nature of the ripple tank introduces randomness into the sampling process and this reduces measurement time by exploiting the inherent sparsity of THz band signals. This work employed Convolutional Neural Network to perform target classification based on the distinct signal patterns acquired through the caustic lens mask. The proposed classifier achieved 99.22% accuracy rate in distinguishing targets shaped like Latin letters. The controlled randomness introduced by the caustic lens mask is believed to play a crucial role in achieving this high accuracy by mitigating overfitting, a common challenge in machine learning.</p>","PeriodicalId":19030,"journal":{"name":"Multidimensional Systems and Signal Processing","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Multidimensional Systems and Signal Processing","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s11045-024-00890-6","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

Abstract

Terahertz imaging presents immense potential across many fields but the affordability of multiple-pixel imaging equipment remains a challenge for many researchers. To address this, the adoption of single-pixel imaging emerges as a lower-cost option, however, the data acquisition process necessary for reconstructing images is time-intensive. Compressive Sensing, which allows for generation of images using a reduced number of measurements than Nyquist's theorem demands, presents a promising solution but long processing times are still issue particularly large-sized images. Our proposed solution to this issue involves using caustic lens effect induced by perturbations in a ripple tank as a sampling mask. The dynamic nature of the ripple tank introduces randomness into the sampling process and this reduces measurement time by exploiting the inherent sparsity of THz band signals. This work employed Convolutional Neural Network to perform target classification based on the distinct signal patterns acquired through the caustic lens mask. The proposed classifier achieved 99.22% accuracy rate in distinguishing targets shaped like Latin letters. The controlled randomness introduced by the caustic lens mask is believed to play a crucial role in achieving this high accuracy by mitigating overfitting, a common challenge in machine learning.

Abstract Image

利用波纹槽中的周期性扰动诱导苛性透镜掩膜进行压缩传感成像
太赫兹成像在许多领域都具有巨大的潜力,但对于许多研究人员来说,能否负担得起多像素成像设备仍然是一个挑战。为解决这一问题,采用单像素成像技术成为成本较低的选择,但重建图像所需的数据采集过程耗费大量时间。压缩传感技术允许使用比奈奎斯特定理所要求的更少的测量次数来生成图像,是一种很有前景的解决方案,但处理时间过长仍然是个问题,尤其是大型图像。针对这一问题,我们提出的解决方案是利用涟漪槽中的扰动引起的苛性透镜效应作为采样掩膜。波纹槽的动态性质为采样过程引入了随机性,从而利用太赫兹波段信号固有的稀疏性缩短了测量时间。这项工作采用卷积神经网络,根据通过苛性透镜掩膜获取的不同信号模式进行目标分类。所提出的分类器在区分形似拉丁字母的目标方面达到了 99.22% 的准确率。苛性透镜掩膜引入的可控随机性被认为在实现高准确率方面发挥了至关重要的作用,减轻了机器学习中常见的过拟合问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Multidimensional Systems and Signal Processing
Multidimensional Systems and Signal Processing 工程技术-工程:电子与电气
CiteScore
5.60
自引率
8.00%
发文量
50
审稿时长
11.7 months
期刊介绍: Multidimensional Systems and Signal Processing publishes research and selective surveys papers ranging from the fundamentals to important new findings. The journal responds to and provides a solution to the widely scattered nature of publications in this area, offering unity of theme, reduced duplication of effort, and greatly enhanced communication among researchers and practitioners in the field. A partial list of topics addressed in the journal includes multidimensional control systems design and implementation; multidimensional stability and realization theory; prediction and filtering of multidimensional processes; Spatial-temporal signal processing; multidimensional filters and filter-banks; array signal processing; and applications of multidimensional systems and signal processing to areas such as healthcare and 3-D imaging techniques.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信