Image sensing with multilayer nonlinear optical neural networks

计算机科学 人工智能 计算机视觉 图像处理 像素 编码器 图像传感器 图像(数学) 操作系统
作者
Tianyu Wang,Mandar M. Sohoni,Logan G. Wright,Martin M. Stein,Shi-Yuan Ma,Tatsuhiro Onodera,Maxwell G. Anderson,Peter L. McMahon
出处
期刊:Nature Photonics [Springer Nature]
卷期号:17 (5): 408-415 被引量:66
标识
DOI:10.1038/s41566-023-01170-8
摘要

Optical imaging is commonly used for both scientific and technological applications across industry and academia. In image sensing, a measurement, such as of an object's position, is performed by computational analysis of a digitized image. An emerging image-sensing paradigm breaks this delineation between data collection and analysis by designing optical components to perform not imaging, but encoding. By optically encoding images into a compressed, low-dimensional latent space suitable for efficient post-analysis, these image sensors can operate with fewer pixels and fewer photons, allowing higher-throughput, lower-latency operation. Optical neural networks (ONNs) offer a platform for processing data in the analog, optical domain. ONN-based sensors have however been limited to linear processing, but nonlinearity is a prerequisite for depth, and multilayer NNs significantly outperform shallow NNs on many tasks. Here, we realize a multilayer ONN pre-processor for image sensing, using a commercial image intensifier as a parallel optoelectronic, optical-to-optical nonlinear activation function. We demonstrate that the nonlinear ONN pre-processor can achieve compression ratios of up to 800:1 while still enabling high accuracy across several representative computer-vision tasks, including machine-vision benchmarks, flow-cytometry image classification, and identification of objects in real scenes. In all cases we find that the ONN's nonlinearity and depth allowed it to outperform a purely linear ONN encoder. Although our experiments are specialized to ONN sensors for incoherent-light images, alternative ONN platforms should facilitate a range of ONN sensors. These ONN sensors may surpass conventional sensors by pre-processing optical information in spatial, temporal, and/or spectral dimensions, potentially with coherent and quantum qualities, all natively in the optical domain.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
雷雷发布了新的文献求助10
2秒前
善学以致用应助葳蕤苍生采纳,获得10
2秒前
2秒前
ausue发布了新的文献求助10
2秒前
2秒前
2秒前
fuchao发布了新的文献求助10
3秒前
3秒前
一念之间发布了新的文献求助10
3秒前
杜子哥关注了科研通微信公众号
5秒前
iNk应助苏远山爱吃西红柿采纳,获得10
6秒前
7秒前
wujun发布了新的文献求助10
8秒前
9秒前
鲸妹冲啊完成签到,获得积分10
10秒前
还单身的寒云完成签到,获得积分10
10秒前
11秒前
jk258发布了新的文献求助10
11秒前
之心完成签到,获得积分20
11秒前
12秒前
13秒前
声声慢完成签到,获得积分10
14秒前
14秒前
14秒前
芝麻发布了新的文献求助10
15秒前
Jasper应助一只菜谱采纳,获得10
15秒前
16秒前
吐司匹林发布了新的文献求助10
17秒前
于浩完成签到,获得积分10
18秒前
地地道道的完成签到,获得积分10
19秒前
田様应助赤尤采纳,获得10
19秒前
千冬发布了新的文献求助10
19秒前
稳重茹嫣发布了新的文献求助30
20秒前
土三水完成签到,获得积分10
20秒前
daker发布了新的文献求助10
20秒前
21秒前
21秒前
Gilbert发布了新的文献求助10
21秒前
丘比特应助哈哈采纳,获得10
24秒前
鲸妹冲啊发布了新的文献求助10
26秒前
高分求助中
Kinetics of the Esterification Between 2-[(4-hydroxybutoxy)carbonyl] Benzoic Acid with 1,4-Butanediol: Tetrabutyl Orthotitanate as Catalyst 1000
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Very-high-order BVD Schemes Using β-variable THINC Method 568
Chen Hansheng: China’s Last Romantic Revolutionary 500
XAFS for Everyone 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3137994
求助须知:如何正确求助?哪些是违规求助? 2788986
关于积分的说明 7789404
捐赠科研通 2445432
什么是DOI,文献DOI怎么找? 1300328
科研通“疑难数据库(出版商)”最低求助积分说明 625900
版权声明 601046