Jingxi Li,1 Deniz Mengu,1 Nezih T. Yardimci,1 Xurong Li,1 Yi Luo,1 Muhammed Veli,1 Yair Rivenson,1 Mona Jarrahi,1 Aydogan Ozcanhttps://orcid.org/0000-0002-0717-683X1
1UCLA Samueli School of Engineering (United States)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Using deep learning-based training of diffractive layers we designed single-pixel machine vision systems to all-optically classify images by maximizing the output power of the wavelength corresponding to the correct data-class. We experimentally validated our diffractive designs using a plasmonic nanoantenna-based time-domain spectroscopy setup and 3D-printed diffractive layers to successfully classify the images of handwritten-digits using a single-pixel and snap-shot illumination. Furthermore, we trained a shallow electronic neural network as a decoder to reconstruct the images of the input objects, solely from the power detected at ten distinct wavelengths, also demonstrating the success of this platform as a task-specific, single-pixel imager.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Jingxi Li, Deniz Mengu, Nezih T. Yardimci, Xurong Li, Yi Luo, Muhammed Veli, Yair Rivenson, Mona Jarrahi, Aydogan Ozcan, "Spectrally encoded machine vision using trainable materials," Proc. SPIE 11703, AI and Optical Data Sciences II, 117031J (5 March 2021); https://doi.org/10.1117/12.2580625