Trending...
- The 2025 ESPY Awards After Party- Presented by Poppi & High Noon
- General Auction Company Announces August 8th Auction- Now Accepting Consignments
- $53 Million Company Valuation Investment with Majority Acquisition Option, Plus New Stock CUSIP Supporting Brand Transition of Fan Engagement Company
LOS ANGELES - Californer -- A new research paper published in eLight demonstrated a new paradigm to achieve privacy-preserving imaging by building a fundamentally new type of imager designed by AI. In their paper, UCLA researchers presented a smart camera design that images only certain types of desired objects, while instantaneously erasing other types of objects from its images without requiring any digital processing.
This new camera design consists of successive transmissive surfaces, each composed of tens of thousands of diffractive features at the scale of the wavelength of light. The structure of these transmissive surfaces is optimized using deep learning to modulate the phase of the transmitted optical fields such that the camera only images certain types/classes of desired objects and erases the others. After its deep learning-based design (training), the resulting layers are fabricated and assembled in 3D. When the input objects from the target classes of objects appear in front of this camera, they form high-quality images at the camera's output – as desired. In contrast, when the input objects in front of the same camera belong to other undesired classes, they are optically erased, forming non-informative and low-intensity patterns similar to random noise. Since the characteristic information of undesired classes of objects is all-optically erased at the camera output through light diffraction, this AI-designed camera never records their direct images. Therefore, the protection of privacy is maximized since an adversarial attack that has access to the recorded images of this camera cannot bring the information back.
More on The Californer
This AI-based camera design was also used to build encryption cameras, providing an additional layer of security and privacy protection. Such an encryption camera optically performs a selected linear transformation, exclusively for the target objects of interest. Only those with access to the decryption key (i.e., the inverse linear transformation in this case) can recover the original image of the target objects. On the other hand, the information of the other undesired objects is irreversibly lost since the AI-designed camera all-optically erases them at the output. Therefore, even if the decryption key is applied to the recorded images, it yields noise-like, unrecognizable features for other classes of undesired objects.
This research was led by Professor Aydogan Ozcan along with Professor Mona Jarrahi, both from the Electrical and Computer Engineering (ECE) department at UCLA. The other authors include graduate students Bijie Bai, Yi Luo, Tianyi Gan, Yuhang Li, Yifan Zhao, Deniz Mengu and post-doctoral researcher Dr. Jingtian Hu, all with the ECE department at UCLA. The authors report the support of the US Office of Naval Research and the US Department of Energy.
More on The Californer
See the article: https://elight.springeropen.com/articles/10.1186/s43593-022-00021-3
This new camera design consists of successive transmissive surfaces, each composed of tens of thousands of diffractive features at the scale of the wavelength of light. The structure of these transmissive surfaces is optimized using deep learning to modulate the phase of the transmitted optical fields such that the camera only images certain types/classes of desired objects and erases the others. After its deep learning-based design (training), the resulting layers are fabricated and assembled in 3D. When the input objects from the target classes of objects appear in front of this camera, they form high-quality images at the camera's output – as desired. In contrast, when the input objects in front of the same camera belong to other undesired classes, they are optically erased, forming non-informative and low-intensity patterns similar to random noise. Since the characteristic information of undesired classes of objects is all-optically erased at the camera output through light diffraction, this AI-designed camera never records their direct images. Therefore, the protection of privacy is maximized since an adversarial attack that has access to the recorded images of this camera cannot bring the information back.
More on The Californer
- A Century of Compassion: Butte Humane Society Hosts 114th Anniversary Gilded Garden Gala
- United Set to Hire More Special Olympics Athletes As Customer Service Ambassadors
- Exelon Leader Tamla Olivier Named 2025 Technologist of the Year by Waves of Change STEM Conference
- KIDZ BOP RELEASES BRAND NEW ALBUM 'KIDZ BOP 51' FEATURING HITS "APT" & "PINK PONY CLUB"
- Be Part of the World's Largest Art Biennale | Moons, Castles, Trees | Copenhagen Chronotopes
This AI-based camera design was also used to build encryption cameras, providing an additional layer of security and privacy protection. Such an encryption camera optically performs a selected linear transformation, exclusively for the target objects of interest. Only those with access to the decryption key (i.e., the inverse linear transformation in this case) can recover the original image of the target objects. On the other hand, the information of the other undesired objects is irreversibly lost since the AI-designed camera all-optically erases them at the output. Therefore, even if the decryption key is applied to the recorded images, it yields noise-like, unrecognizable features for other classes of undesired objects.
This research was led by Professor Aydogan Ozcan along with Professor Mona Jarrahi, both from the Electrical and Computer Engineering (ECE) department at UCLA. The other authors include graduate students Bijie Bai, Yi Luo, Tianyi Gan, Yuhang Li, Yifan Zhao, Deniz Mengu and post-doctoral researcher Dr. Jingtian Hu, all with the ECE department at UCLA. The authors report the support of the US Office of Naval Research and the US Department of Energy.
More on The Californer
- California sends more search and rescue crews to Texas
- YourEggs Is Leading the Way in Providing Access to the Best Asian Egg Donors to Families Worldwide
- California: Governor Newsom and Acting Governor Kounalakis honor fallen CDCR Parole Agent
- California sues to stop Trump's politically motivated attack on high-speed rail
- SeedList Launching Institutional Crypto Crowdfunding Project to Empower Retail Investors and Disrupt the VC-Dominated Crypto Fundraising Landscape
See the article: https://elight.springeropen.com/articles/10.1186/s43593-022-00021-3
Source: UCLA ITA
Filed Under: Science
0 Comments
Latest on The Californer
- CelluHeal™ Launches Full Line of Advanced Wound Dressings for Online Purchase in the USA, Canada, and Beyond
- California: Governor Newsom responds to Trump's latest gift to China: Defunding America's only high-speed rail
- California: Governor Newsom announces appointments 7.16.25
- California: Governor Newsom calls on Trump to end Los Angeles militarization, shares community resources
- City of Long Beach to Host Compost and Recycling Ambassador Program
- AMAZON DRIVERS IN CITY OF INDUSTRY JOIN THE TEAMSTERS
- Silva Construction Details Common Home Renovation Mistakes and How to Avoid Them
- Governor Newsom invites LA Fire survivors to continue shaping rebuilding efforts through Engaged California
- DOGUE Magazine and CoverDogs Announce Series A to Redefine Modern Pet Culture
- Voices for Humanity Treks High into the Himalayas to Deliver the Way to Happiness with Meena Sharma
- Nonprofit innovator named Mensa Executive Director
- Following Trump cut to LGBTQ youth suicide hotline, California steps up to fill the gap
- Yasmine Roulleau named Managing Director in Vancouver, Canada
- Chasing Elizabeth Taylor — The Dazzling True Story Behind the Queen of Diamonds Now Available in Limited-Edition Hardcover
- Swim Up Hill Animation Premieres Pilot Episode of "The Adventure of Swim Up Hill"
- LOS ANGELES TEAMSTERS AT METRO TRANSIT RATIFY FIRST CONTRACT
- Calmwater Capital Funds $22.8 Million Loan to Refinance Retail Complex in Park City
- From Barrio to Transgender Pioneer: Chapter 14 Personal Injustices Faced by the Protagonist
- Blacksmith InfoSec and Liongard Launch Strategic Integration to Simplify MSP Compliance Audits
- Surefox North America & Eagle Eye International Protective Services Announce Strategic Partnership