Trending...
- Tampa-Based Digital Marketing Agency Launches New Website to Help Local Businesses Grow Online - 115
- California: Governor Newsom announces new tax credits that will generate $2.1 billion investment in world's 4th largest economy
- New PSA Campaign to Address Black Maternal and Infant Mortality in Los Angeles County
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
- Terra Divine Skincare Earns Coveted Spot on Organically Becca's Clean Brand Master List
- NBA Champion Lamar Odom Launches Anti-Addiction Meme Coin, Ushering in a Disruptive Innovation in Web3
- Emmetra Partners with Renesas to Advance Agentic AI-Powered Imaging Solutions
- Gravity to Bring 5-Minute EV Charging to 8 Sites Across Greater LA
- California: Governor Newsom issues statement on Pope Leo XIV, the first American Pope
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
- New poll shows high rates of employee burnout amid concerns over politics and personal finances
- Tessellations Appoints Luthern Williams as Head of School
- Aureli Construction Sets the Standard for Seamless Home Additions in Greater Boston
- Psychological Thriller "Killing Off Connor" To Open 34th IFS Film Fest After 12-years In Post
- Harvest Properties Acquires Two San Francisco Bay Area Self Storage Facilities for $44.2 Million
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
- Long Beach to Commemorate its Naval History with Commemorative Community Event
- Long Beach: City Celebrates Inaugural National Home Improvement Month: Love Where You Live
- California sues Trump administration for illegally withholding billions in bipartisan infrastructure funds: 'Another Trump gift to China'
- Tale of two trains: California high-speed rail leaves Texas in the dust
- California: State invests nearly $33 billion in cap-and-trade dollars to make communities cleaner and healthier
- Where AI Falls Short, Real Connections Rise—Media Outreach with Heart
- Cybersecurity is Protecting Your Personal Information and Your Portfolio
- EY US unveils Puneet Nanda of GuruNanda as an Entrepreneur Of The Year® 2025 Award Finalist
- California: Governor Newsom proclaims Children's Mental Health Awareness Week 2025
- VC Mastermind Launches: A Private Global Network and Podcast for Top-Tier Venture Capital Leaders
- L2 Aviation Celebrates Grand Opening of New Facility at Cincinnati/Northern Kentucky International Airport (CVG)
- Actor and Writer Ernie Rivera Launches Groundbreaking Indie Superhero Thriller, Citadel Lost, with Full Campaign and Industry Buzz
- Managing Summer Staffing Surges with Confidence: Why Name Badges Are a Must for Seasonal Success
- Visa Named Title Sponsor of Ascending Athletes' Business Owners Summits for NFL Entrepreneurs
- The Paris Court of International Arbitration Elects Dr. John J. Maalouf as its New President
- ViroMissile Unveils IDOV™ Platform: A Potential One-Shot Cure for Cancer
- $56.7 Million Announced in Q1 2025 with Revenue Growth and Progress Toward NASDAQ Uplisting for AI Marketing Company: IQSTEL, Inc. Stock Symbol: IQSTD
- SAVVY MINING raised $500 million and launched BTC.XRP.DOGE cloud mining, increasing investors' returns by 30%
- New National Nonprofit Launches to Capture Firsthand Accounts of Adoption Stories
- The Tide Project Opens at Biennale Architettura 2025 in Venice Amplifying Youth Voices