Audio and Video

Watch: AI System Maintains Person’s Anonymity by Creating a Painting Instead of Pixelating

02 August 2018

SIAT professor Steve DiPaola, pictured, together with SIAT professor Kate Hennessy and Taylor Owen from UBC’s journalism school, received a Google/Knight Foundation grant to come up with a way to replace the use of ‘blurring’ faces in news reports when anonymity is needed. Source: SFUSIAT professor Steve DiPaola, pictured, together with SIAT professor Kate Hennessy and Taylor Owen from UBC’s journalism school, received a Google/Knight Foundation grant to come up with a way to replace the use of ‘blurring’ faces in news reports when anonymity is needed. Source: SFU

SFU’s School of Interactive Arts and Technology (SIAT) has developed a new method to replace the 'blurring face' technique that is commonly used to keep people’s identities anonymous in news stories, documentaries, reality TV and more.

The new technique uses artificial intelligence (AI) to improve the visuals in a video allowing for more emotion to show through the video while maintaining the subject’s anonymity.

“Our goal is to create a working technique that would be much better at conveying emotional and knowledge information than current anonymization techniques," says DiPaola, a pioneer in AI/VR facial recognition processes.

The system doesn’t completely change the pixels of video frames. Instead, it produces a painting-like style rendition of the video frames.

The new process updates the pixelating technique with AI ‘painting' approach. Instead of completely blurring and pixelating the person’s face and basically eliminating the emotions from the face completely, the AI approach creates a “painting” on the person’s face. The “painting” allows the emotions that a person is displaying while talking to still be shown, but it disguises the person enough so no one could figure out who is speaking.

"When artists paint a portrait, they try to convey the subject's outer and inner resemblance," says DiPaola, who heads SFU's Interactive Visualization Lab. "With our AI, which learns from more than 1,000 years of artistic technique, we have taught the system to lower the outer resemblance and keep as high as possible the subject's inner resemblance - in other words, what they are conveying and how they are feeling. Our system uses five levels of AI processing to simulate a smart painter, using art abstraction to repaint the video as if an artist was painting every frame. The result is more engaging, especially since not everyone listens to stories - so the art component becomes more relevant."

The system created a better video for any media that uses anonymous interviews. It is a great tool for regular video, but also 360° and virtual reality (VR) video.

The researchers presented the new technology at the Journalism 360 conference event. To learn more, visit the website about this technology.



Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the GlobalSpec
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement