German researchers at the Fraunhofer Institute for Integrated Circuits IIS have developed a Google Glass app that recognises faces, but not the identity of the person. Emotions, gender, and age are recognised, and no images are sent over a network to do so.
Sophisticated High-speed Object Recognition Engine (SHORE) is the name of the group's software, which processes video on the Google Glass CPU. All calculations are performed in real-time by the CPU. By participating in the Google Glass "Explorer Program" Fraunhofer IIS was able to test the smart eyewear. The Google Glass app was made possible by adapting and implementing the Fraunhofer IIS SHORE software library as Glassware.
A software library of data built on C++ analyzes the face. Information about the person—happy, sad, angry, surprised, age estimation, gender—is superimposed next to the face. SHORE can also do eye-blink estimation and valence (emotion) recognition.
The researchers said the database has over 10,000 annotated faces. In combination with structure-based features and learning algorithms, they said they can train so-called models that boast extremely high recognition rates.
CNET's Seth Rosenblatt said the organization sees SHORE as a communication aid for people, for example, on the autism spectrum who may have difficulties in identifying emotions. "Fraunhofer also points out that its app could be applied to market analyses and other more commercial uses," he wrote.
Related Stories
Two Harvard students recently revealed that it's possible to combine Meta smart glasses with face image search technology to "reveal anyone's personal details," including their name, address, and phone number, "just from looking at them."
In a Google document, AnhPhu Nguyen and Caine Ardayfio explained how they linked a pair of Meta Ray Bans 2 to an invasive face search engine called PimEyes to help identify strangers by cross-searching their information on various people-search databases. They then used a large language model (LLM) to rapidly combine all that data, making it possible to dox someone in a glance or surface information to scam someone in seconds—or other nefarious uses, such as "some dude could just find some girl's home address on the train and just follow them home," Nguyen told 404 Media.
This is all possible thanks to recent progress with LLMs, the students said.
[...] To prevent anyone from being doxxed, the co-creators are not releasing the code, Nguyen said on social media site X. They did, however, outline how their disturbing tech works and how shocked random strangers used as test subjects were to discover how easily identifiable they are just from accessing with the smart glasses information posted publicly online.
[...] But while privacy is clearly important to the students and their demo video strove to remove identifying information, at least one test subject was "easily" identified anyway, 404 Media reported. That test subject couldn't be reached for comment, 404 Media reported.
So far, neither Facebook nor Google has chosen to release similar technologies that they developed linking smart glasses to face search engines, The New York Times reported.
[...] In the European Union, where collecting facial recognition data generally requires someone's direct consent under the General Data Protection Regulation, smart glasses like I-XRAY may not be as big of a concern for people who prefer to be anonymous in public spaces. But in the US, I-XRAY could be providing bad actors with their next scam.
"If people do run with this idea, I think that's really bad," Ardayfio told 404 Media. "I would hope that awareness that we've spread on how to protect your data would outweigh any of the negative impacts this could have."
(Score: 0) by Anonymous Coward on Saturday August 30 2014, @03:06AM
Now you'll be able to tell if you're looking at a male or female, if they are young or old, and if they are happy or mad.
(Score: 3, Insightful) by Tork on Saturday August 30 2014, @05:18AM
🏳️🌈 Proud Ally 🏳️🌈 - Give us ribbiti or make us croak! 🐸
(Score: 0) by Anonymous Coward on Saturday August 30 2014, @05:37AM
It'd be great tool for the blind.
Like all eyewear...
(Score: 3, Insightful) by Tork on Saturday August 30 2014, @05:52AM
🏳️🌈 Proud Ally 🏳️🌈 - Give us ribbiti or make us croak! 🐸
(Score: 3, Interesting) by tathra on Saturday August 30 2014, @06:50AM
no. think of it as an extremely primative version of Geordi LaForge's visor. it identifies the other person's sex/emotions/etc and gives the wearer feedback for them to interpret - could be by voice, it could vibrate in certain patterns, or give like little pulses/shocks, and eventually paired with neural chip implants.
it'll also probably be good for robotics. now your sexbot can tell when you're in the mood and come to you, rather than simply being a passive programmable doll!
(Score: 2) by maxwell demon on Saturday August 30 2014, @10:52AM
Could be a godsend for autistic people
The Tao of math: The numbers you can count are not the real numbers.
(Score: 2) by Magic Oddball on Sunday August 31 2014, @02:40AM
It'd be even more useful for us if it were to interpret our expressions accurately for the neurotypicals — a lot of usually-unintentional harm has been done due to their equally strong disability at reading us.
(Score: 0) by Anonymous Coward on Saturday August 30 2014, @04:09AM
Keep da whitey down! Nigga Up, Barak Forevvvvver!!!!!!!!!!!!!
(Score: 2) by q.kontinuum on Saturday August 30 2014, @08:26AM
... and in real live, while wearing Google Glass, this should be a rare occasion. So, specialized software is really not required.
Registered IRC nick on chat.soylentnews.org: qkontinuum
(Score: 0) by Anonymous Coward on Saturday August 30 2014, @09:16AM
Cumshot! not a rare occasion when you use your Google Goggles for porn, natch.
(Score: 2) by q.kontinuum on Saturday August 30 2014, @06:51PM
The software is advertised for offline use, mainly to analyse the camera capture. And in that case I still expect it will be rare cases where someone sees the facial while wearing such a device. (Well... hobby-POV producers maybe, if the camera quality of Google Glass is good enough...)
Registered IRC nick on chat.soylentnews.org: qkontinuum
(Score: 1) by Pseudonymous Coward on Saturday August 30 2014, @09:46AM
More like 'assware'!
HA! TAKE THAT, 1e100!
(Score: 2) by Tork on Saturday August 30 2014, @02:19PM
🏳️🌈 Proud Ally 🏳️🌈 - Give us ribbiti or make us croak! 🐸
(Score: 1) by pnkwarhall on Saturday August 30 2014, @07:37PM
HA! TAKE THAT, 1e100!
I see someone's been checking out their network connections... It was an eye-opener for me.
Lift Yr Skinny Fists Like Antennas to Heaven
(Score: 3, Interesting) by CRCulver on Saturday August 30 2014, @09:51AM
(Score: 2) by maxwell demon on Saturday August 30 2014, @10:55AM
The obvious strategy would be to analyse whether the face looks European or Asian, and employ different interpretation algorithms based on that.
The Tao of math: The numbers you can count are not the real numbers.
(Score: 2) by CRCulver on Saturday August 30 2014, @11:52AM
And what about the millions of Asian-looking faces living outside Asia who follow the facial-expression norms of the Western society around them?
Furthermore, even within Asia the smiling thing is limited to certain regions, the inhabitants of which may not be easy or even possible to tell apart algorithmically.