Lifehacker: Use This Website to Stop Touching Your Damn Face With Your Virus Hands. “For those who are terrified of the Coronavirus, or just want to practice better habits as it relates to any infectious diseases, I recommend keeping ‘Do Not Touch Your Face’ as a pinned browser tab for the time being. Or, better yet, get it working on your kid’s computer so they stop touching their face with their gross, unwashed hands.” Unfortunately this only works if you don’t mind having a webcam pointed at your face all day.
Penn State News: Emotion expression database new resource for researchers. “The ability to understand facial expressions is an important part of social communication. However, little is known about how complex facial expression signal emotions related to social behavior and inner thoughts. To answer these questions, Penn State researchers developed the Complex Emotion Expression Database (CEED), a digital stimulus set of 243 basic and 237 complex emotional facial expressions.”
EurekAlert: New research uses physiological cues to distinguish computer-generated faces from human ones. “‘Digital human face detection in video sequences via a physiological signal analysis,’ a paper published today in the Journal of Electronic Imaging (JEI), presents a viable, innovative way to discern between natural humans (NAT) and CG faces within the context of multimedia forensics, using individuals’ heart rate as the discriminating feature.”
The New Yorker: The Age of Instagram Face. “This past summer, I booked a plane ticket to Los Angeles with the hope of investigating what seems likely to be one of the oddest legacies of our rapidly expiring decade: the gradual emergence, among professionally beautiful women, of a single, cyborgian face.”
TechCrunch: Snapchat Cameos edit your face into videos. “Snapchat is preparing to launch a big new feature that uses your selfies to replace the faces of people in videos you can then share. It’s essentially a simplified way to Deepfake you into GIFs. Snapchat Cameos are an alternative to Bitmoji for quickly conveying an emotion, reaction, or silly situation in Snapchat messages.”
USA Today: Snapchat Time Machine is a selfie-altering feature that lets you ‘age’ before your eyes. “Snapchat is picking up where Face App left off by rolling out a new tool that tries to show you what you look like at every phase of life. The app’s latest Lens is called Time Machine, and it includes a slider you can drag across your screen to watch the years add up. You can also use the feature to see what you supposedly looked like when you were younger.”
Interesting Engineering: A Database of 100,000 AI Generated Faces Is Changing the Way We Think about Stock Photos. “Artificial intelligence can now give you a quality stock photo of a model… that does not exist. That’s right, AI can now generate imaginary faces for your next project. Dubbed Generated Photos, the collection of faces was created by Konstantin Zhabinskiy and his team.”
Packt: Speech2Face: A neural network that “imagines” faces from hearing voices. Is it too soon to worry about ethnic profiling?. “The researchers designed and trained a neural network which uses millions of natural Internet/YouTube videos of people speaking. During training, they demonstrated that the model learns voice-face correlations that allows it to produce images that capture various physical attributes of the speakers such as age, gender, and ethnicity.”
CNET: This website uses AI to generate startling fake human faces. “When you visit the website “This Person Does Not Exist” you will likely see a face smiling back at you. Seems innocent enough — until you realize the face is not actually real, but generated by a neural network algorithm. That person is not real. They don’t exist.” Based on my playing with this, AI has the most problems with ears, teeth, and hair.
Friday Fun from Joe: You can use this new website to help you find your World Cup twin. “A website built by Norwegian newspaper VG lets you find this the easy way. Just upload a photo of yourself – or your mates, or your dog, or a celebrity, or whoever – and it scans through all the players at the tournament, and pulls out your doppelgänger.” I was not struck by any great resemblance when I tried this, but it was amusing.
San Francisco Museum of Modern Art: Your Pretty Face is Going to Sell. “On YouTube, there’s a long tail of content that pretty much guarantees the inclusion of every potential human interest. There are skate videos, makeup tutorials, and backyard surgical removals of blackheads. And yet the presentation of a lot of this content — especially when it’s trying to attract a large audience — is remarkably similar. Everywhere you look, there’s YouTube Face. The Face is hard to miss once you first spot it: an exaggerated expression, an overreaction to a given video’s subject, typically conveying heightened states like disgust, anger, or ecstasy. The assault of a bad smell; a bite of something intensely sour; a faked orgasm; an elbow to the guts.”
Digital Trends: Microsoft’s New Face Swap App Lets Users Insert Their Mug Into Any Image. “Face Swap is all about inserting the user’s face into an existing image without the need for any manual editing. The results are often quite silly, but the technology underpinning the app is actually rather advanced, bringing together the power of Bing image search with facial recognition technology developed by Microsoft Research.”
I missed this when it was launched in January but it looks like fun: This Museum Wants to Match You With Your Ancient Statue Doppelgänger. “In addition to supporting the arts and broadening your horizons, a trip to a museum is an opportunity to find your millennia-old look-alike hiding in an exhibit. If you haven’t been lucky enough to make such a discovery on your own, the Musée de la civilisation in Quebec City wants to help you find your match. The museum’s new project, ‘My 2000-Year-Old Double,’ pairs people’s faces with their ancient Greco-Roman or Egyptian sculpture counterparts.”
Wow: using neural networks to turn face sketches into photorealistic images. How cool is this? “A team of four neuroscientists at Radboud University is working on a model for inverting face sketches to synthesize photorealistic face images by using deep neural networks. The results of the study (Convolutional Sketch Inversion) were first made available in the online archive arXiv and have recently been accepted at the European Conference on Computer Vision in Amsterdam.”
A new search engine faceswaps you into image search results. “The system analyzes the picture of your face and determines how to intelligently crop it to leave nothing but your face. It then searches for images matching your search term — curly hair, for example — and looks for ‘doppelganger sets,’ images where the subject’s face is in a similar position to your own.” Bleh. It’s in closed beta and I can’t play with it.