face
Facebook facial recognition may violate EU privacy laws
Facebook has been warned by a German government lawyer to bring its facial recognition software into conformity with privacy laws in Germany and the European Union by November 7th. The action stems from Facebook's application that allows users to identify other people in online photos. Facebook is accused of violating data protection laws because it collected personal data without the explicit consent of its users. More information is available in a CIO article.
Related news on Computer Vision Central:
FTC to investigate privacy implications of face recognition
According to the Washington Post, Senator John "Jay" Rockefeller has asked the U.S. Federal Trade Commission (FTC) to examine privacy implications of face recognition technology. The FTC is to provide its finding after a workshop that it is hosting on the same subject. The concern comes amidst new face recognition technology being announced by Google, Facebook, and other web companies. Google, for example, is planning to use this technology in the Android 4.0 operating system. Senator Rockefeller has also introduced a "Do Not Track" bill for consumers to stop tracking activity by online marketers.
Related news on Computer Vision Central:
Detecting people who return to the scene of the crime
A team of researchers from the University of Notre Dame are developing computer vision software to detect people who repeatedly visit the scene of a crime or attack. It is known that some types of criminals, such as arsonists, tend to visit the scene of their crime, and the U.S. military believes that bomb-makers visit explosion sites to gather feedback for improving their improvised explosive devices (IEDs). Jeremiah Barr, Patrick Flynn, and Kevin Bowyer are developing the Questionable Observer Detector (QuOD) biometrics system, which clusters faces of people present in the area in order to report which people appear more frequently than normal. More information is available from the Notre Dame press release.
3D facial analysis tracks each pixel
Researchers from Bath University, UK, have developed a method to build models of human faces without using physical markers. These models can be used to create more realistic facial animations. Computer vision algorithms track individual pixels in each frame of video with depth information. The 3D image is projected onto a cylinder, and then unwrapped similarly to the way world maps are drawn. This method allows subtle facial movements to be captured and replicated. There are applications in film, gaming, and security. More information is available in an article in The Engineer.
Tonchidot releases Smile Fever
Startup Tonchidot has released an iPhone app, Smile Fever, that ranks a person's smile. The app is part of the company's portfolio of Sekai Apps augmented reality (AR) suite. The application supports English, Korean, and Japanese. The company is also marketing the app as an icebreaker as well as a party game.
Humans recognize faces better than machines do
In a Wall Street Journal article, author Carl Bialik points to an investigation that suggests that humans are still better at recognizing faces than face-recognition software. He suggested that some published results are "less impressive than they seem." For example, he noted the application of such software on CCTV footage that failed to detect suspects in London riots. In The Numbers Guy blog, he referenced the "Labeled Faces in the Wild" project at the University of Massachusetts-Amherst, where researchers found that humans performed better at identifying a newsmaker in an assembled database of news photographs.
Computer vision startup SceneTap counts people in bars
Forbes reports that computer vision startup SceneTap has developed a system that uses face detection and gender recognition to automatically count the number of people of each gender in a bar. Users of SceneTap's app can be notified of the crowding and gender ratios of bars to help them decide which bar to go to. SceneTap, which has received angel investment funding, has placed cameras in 50 Chicago bars, and in 200 bars across the United States.
Facial recognition provides tools for police
Facial recognition software is being used by police in the UK to track down riot suspects. However, according to a New Scientist article, the CCTV footage suffers from poor quality. The article mentions a new system called Photoface, which uses multiple 2D face images to recreate a 3D model that produces more robust recognition under different lighting and viewing angle. Photoface is being developed by the University of the West of England, under Lyndon Smith.
More information is available in a news article by Tucone.com. Also reported in the article is research at Carnegie Mellon by Alessandro Acquisti, in which facial recognition software automatically links student volunteers directly to their Facebook profiles.
Recent news on Computer Vision Central:
Algorithm developed to predict social traits from facial analysis
Researchers at the Autonomous University of Barcelona in Spain, in cooperation with Princeton University, have developed algorithms to predict personal traits from observing facial features. In a paper published in the journal PLoS ONE, Mario Rojas and associates describe their facial analysis tool that can categorize traits such as attractive, competent, trustworthy, dominant, mean, frightening, extroverted, threatening, and likable. According to a press release, they can achieve accuracies beyond 90%.
Face.com announces competition for unpaid evangelist position
The startup Face.com has announced a competition for an unpaid job, entitled "Developer Evangelist". Face.com is known for its face recognition technology. The purpose of the position is to spread the word for its "robust, free REST API". The job includes all expenses for travel around the United States for publicity events, conventions, and conferences. According to the Face.com job posting, the job is also dubbed as "social engineer".
Related news on Computer Vision Central: