InfoQ Homepage Facial Recognition Content on InfoQ
News
RSS Feed-
AWS Researchers Propose a Method That Predicts Bias in Face Recognition Models Using Unlabeled Data
AWS researchers presented a novel method for evaluating bias in face recognition algorithms, which does not require data with identity annotations. The tests show that, despite the method's limitation to estimating a model's performance on data from various demographic groups, those estimates are reliable enough to identify performance discrepancies that are indicative of bias.
-
Microsoft Limits Public Access to AI-Powered Facial Analysis Features
Microsoft recently announced phasing out public access to AI-powered Facial Analysis features in several Azure services.
-
Amazon Rekognition Introduces Streaming Video Events
AWS recently announced the general availability of Streaming Video Events, a new feature of Amazon Rekognition to provide real-time alerts on live video streams.
-
AI Listens by Seeing as Well
Meta AI released a self-supervised speech recognition model that also uses video and achieves 75% better accuracy for some amount of data than current state-of-the-art models. This new model, Audio-Visual Hidden BERT (AV-HuBERT), uses audiovisual features for improving models based only on hearing speech. Visual features used are based on lip-reading, similar to what humans do.
-
Porting a Go-Based Face Detection Library to Wasm: Q&A with Endre Simo
Endre Simo, senior software developer and open-source contributor to a few popular image-processing projects, ported the Pigo face-detection library from Go to browsers with WebAssembly. The port illustrates the performance potential of WebAssembly today to run heavy-weight desktop applications in a browser context.
-
Amazon Introduces AWS RoboMaker for Building Intelligent Robotic Applications
At the recent AWS re:Invent 2018 conference, Amazon introduced AWS RoboMaker, a service that simplifies the development, testing and deployment of intelligent robotic applications at scale. RoboMaker includes extensions for the Robot Operating System (ROS) that enable cloud connectivity to AWS to take advantage of machine learning, cognitive, monitoring and analytics services.