Recognition Tech: New A.I can match Face to Body A Japanese company has developed a system that would be able to identify a person even if they aren't directly facing the camera, according to New Atlas. Recognition Tech: New A.I can match Face to Body

Growing a moustache, liberally applying make-up and dying your hair are all effective ways of hiding your identity. Scientists have found that small, simple and deliberate alterations to a person's appearance are surprisingly effective in identity concealment. People were asked to judge whether two photographs that showed the same person and the study discovered the disguises reduced the ability to match faces by around 30 per cent. Scientists have found that small, simple and deliberate alterations to a person's appearance are surprisingly effective in identity concealment. Models were recruited for the study and given money to make their transformation as convincing as possible.

A research paper and associated article published yesterday made claims about the accuracy of Amazon Rekognition. We welcome feedback, and indeed get feedback from folks all the time, but this research paper and article are misleading and draw false conclusions. This blog post shares details which we hope will help clarify several misperceptions and inaccuracies. People often think of accuracy as an absolute measure, such as a percentage score on a math exam, where each answer is either right or wrong. To understand, interpret, and compare the accuracy of machine learning systems, it's important to understand what is being predicted, the confidence of the prediction, and how the prediction is to be used, which is impossible to glean from a single absolute number or score. What is being predicted: Amazon Rekognition provides two distinct face capabilities using a type of machine learning called computer vision.