Three Google researchers have published a paper on a new artificial intelligence system called FaceNet, that they claim is one of the most-accurate ways of identifying human faces. <\/p>\n
The Google researchers, Florian Schroff, Dmitry Kalenichenko and James Philbin, say that their system achieved a new record accuracy of 99.63 per cent on the widely used Labeled Faces in the Wild (LFW) dataset. On YouTube Faces DB it achieved 95.12 per cent. \"Our system cuts the error rate in comparison to the best published result by 30 per cent on both datasets,\" the paper claims. <\/p>\n
Facial recognition is a high-interest area for both companies and governments alike. In 2014, researchers from Facebook had published a paper claiming more than 97 per cent accuracy in recognising faces. Another group of Chinese researchers claimed better than 99 per cent accuracy, according to a report on Fortune. <\/p>\n
Google researchers have published a paper on a new artificial intelligence system called FaceNet, that they claim is one of the most-accurate ways of identifying human faces. (Facial recognition, via Shutterstock) <\/p>\n
These systems incorporate an artificial intelligence technique called deep learning and also includes recognising voices and understanding the content of written text. <\/p>\n
Aside from Google and Facebook, companies including Microsoft, Baidu, and Yahoo are also investing heavily in deep learning research, says the Fortune report. The US Department of Defence's research agency DARPA, is also looking at ways in which deep learning techniques could be able to help it make sense of the massive streams of communications crossing intelligence networks. <\/p>\n
<\/p>\n
More here:<\/p>\n
Google's FaceNet facial recognition claims to be the best yet<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Three Google researchers have published a paper on a new artificial intelligence system called FaceNet, that they claim is one of the most-accurate ways of identifying human faces. The Google researchers, Florian Schroff, Dmitry Kalenichenko and James Philbin, say that their system achieved a new record accuracy of 99.63 per cent on the widely used Labeled Faces in the Wild (LFW) dataset. On YouTube Faces DB it achieved 95.12 per cent Continue reading