http://en.rocketnews24.com/2014/08/24/amazing-real-time-projection-mapping-technology-blurs-line-between-reality-and-fantasy-%E3%80%90video%E3%80%91/
OMOTE / REAL-TIME FACE TRACKING & PROJECTION MAPPING from something wonderful on Vimeo.
Showing posts with label face. Show all posts
Showing posts with label face. Show all posts
Friday, August 29, 2014
Friday, March 21, 2014
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
https://www.facebook.com/publications/546316888800776/
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4,000 identities, where each identity has an average of over a thousand samples. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.25% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 25%, closely approaching human-level performance.
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4,000 identities, where each identity has an average of over a thousand samples. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.25% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 25%, closely approaching human-level performance.
Wednesday, March 19, 2014
Are we more comfortable with robots with faces?
http://www.itv.com/news/calendar/story/2014-02-11/scientists-test-robots-with-facial-expressions/
Scientists at the University of Lincoln are testing out two different robots to see how people react to them. One is capable of making five different facial expressions. The other makes gestures with its head and arm.
Scientists at the University of Lincoln are testing out two different robots to see how people react to them. One is capable of making five different facial expressions. The other makes gestures with its head and arm.
Subscribe to:
Posts (Atom)