Facebook has reached a major milestone in computer vision and pattern recognition, with ‘DeepFace,’ an algorithm capable of identifying a face in a crowd with 97.25 percent accuracy. Which is pretty much on par with how good the average human is (97.5 percent accurate) at recognizing the faces of other walking, talking meat sacks.
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 they 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.
This project is being put forward as mostly an academic pursuit,in a research paper released last week, and the research team behind it will present its findings at the Computer Vision and Pattern Recognition conference in Columbus, Ohio in June.
Still, it has tremendous potential for future application, both for Facebook itself and in terms of its ramifications for the field of study as a whole.
Author Venkatesh Yalagandula Follow us Google + and Facebook and Twitter
No comments:
Post a Comment