DeepFace: Closing the Gap to Human-Level Performance in Face Verification
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 repres...
Hasnain says:
This is an interesting paper on face recognition.
"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."
Posted on 2014-03-13T18:24:47+0000