公开(公告)号：US20170243053A1

公开(公告)日：2017-08-24

申请号：US15438551

申请日：2017-02-21

申请人： Pinscreen, Inc.

发明人： Hao Li ,  Tianye Li ,  Shunsuke Saito

IPC分类号： G06K9/00 ,  G06T5/20 ,  G06T11/60 ,  G06T5/00 ,  G06T7/11 ,  G06T3/40

CPC分类号： G06K9/00281 ,  G06K9/00234 ,  G06K9/4628 ,  G06T7/11 ,  G06T7/143 ,  G06T7/194 ,  G06T2207/10024 ,  G06T2207/20016 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30201

摘要： There is disclosed a system and method of performing facial recognition from RGB image data. The method includes generating a lower-resolution image from the RGB image data, performing a convolution of the lower-resolution image data to derive a probability map identifying probable facial regions and a probable non-facial regions, and performing a first deconvolution on the lower-resolution image using a bilinear interpolation layer to derive a set of coarse facial segments. The method further includes performing a second deconvolution on the lower-resolution image using a series of unpooling, deconvolution, and rectification layers to derive a set of fine facial segments, concatenating the set of coarse facial segments to the set of fine facial segments to create an image matrix made up of a set of facial segments, and generating a binary facial mask identifying probable facial regions and probable non-facial regions from the image matrix.

公开(公告)号：US10198624B2

公开(公告)日：2019-02-05

申请号：US15438551

申请日：2017-02-21

申请人： Pinscreen, Inc.

发明人： Hao Li ,  Tianye Li ,  Shunsuke Saito

IPC分类号： G06K9/00 ,  G06T7/11 ,  G06K9/46 ,  G06T7/143 ,  G06T7/194

摘要： There is disclosed a system and method of performing facial recognition from RGB image data. The method includes generating a lower-resolution image from the RGB image data, performing a convolution of the lower-resolution image data to derive a probability map identifying probable facial regions and a probable non-facial regions, and performing a first deconvolution on the lower-resolution image using a bilinear interpolation layer to derive a set of coarse facial segments. The method further includes performing a second deconvolution on the lower-resolution image using a series of unpooling, deconvolution, and rectification layers to derive a set of fine facial segments, concatenating the set of coarse facial segments to the set of fine facial segments to create an image matrix made up of a set of facial segments, and generating a binary facial mask identifying probable facial regions and probable non-facial regions from the image matrix.