US 11,756,334 B2
Facial expression recognition
Peng Liu, San Diego, CA (US); Lei Wang, San Diego, CA (US); Kuang-Man Huang, Zhubei (TW); Michel Adib Sarkis, San Diego, CA (US); and Ning Bi, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Feb. 25, 2021, as Appl. No. 17/185,811.
Prior Publication US 2022/0269879 A1, Aug. 25, 2022
Int. Cl. G06V 40/16 (2022.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01)
CPC G06V 40/174 (2022.01) [G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06V 40/171 (2022.01)] 27 Claims
OG exemplary drawing
 
1. An apparatus for facial expression recognition, the apparatus comprising:
a memory; and
one or more processors coupled to the memory, the one or more processors being configured to:
receive an image frame corresponding to a face of a person;
determine, based on a three-dimensional model of the face, landmark feature information associated with landmark features of the face, wherein the landmark feature information includes one or more blendshape coefficients determined based on the three-dimensional model;
input, to at least one layer of a neural network trained for facial expression recognition, the image frame and the landmark feature information;
determine, using the neural network, a facial expression associated with the face;
generate the three-dimensional model of the face; and
determine the one or more blendshape coefficients based on a comparison between the three-dimensional model of the face and image data corresponding to the face within the image frame.