FACIAL EXPRESSION RECOGNITION USING RELATIONS DETERMINED BY CLASS-TO-CLASS COMPARISONS

WIPO Patent Application WO/2017/045157

A1

Facial expressions are recognized using relations determined by class-to-class comparisons. In one example, descriptors are determined for each of a plurality of facial expression classes. Pair-wise facial expression class-to-class tasks are defined. A set of discriminative image patches are learned for each task using labelled training images. Each image patch is a portion of an image. Differences in the learned image patches in each training image are determined for each task. A relation graph is defined for each image for each task using the differences. A final descriptor is determined for each image by stacking and concatenating the relation graphs for each task. Finally, the final descriptors of the images of the are fed into a training algorithm to learn a final facial expression model.

YAO ANBANG (CN)
SHAO JUNCHAO (CN)
CHEN YURONG (CN)

PCT/CN2015/089751

March 23, 2017

September 16, 2015

Click for automatic bibliography generation  

INTEL CORP (US)
YAO ANBANG (CN)
SHAO JUNCHAO (CN)
CHEN YURONG (CN)

G06K9/00

US20150242678A1	2015-08-27
US20140063236A1	2014-03-06
CN101908149A	2010-12-08

KYPEROUNTAS, MARIOS ET AL.: "Facial Expression Recognition Using Two-Class Discriminant Features", BIOMETRIC ID MANAGEMENT AND MULTIMODAL COMMUNICATION, vol. LNCS 570, 18 September 2009 (2009-09-18), XP047399287, ISSN: 0302-9743
ZAFEIRIOU, STEFANOS ET AL.: "Discriminant Graph Structures for Facial Expression Recognition", IEEE TRANSACTIONS ON MULTIMEDIA, vol. 10, no. 8, 31 December 2008 (2008-12-31), XP011239307

NTD PATENT AND TRADEMARK AGENCY LIMITED (CN)

View/Download PDF      PDF Help

Previous Patent: CHAIN COMPOSED OF DIFFERENT PITCH LINKS WITH REPEATED SEQUENCE

Next Patent: REGISTRATION MANAGEMENT OF WIRELESS COMMUNICATION DEVICES WITH A COMMUNICATION SYSTEM