Emotion recognition method and system of intelligent equipment

• Main Authors: WANG FEIWEN, ZHAN CHAOJUN, XIA YUCHEN, MAO JIANXU, ZHANG BIN, JIANG HAIFEI, GUO CHEN, ZHOU XIAN'EN, WU CHENGZHONG, LIU SHIFU
• Format: Patent
• Language: Chinese; English
• Published: 01.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; ELECTRIC DIGITAL DATA PROCESSING; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention relates to the field of emotion recognition, and particularly discloses an emotion recognition method and system for intelligent equipment, and the method comprises the steps: extracting implicit feature distribution information in a time dimension from an image frame of a human face monitoring video through a convolutional neural network with a three-dimensional convolution kernel; and extracting high-dimensional correlation feature information on a time sequence from time-frequency correlation features of the electroencephalogram signals, so that when the two pieces of feature information are fused, an iteration mutual weighting coefficient for performing fusion iteration weighting optimization on feature values of all positions of the feature map is introduced, and the fusion iteration weighting optimization is performed on the feature values of all the positions of the feature map. The problem that the feature map is locally optimal at some positions and cannot continue to be optimized is av