Emotion recognition method and system and intelligent nursing system using method

Abstract

The invention relates to an emotion recognition method and system and an intelligent nursing system using the method. The emotion recognition method comprises the steps that a tested face image and an electroencephalogram signal at the same moment or in the same time period are acquired; the tested face image and the electroencephalogram signal are processed to obtain an expression parameter value and an inner emotion parameter value respectively; data fusion processing is performed on the expression parameter value and the inner emotion parameter value to obtain an emotion fusion parameter value; and a current emotion of a tested face is recognized in a pre-stored emotion fusion database according to the emotion fusion parameter value to obtain emotion information. In this way, the information fusion technology is utilized to process a face and a body brain wave in a combined mode from face image processing and body brain wave processing, body emotion recognition is realized, the accuracy and reliability of emotion recognition are improved, recognition difficulty is lowered, and influences of individual differences on emotion recognition are avoided.

Description

technical field [0001] The invention relates to the field of emotion recognition, in particular to an emotion recognition method and system, and an intelligent nursing system applying the method. Background technique [0002] Emotion is a comprehensive state of people's feelings, thoughts and behaviors, which includes not only people's psychological reactions to external or self-stimuli due to personal experiences, but also the resulting physiological reactions. Emotion is crucial in people's daily life communication, and emotion recognition can be applied to many fields, such as intelligent robot control, entertainment, education, health care and even marketing. [0003] At present, emotion recognition is generally based on external features such as facial expressions, voice or body language. Although these features are easy to extract, they are also easy to be camouflaged, especially when people do not want others to know their thoughts. Make other reactions contrary to t...

AI Technical Summary

Problems solved by technology

[0005] 1. The quality of EEG signal collection needs to be improved, the stability is not high, and the cost is high;

[0006] 2. The real environment where the EEG signal is collected is relatively complex, which will have a greater impact on the EEG signal, and the processing of the EEG signal has high requirements for the artifact removal algorithm, and a more effective artifact removal algorithm is needed. It can remove ocular electricity, myoelectricity, electrocardiogram, power frequency interference, electromagnetic interference and other EEG signals that are not related to emotions in the EEG signal; therefore, the preprocessing of the EEG signal is to remove false The processing of the trace signal has higher requirements on the algorithm, and it is more difficult to realize;

[0007] 3. Since EEG signals have certain personality differences in the process of signal representation, and different subjects have different responses to the same stimulus material, how to find a stable relationship between emotions and EEG signal characteristics from this difference , so as to basically eliminate individual differences, is a challenging problem

Images