Automatic emotion recognition method based on bimodal signal

Abstract

The invention discloses an automatic emotion recognition method based on a bimodal signal. The method comprises the following steps: cutting and framing video data containing facial expressions and actions, extracting a facial expression picture sequence, extracting LBP-TOP features of the facial expression picture sequence, extracting pulse wave signals of the facial expression picture sequence based on a chromaticity model, and extracting time domain and frequency domain features of the pulse wave signals; fusing the extracted LBP-TOP features of the facial expression picture sequence with the time domain and frequency domain features of the pulse wave signal; dividing the fused facial expression images into a training set and a test set, inputting the training set into a support vectormachine for training and optimization, and then inputting the training set into the support vector machine to realize automatic emotion recognition in the facial expression images. According to the invention, the system complexity is greatly reduced, and the convenience of the system is improved; the fused features can avoid the problem of low recognition precision caused by artificial intentionalemotion masking or no obvious expression change of the human face.

Description

technical field [0001] The invention relates to the technical field of image processing, and more specifically, relates to an automatic emotion recognition method based on dual-mode signals. Background technique [0002] With the update of equipment and the development of artificial intelligence, emotion recognition technology is becoming more and more mature, and it is widely used in various fields such as clinical medicine, emotional intelligence, national security, and political psychology. Existing emotion recognition methods mainly include the following two types, one is based on the detection of physical signs based on precision instruments, and achieves the recognition and classification of emotions by detecting physiological signals such as human brain electricity, electrocardiogram, and pulse wave, and the other is intelligent recognition of facial emotions based on machine learning Detection, which mainly realizes emotion recognition by capturing the movement of fa...

AI Technical Summary

Problems solved by technology

[0003] However, the above two methods have their own advantages and disadvantages. The first method often requires relatively expensive and complicated equipment. Although the detection results are highly accurate, the detection costs are high, and both are contact methods, and the data collection process is relatively complex. It is complex and labor-intensive, and it is easy to bring discomfort to the subjects. Therefore, it has certain limitations in practical application and is not suitable for large-scale promotion. It is often used in some special scenarios, such as astronaut emotion detection, and military emotion after participating in major rescues. detection; and the second method is a commonly used method of identification and detection. This method does not require expensive equipment and is easy to operate

However, it cannot guarantee the accuracy of detected and recognized emotions. Although facial expressions seem to show emotional changes intuitively, many internal emotional change processes are not perceived with visual facial activities, and people can cover up and hide their emotions. experience, causing observers to misunderstand the meaning of expressions, thereby affecting the accuracy of emotion recognition

Images