A real-time expression recognition method based on multi-channel parallel convolutional neural network

Abstract

The present invention claims to protect a real-time expression recognition method based on multi-channel parallel convolutional neural network, comprising the following steps: extracting expression data including RGB and Depth images from the facial expression data set; performing local binarization on the color image and extracting the face Key point preprocessing, gradient preprocessing of the depth image, divide the preprocessed image into training set and test set and build a multi-channel parallel convolutional neural network; send the preprocessed image in the training set to the network During training, the depth channel, lbp channel, and key point channel recognition models that learned facial expression contours, three-dimensional distribution, and key point features were obtained; the classification results of the three recognition models were fused with maximum confidence to obtain the final expression recognition model and build a real-time facial expression recognition system. The invention enhances the robustness of the recognition network and effectively improves the performance of the real-time facial expression recognition system.

Description

technical field [0001] The invention belongs to the fields of image recognition, human-computer interaction, and artificial intelligence, and in particular relates to an expression recognition method based on deep learning fusion multi-feature extraction. Background technique [0002] Facial expressions are an important carrier of human communication and an important way of non-verbal communication. Mental state, health status and other factors are extremely closely related. Psychologist Mehrabian proposed that in the process of human communication, only 7% of the information is expressed through language, and 38% is conveyed through auxiliary language, such as rhythm, voice, intonation, etc., and facial expressions account for the largest part. ——Able to reach 55% of the total amount of information. Therefore, a lot of valuable information can be obtained through the study of human facial expressions, so as to analyze human mental activities and mental states. [0003] D...

AI Technical Summary

Problems solved by technology

[0009] To sum up, although researchers have done a lot of research on facial expression recognition, there are still not many research results on deep learning in facial expression recognition. How to overcome different lighting, head postures, and complex backgrounds The impact of other practical factors is still a very thorny issue

Images