Convolutional neural network-based human face expression identification method

Abstract

The invention relates to a human face expression identification method, in particular to a convolutional neural network-based human face expression identification method. The method comprises the steps of firstly obtaining human face images from a video, performing scale normalization operation processing on the obtained human face images to obtain human face images same in size, and performing alignment preprocessing operation on the human face images same in size to obtain preprocessed human face images; and performing feature extraction operation on the preprocessed human face images by using a convolutional neural network to obtain features of the human face images, and performing classified identification operation on the features of the human face images by utilizing a Softmax classifier. A human face expression identification algorithm realized by utilizing the convolutional neural network is an end-to-end process. According to the method, the human face images only need to be simply preprocessed and then fed into the convolutional neural network, the feature extraction is automatically performed, and a classification result is given, so that the accuracy is greatly improved, adjustable parameters are reduced, and intermediate processing steps are simplified to a great extent.

Description

technical field [0001] The invention relates to a method for recognizing facial expressions, in particular to a method for recognizing facial expressions based on a convolutional neural network. Background technique [0002] Video face images are one of the most basic and important data in the basic video platform of Safe City. The study of facial expressions plays an important role in the analysis of public opinion. However, due to the reasons of the camera itself, for example, there is dust on the camera lens or external light, etc. Influenced by various factors, the obtained video image is blurred and unclear, which has a certain impact on the facial expression recognition of the obtained target image. The speed has become slower and a lot of manpower and material resources have been wasted. [0003] At present, the feature extraction processing algorithms of traditional facial expression recognition methods include Gabor wavelet algorithm, principal component analysis a...

AI Technical Summary

Problems solved by technology

The above-mentioned traditional algorithms have their own limitations and deficiencies in the practical application of facial expression recognition, such as slow calculation speed, low accuracy rate, complex and diverse parameters that can be set and adjusted, and complicated operations

Images