Deep network model constructing method, and facial expression identification method and system

Abstract

The invention discloses a deep network model constructing method, which comprises the steps of: step S1) establishing a deep network model used for facial expression identification, and initializing parameters of the deep network model, wherein the deep network model comprises a convolutional neural network used for extracting high-level features of pictures, a reconstructed network used for extracting low-level features of the pictures and a joint decision network used for identifying facial expressions; step S2) dividing all training pictures into N groups; step S3) sequentially inputting each group of the pictures into the deep network model, and training parameters in the deep network model based on a gradient descent method; step S4) regarding the parameters of the deep network modelobtained in the step S3) as initial values of model parameters, and re-dividing all the training pictures into N groups, then jumping to the step S3), and carrying out the process repeatedly until allthe trained model parameters no longer change when compared to the initial values of the model parameters. The invention further discloses a facial expression identification method and a facial expression identification system.

Description

Technical field [0001] The invention relates to the technical field of computer vision and deep learning, in particular to a method for constructing a deep network model and a method and system for facial expression recognition. Background technique [0002] As an object that is very difficult for computers to recognize and analyze, human face has attracted wide attention of researchers since the 1990s. The successful and effective face analysis has huge application prospects in the fields of intelligent surveillance, video indexing and demographic information statistics. [0003] The existing related research in the field of face analysis is based on human "manual" determination of feature descriptors to represent human faces, combined with classifier algorithms or regression algorithms. Manual selection of features often consumes a lot of preliminary preparation time and is subjective, and the selected features often perform well on a certain type of data, but when extended to o...

AI Technical Summary

Problems solved by technology

[0006] Based on the above, applying the traditional "manual" method of determining feature descriptors in the field of face analysis, or directly applying convolutional neural networks (including other existing deep learning methods), their performance and final effect cannot meet the actual application needs

Images