Research on Face Expression Detection Based on Improved Faster R-CNN

Because facial expression is easy to be confused, and is easily affected by environment, Angle and other factors, this paper proposes an improved Faster R-CNN based facial expression detection method. In this method, histogram equalization and adaptive histogram equalization are preprocessed for SFEW 2.0 of the facial expression data set, and the facial expression data is enhanced and expanded. Then the repetitive experimental optimization of the hyperparameters is carried out to improve the training and learning effect of the model and improve the detection accuracy. In the end, based on the regularization model structure optimization, Soft-max cross entropy classification loss function and L1 Smooth regression loss function with parameter constraint term were proposed. The regularization method was used to optimize parameter weight, improve detection accuracy, and an improved Faster R-CNN model adapted to face expression characteristics was obtained.