摘要：Due to the large individual differences in the facial features of each person and the fact that the age has a certain time sequence, the age estimation based on face images faces certain difficulties. This article proposes a method based on fusion classification and regression model: A classification model and a regression model are added to the convolutional neural network to train the network under the premise of sharing convolutional layer parameters. The classification of the age of the label is used to code the age distribution, and the age is regressed using the Euclidean distance. The final predicted value of the model is the average of the two. Experiments show that the effect of fusion classification and regression model is better than that of a single model, which improves the accuracy of age estimation.
