Concerning low accuracy of age classification of face images under unrestricted conditions, a new method of face age classification under unconstrained conditions based on deep Residual Networks (ResNets) and large dataset pre-training was proposed. Firstly, the deep residual networks were used as the basis convolutional neural network model to deal with the problem of face age classification. Secondly, the deep residual networks were trained on the ImageNet dataset to learn the expression of basic image features. Thirdly, the large-scale face age images IMDB-WIKI was cleaned, and the IMDB-WIKI-8 dataset was established for fine-tuning the deep residual networks, and migration learning from the general object image to face age image was achieved to make the model adapt to the distribution of the age group and improve the network learning capability. Finally, the fine-tuned network model was trained and tested on the unconstrained Adience dataset, and the age classification accuracy was obtained by the cross-validation method. Through the comparison of 34/50/101/152-layer residual networks, it could be seen that the more layers of the network have the higher accuracy of age classification. And the best state-of-the-art age classification result on Adience dataset with the accuracy of 65.01% was achieved by using the 152-layer residual network. The experimental results show that the combination of deeper residual network and large dataset pretraining can effectively improve the accuracy of face age classification.

There are redundant antibodies after training in self-organization Antibody Network (soAbNet) and its network performance is instable. In order to improve the performance of soAbNet, a hybrid immune diagnosis method was proposed based on intelligence complementary strategy. Immune operator was introduced into soAbNet, which consisted of two components: vaccination and immunoselection. Vaccines obtained through K-means algorithm were taken as initial antibodies in immune operator, and immune network architecture was optimized by immunoselection. The experimental results on Iris dataset demonstrate that, the proposed hybrid immune algorithm sufficiency makes use of prior knowledge and learns data characteristics effectively, and the diagnostic accuracy and data enrichment rate are higher compared with soAbNet.