An improved residual neural network face recognition algorithm is proposed aiming at problem that traditional face recognition technology has limited ability to extract facial features. The algorithm improves the network performance by adjusting the structure of the original residual neural network model

increasing the convolution output appropriately

and reducing residual unit

so as to improve the ability of the residual neural network to extract facial features. Experimental results show that the proposed algorithm outperforms in face recognition performance of the existing residual network in the self-made Our Face dataset and CASIA-Web Face dataset.