Abstract
Face recognition is an active research subject of biometrics due to its significant research and application prospects. The performance of face recognition can be affected by a series of uncontrollable factors, such as illumination, expression, posture and occlusion, which restricts its real-world applications. Therefore, improving the robustness of face recognition to environmental changes became an urgent problem. In this paper, a simplified deep convolutional neural network structure having high robustness under unlimited conditions is designed for face recognition. This structure can improve training speed and face recognition accuracy, and be suitable for small-scale data sets. Inception Module Incorporated Siamese Convolutional Neural Networks (IMISCNN) is developed based on effective reduction of external interference and better features extraction by adopting the Siamese network structure. A cyclical learning rate strategy is also introduced in IMISCNN for better model convergence. Compared to classical face recognition algorithms, such as PCA, PCA and SVM, CNN, PCANet, and the original SNN et al. The accuracy of IMISCNN in CASIA-webface and Extended Yale B standard face database is 99.36% and 99.21%, respectively. Its feasibility and effectiveness have been verified in our experiments.
Highlights
With the improvement of security awareness, people’s demands for public and personal safety have been increasing
With the rapid development of deep learning [14], face recognition algorithms based on convolutional neural networks [15]–[17] have been widely proposed
Inspired by the findings in [23], we creatively introduce the cyclical learning rate strategy into the Siamese Network structure
Summary
With the improvement of security awareness, people’s demands for public and personal safety have been increasing. When there are environmental issues, such as occlusion, PCA cannot obtain the true subspace structure of data This will reduce the recognition accuracy significantly. With the rapid development of deep learning [14], face recognition algorithms based on convolutional neural networks [15]–[17] have been widely proposed. This type of algorithm reduces the influence of complex interference in the process of feature extraction through endto-end autonomous learning. It develops more robust feature representations, and handles high-dimensional data and large-scale training samples without pressure. Chan et al [18]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
