Face Dataset Augmentation with Generative Adversarial Network
Kelun Cong, Mian Zhou · Journal of Physics Conference Series · 2022
Abstract Face recognition is a widely used scene of artificial intelligence technology. However, some face occlusions cause the face to be unable to be effectively detected in a specific environment. Although many algorithms have been proposed to solve this problem, in essence, a large number of face image data containing occlusion elements is needed to train to improve the detection ability of the algorithm. In recent years, this problem can be effectively solved by using the image generation ability of generative adversarial network. This paper proposes an improved Generative Adversarial Networks (GAN), which improves the effect of occluded face image generation by adding coding module. Through the expansion of data set, the detection accuracy of several classic face detection models for occluded faces is improved by more than 3%. At the moment when the epidemic has not been over, occlusion face data is of great significance to improve the performance of face detection systems in specific public places such as customs security inspection and medical centers.