Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (8): 220-224.DOI: 10.3778/j.issn.1002-8331.2001-0227

Previous Articles     Next Articles

Face Forensics Detection Method Based on Enhanced Convolutional Neural Networks

ZHANG Hanyu, WU Zhihao, XU Yong, CHEN Bin   

  1. 1.School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong 518000, China
    2.Key Laboratory of Target Detection and Discrimination, Shenzhen, Guangdong 518000, China
    3.IntelliFusion Technology Corporation, Shenzhen, Guangdong 518040, China
  • Online:2021-04-15 Published:2021-04-23



  1. 1.哈尔滨工业大学(深圳) 计算机科学与技术学院,广东 深圳 518000
    2.深圳市目标检测与判别重点实验室,广东 深圳 518000
    3.深圳市云天励飞技术有限公司,广东 深圳 518040


Because face forensics has great harm, the research on the discrimination method of face forensics is very important. The current researches on face forensics detection based on convolutional neural networks have made some progress, but the detection results are not satisfactory. Most of the existing methods focus only on a certain kind of features of the fake face, and the methods of face forensics are becoming more and more diverse, which is the main reason for the poor robustness of the discrimination result. Aiming at these problems, the proposed method exploits an excellent pre-trained model and a data augmentation method as well as a label smoothing loss function, achieving significant accuracy improvement in detection of face forensics videos. Due to the processing of frame extraction, the proposed method has high computational efficiency.

Key words: face forensics, image classification, pretrained model, data augmentation, label smoothing



关键词: 人脸篡改, 图像分类, 预训练模型, 数据增强, 标签平滑