Open Access

ARTICLE

DeepFake Videos Detection Based on Texture Features

by Bozhi Xu¹, Jiarui Liu¹, Jifan Liang¹, Wei Lu^1,*, Yue Zhang²

1 School of Computer Science and Engineering, Guangdong Province Key Laboratory of Information Security Technology, Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing, Sun Yat-sen University, Guangzhou, 510006, China
2 Department of Computer Science, University of Massachusetts Lowell, Lowell, 01854, MA, USA

* Corresponding Author: Wei Lu. Email:

Computers, Materials & Continua 2021, 68(1), 1375-1388. https://doi.org/10.32604/cmc.2021.016760

Received 09 January 2021; Accepted 11 February 2021; Issue published 22 March 2021

Abstract

In recent years, with the rapid development of deep learning technologies, some neural network models have been applied to generate fake media. DeepFakes, a deep learning based forgery technology, can tamper with the face easily and generate fake videos that are difficult to be distinguished by human eyes. The spread of face manipulation videos is very easy to bring fake information. Therefore, it is important to develop effective detection methods to verify the authenticity of the videos. Due to that it is still challenging for current forgery technologies to generate all facial details and the blending operations are used in the forgery process, the texture details of the fake face are insufficient. Therefore, in this paper, a new method is proposed to detect DeepFake videos. Firstly, the texture features are constructed, which are based on the gradient domain, standard deviation, gray level co-occurrence matrix and wavelet transform of the face region. Then, the features are processed by the feature selection method to form a discriminant feature vector, which is finally employed to SVM for classification at the frame level. The experimental results on the mainstream DeepFake datasets demonstrate that the proposed method can achieve ideal performance, proving the effectiveness of the proposed method for DeepFake videos detection.

---

Keywords

---

Citations