In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 1

Dual-stream face forgery detection algorithm based on improved vit

Fan Longxin
Wang Yiding
School of Information, North China University of Technology, Beijing 100144, China
DOI: 10.19734/j.issn.1001-3695.2025.05.0196

Abstract

The dual-stream feature architecture is an effective framework for forgery image detection, as it combines different types of features to enhance the model's identification capability. Based on this architecture, this paper proposed a new face forgery detection algorithm based on an improved ViT in a dual-stream design. The proposed method addresses inaccurate fine-grained local texture representation and insufficient high-level semantic feature extraction in real and fake face images. The first stream applied LBP to the input face image and emphasizes fine-grained local texture details. A CNN extracted discriminative fine-grained features from the LBP image. In the second stream, an improved ViT model extractd high-level semantic features from the original face image. The second stream processed the image at multiple scales using convolutional operations, then computed histogram features from each scale's output. These histogram features, which encode both local texture information and global statistical patterns, are injected into the ViT through a cross-attention mechanism to impose local constraints and enhance semantic representation. Feature-level fusion combined both streams to leverage the strengths of fine-grained textures and semantic features. Experimental results demonstrate that the proposed algorithm achieves strong generalization across multiple forgery types, with an average precision of 93.9% and average accuracy of 90.0%, outperforming existing methods. The proposed method effectively combines fine-grained features with high-level semantic information, thereby improving the accuracy of fake face image detection.

Foundation Support

国家自然科学基金资助项目(62276018)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.05.0196
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 1

Publish History

[2025-09-16] Accepted Paper

Cite This Article

范龙鑫, 王一丁. 基于ViT变换双流架构的人脸图像鉴别算法研究 [J]. 计算机应用研究, 2026, 43 (1). (2025-09-17). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0196. (Fan Longxin, Wang Yiding. Dual-stream face forgery detection algorithm based on improved vit [J]. Application Research of Computers, 2026, 43 (1). (2025-09-17). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0196. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)