Enhancing Facial Recognition: Assessing CNNs for Detecting Image Manipulation

Year : 2025 | Volume : 12 | Issue : 02 | Page : 27 36
    By

    Karshit Bhaskar,

  • Anurag Aeron,

  • Hemang Shukla,

  • Kanika Yadav,

  • Iesha,

  1. Student, Department of Computer Science and Engineering, Meerut Institute of Engineering and Technology, Meerut, Uttar Pradesh, India
  2. Professor, , Department of Computer Science and Engineering, Meerut Institute of Engineering and Technology, Meerut, Uttar Pradesh, India
  3. Student, Department of Computer Science and Engineering, Meerut Institute of Engineering and Technology, Meerut, Uttar Pradesh, India
  4. Student, Department of Computer Science and Engineering, Meerut Institute of Engineering and Technology, Meerut, Uttar Pradesh, India
  5. Student, Department of Computer Science and Engineering, Meerut Institute of Engineering and Technology, Meerut, Uttar Pradesh, India

Abstract

Deepfake technology, powered by highly advanced deep learning models, has raised significant concerns regarding media manipulation, identity theft, and the spread of online disinformation. Due to the increasing sophistication of deepfake content, traditional forensic methods often fail to detect such artificially generated images with high accuracy. Consequently, deep learning-based approaches have become essential in combating this challenge. This study compares six prominent deep learning architectures: VGG16, ResNet50, MobileNetV2, InceptionV3, EfficientNetB0, and DenseNet121, to analyze the effectiveness of Convolutional Neural Networks (CNNs) in detecting deepfake images. The models were trained on a dataset containing both real and manipulated facial images, incorporating various levels of complexity. Among the tested architectures, ResNet50 emerged as the top-performing model, achieving an impressive accuracy rate of 96.58%. The findings of this research highlight the critical role of deep learning in media verification and cybersecurity. By providing an in-depth analysis of CNN-based deepfake detection methods, this study lays the foundation for future advancements in safeguarding digital content against deceptive media attacks.

Keywords: Efficient Net, CNN, VGG19, Keras, accuracy

[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]

How to cite this article:
Karshit Bhaskar, Anurag Aeron, Hemang Shukla, Kanika Yadav, Iesha. Enhancing Facial Recognition: Assessing CNNs for Detecting Image Manipulation. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(02):27-36.
How to cite this URL:
Karshit Bhaskar, Anurag Aeron, Hemang Shukla, Kanika Yadav, Iesha. Enhancing Facial Recognition: Assessing CNNs for Detecting Image Manipulation. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(02):27-36. Available from: https://journals.stmjournals.com/joipprp/article=2025/view=208940


References

  1. 1. Cozzolino D, Verdoliva L. Noiseprint: A CNN-based camera model fingerprint. IEEE Trans Inf Forensics Secur. 2019 May 13; 15: 144–59.
  2. Zhou P, Han X, Morariu VI, Davis LS. Two-stream neural networks for tampered face detection. In 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). 2017 Jul 21; 1831–1839.
  3. Li Y, Chang MC, Lyu S. In ictu oculi: Exposing ai created fake videos by detecting eye blinking. In 2018 IEEE International workshop on information forensics and security (WIFS). 2018 Dec 11; 1–7.
  4. Afchar D, Nozick V, Yamagishi J, Echizen I. Mesonet: a compact facial video forgery detection network. In2018 IEEE international workshop on information forensics and security (WIFS). 2018 Dec 11; 1–7.
  5. Güera D, Delp EJ. Deepfake video detection using recurrent neural networks. In 2018 15th IEEE international conference on advanced video and signal based surveillance (AVSS). 2018 Nov 27; 1–6.
  6. 11Li L, Feng X, Boulkenafet Z, Xia Z, Li M, Hadid A. An original face anti-spoofing approach using partial convolutional neural network. In 2016 IEEE Sixth international conference on image processing theory, tools and applications (IPTA). 2016 Dec 12; 1–6.
  7. 12Wen D, Han H, Jain AK. Face spoof detection with image distortion analysis. IEEE Trans Inf Forensics Secur. 2015 Feb 4; 10(4): 746–61.
  8. Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019; 4401–4410.
  9. Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T. Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020; 8110–8119.
  10. Tolosana R, Vera-Rodriguez R, Fierrez J, Morales A, Ortega-Garcia J. Deepfakes and beyond: A survey of face manipulation and fake detection. Inform Fusion. 2020 Dec 1; 64: 131–48.
  11. Agarwal S, Farid H, Gu Y, He M, Nagano K, Li H. Protecting world leaders against deep fakes. In CVPR workshops. 2019 Jun 16; 38–45.
  12. Ekman P, Friesen WV. Measuring facial movement. Environmental psychology and nonverbal behavior. 1976 Sep; 1(1): 56–75.
  13. Kim Y, Yoo JH, Choi K. A motion and similarity-based fake detection method for biometric face recognition systems. IEEE Trans Consum Electron. 2011 May; 57(2): 756–62.
Regular Issue Subscription Review Article
Volume 12
Issue 02
Received 13/03/2025
Accepted 12/04/2025
Published 28/04/2025
Publication Time 46 Days
195

Login


My IP

PlumX Metrics