Exploring the Effectiveness of Different Morphed Face Generation Techniques: A Comparative Analysis
Downloads
Generating morphed faces has become an important area of research with various applications. Traditional morphing techniques have limitations in accuracy and realism, especially when dealing with complex facial expressions and identities. This paper compares morphed face-generation techniques, including conventional morphing and deep learning-based approaches. We discuss the strengths and weaknesses of each method, highlighting the limitations of traditional techniques and the promise of deep learning-based techniques in generating highly realistic and diverse morphed faces. We also explore recent advances in deep learning-based morphing techniques, including style transfer and attention mechanisms, which provide more fine-grained control over the generated output. Finally, we discuss the challenges that need to be addressed in this field, such as the need for large amounts of training data and ethical considerations. The continued development of morphed face-generation techniques will likely lead to exciting new applications in various fields, including entertainment, advertising, and social media.
Y. Kortli, M. Jridi, A. al Falou, M. Atri, Face recognition systems: A survey, Sensors. 20 (2020) 342. https://doi.org/10.3390/s20020342.
R. V. Virgil Petrescu, Face Recognition as a Biometric Application, Mechatronics and Robotics. 3 (2019) 237–257. https://doi.org/ 10.3844/jmrsp.2019.237.257.
J. S. del Rio, D. Moctezuma, C. Conde, I. M. de Diego, E. Cabello, Automated border control e-gates and facial recognition systems, computers & security. 62 (2016) 49-72. https://doi.org/ 10.1016/j.cose.2016.07.001.
O. O. Petrova, K. B. Bulatov, Methods of machine-readable zone recognition results post-processing, In: Eleventh International Conference on Machine Vision (ICMV). 11041 (2019) 387-393. https://doi.org/10.1117/12.2522792.
S. Noori, Suspicious infrastructures: automating border control and the multiplication of mistrust through biometric e-gates, Geopolitics. 27(4) (2022) 1117-1139.
https://doi.org/10.1080/14650045.2021.1952183.
D. Ortega, A. Fernández-Isabel, I. Martín de Diego, C. Conde, E. Cabello, Dynamic facial presentation attack detection for automated border control systems, Comput Secur. 92 (2020) 101744. https://doi.org/10.1016/J.COSE.2020.101744.
A. Makrushin, T. Neubert, J. Dittmann, Automatic generation and detection of visually faultless facial morphs. In: 12th International Joint Conference on Computer Vision Theory and Applications. 7 (2017) 39–50. https://doi.org/10.5220/0006131100390050.
U. M. Kelly, L. Spreeuwers, R. Veldhuis, Improving Deep-Learning-based Face Recognition to Increase Robustness against Morphing Attacks. In: CS & IT Conference Proceedings. 10 (2020) 1–12. https://doi.org/10.5121/csit.2020.101901.
U. Scherhag, L. Debiasi, C. Rathgeb, C. Busch, A. Uhl, Detection of Face Morphing Attacks Based on PRNU Analysis, Transactions on Biometrics, Behavior, and Identity Science. 1 (2019) 302–317. https://doi.org/10.1109/TBIOM.2019.2942395.
S. Venkatesh, R. Ramachandra, K. Raja, C. Busch, Single Image Face Morphing Attack Detection Using Ensemble of Features, In: 23rd International Conference on Information Fusion, (2020) 1-6. https://doi.org/10.23919/FUSION45008.2020.9190629.
L. DeBruine, B. Jones, Face Research Lab London Set, (2017).
https://figshare.com/articles/dataset/Face_Research_Lab_London_Set/5047666/ (accessed May 30, 2017).
J. Bird, Football players and staff faces, dataset for project Generating a Football Team with Progressive GAN (PGAN) and Char-RNN, (2020). https://www.kaggle.com/datasets/birdy654/football-players-and-staff-faces/ (accessed November 27, 2022).
L. DeBruine, B. Jones, Young Adult White Faces with Manipulated Versions, (2022). https://figshare.com/articles/dataset/Young_Adult_White_Faces_with_Manipulated_Versions/4220517/ (accessed November 27, 2022).
J. M. Chen, J. B. Norman, Y. Nam, Broadening the stimulus set: Introducing the American Multiracial Faces Database, Behav Res. 53 (2021) 371–389. https://doi.org/doi: 10.3758/S13428-020-01447-8.
M. Walker, S. Schönborn, R. Greifeneder, T. Vetter, the basel face database: A validated set of photographs reflecting systematic differences in big two and big five personality dimensions, (2018). https://doi.org/10.1371/JOURNAL.PONE.0193190.
S. Adil Saribay, A. F. Biten, E. O. Meral, P. Aldan, V. Trebicky, K. Kleisner, The Bogazici face database: Standardized photographs of Turkish faces with supporting materials, (2018). https://doi.org/10.1371/JOURNAL.PONE.0192018.
D. S. Ma, J. Kantner, B. Wittenbrink, Chicago Face Database: Multiracial expansion, 53 (2021)1289–1300. https://doi.org/10.3758/S13428-020-01482-5.
N. Strohminger, K. Gray, V. Chituc, J. Heffner, C. Schein, C., T. B. Heagins, MR2 face database, (2015). https://doi.org/10.3758/T45216-060-00322-5.
S. Venkatesh, H. Zhang, R. Ramachandra, K. Raja, N. Damer, C. Busch, International Workshop on Biometrics and Forensics (IWBF), Transactions on Biometrics, Behavior, and Identity Science, 3 (2020) 154 - 154.
https://doi.org/10.1109/IWBF49977.2020.9107970
T. Neubert, A. Makrushin, M. Hildebrandt, C. Kraetzer, J. Dittmann, Extended StirTrace benchmarking of biometric and forensic qualities of morphed face images, IET Biometrics, 7 (2018) 325–332.
