Towards Better Morphed Face Images Without Ghosting Artifacts

Clemens Seibold, Anna Hilsmann, Peter Eisert, Peter Eisert

2024

Abstract

Automatic generation of morphed face images often produces ghosting artifacts due to poorly aligned structures in the input images. Manual processing can mitigate these artifacts. However, this is not feasible for the generation of large datasets, which are required for training and evaluating robust morphing attack detectors. In this paper, we propose a method for automatic prevention of ghosting artifacts based on a pixel-wise alignment during morph generation. We evaluate our proposed method on state-of-the-art detectors and show that our morphs are harder to detect, particularly, when combined with style-transfer-based improvement of low-level image characteristics. Furthermore, we show that our approach does not impair the biometric quality, which is essential for high quality morphs.

Paper Citation

in Harvard Style

Seibold C., Hilsmann A. and Eisert P. (2024). Towards Better Morphed Face Images Without Ghosting Artifacts. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 272-281. DOI: 10.5220/0012302800003660

in Bibtex Style

@conference{visapp24,
author={Clemens Seibold and Anna Hilsmann and Peter Eisert},
title={Towards Better Morphed Face Images Without Ghosting Artifacts},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={272-281},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012302800003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Towards Better Morphed Face Images Without Ghosting Artifacts
SN - 978-989-758-679-8
AU - Seibold C.
AU - Hilsmann A.
AU - Eisert P.
PY - 2024
SP - 272
EP - 281
DO - 10.5220/0012302800003660
PB - SciTePress