Towards Better Morphed Face Images without Ghosting Artifacts
This addresses the need for large, high-quality datasets to train robust morphing attack detectors in biometric security, representing an incremental improvement over existing methods.
The paper tackles the problem of ghosting artifacts in automatically generated morphed face images by proposing a pixel-wise alignment method during morph generation, resulting in morphs that are harder to detect by state-of-the-art detectors without impairing biometric quality.
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.