Generalized Facial Manipulation Detection with Edge Region Feature Extraction
This work addresses the problem of detecting deepfake and manipulated facial content for digital forensics and media authenticity verification, which is crucial for combating misinformation.
This paper proposes a method for detecting facial manipulation by analyzing pixel-level color features in the edge regions of images, which are often altered during synthesis processes. The framework utilizes a 3D-CNN to interpret these features spatially and temporally across multiple video frames, achieving superior accuracy and robustness compared to state-of-the-art methods in various experiments, including real-world scenarios.
This paper presents a generalized and robust face manipulation detection method based on the edge region features appearing in images. Most contemporary face synthesis processes include color awkwardness reduction but damage the natural fingerprint in the edge region. In addition, these color correction processes do not proceed in the non-face background region. We also observe that the synthesis process does not consider the natural properties of the image appearing in the time domain. Considering these observations, we propose a facial forensic framework that utilizes pixel-level color features appearing in the edge region of the whole image. Furthermore, our framework includes a 3D-CNN classification model that interprets the extracted color features spatially and temporally. Unlike other existing studies, we conduct authenticity determination by considering all features extracted from multiple frames within one video. Through extensive experiments, including real-world scenarios to evaluate generalized detection ability, we show that our framework outperforms state-of-the-art facial manipulation detection technologies in terms of accuracy and robustness.