DEEPFAKE FACE DETECTION IN VIDEOS USING OPENCV AND MOBILENETV2

Abstract

The broad dissemination of altered facial photographs, especially Deepfakes, which are getting harder to identify with traditional techniques, is made possible by the Internet's quick development. While existing methods concentrate on intricate network architectures or geographical domain properties, they sometimes lack resilience against advanced counterfeit techniques. In order to overcome this, we suggest a Deepfake detection framework based on MobileNetV2, which uses effective convolutional feature extraction to accurately classify real and fake facial photos. In order to guarantee consistent input quality and improve the discriminative features for detection, the framework starts with OpenCV-based preprocessing, which includes face detection, alignment, and normalisation. By automatically learning hierarchical spatial features from the pre-processed facial photos, MobileNetV2, a lightweight yet powerful convolutional neural network, replaces the requirement for manually created features.