Wavelet Transform-based Methods for Forensic Analysis of Digital Images

Abstract

In recent years, Generative Adversarial Networks (GANs) have been utilized in many applications of our daily lives to create digital media that was previously impossible. This paper utilizes GANs in multimedia forensics, where the precision and accuracy of image classification are crucial. The objective of the study is to detect sophisticated manipulated images generated by advanced deep learning methods using classical transformation methods. The method combines the classical wavelet transform for feature extraction with a classifier model to distinguish between real and fake images. The proposed method extracts unique features that differentiate between fake and real images, which are then fed to several gradient-boosting-based classifiers. The proposed method was tested using the FaceForensics++ dataset, which contains low-resolution video sequences of faces. The proposed model achieves an accuracy of 95% in detecting manipulated videos compared with 87% accuracy of other classical techniques.