A Simplistic Global Median Filtering Forensics Based on Frequency Domain Analysis of Image Residuals

Abstract

Sophisticated image forgeries introduce digital image forensics as an active area of research. In this area, many researchers have addressed the problem of median filtering forensics. Existing median filtering detectors are adequate to classify median filtered images in uncompressed mode and in compressed mode at high-quality factors. Despite that, the field is lacking a robust method to detect median filtering in low-resolution images compressed with low-quality factors. In this article, a novel feature set (four feature dimensions), based on first-order statistics of frequency contents of median filtered residuals (MFRs) of original and median filtered images, has been proposed. The proposed feature set outperforms handcrafted features-based state-of-the-art detectors in terms of feature set dimensions and detection results obtained for low-resolution images at all quality factors. Also, results reveal the efficacy of proposed method over deep-learning-based median filtering detector. Comprehensive results expose the efficacy of the proposed detector to detect median filtering against other similar manipulations. Additionally, generalization ability test on cross-database images support the cross-validation results on four different databases. Thus, our proposed detector meets the current challenges in the field, to a great extent.