On the exploitation of DCT statistics for cropping detectors

TL;DR

This paper introduces a novel method using DCT statistics and machine learning to accurately detect image cropping and estimate original resolution, enhancing image authenticity verification and quality assessment.

Contribution

It presents a new approach leveraging DCT-based features and ML classifiers for reliable detection of cropped images and estimation of their original resolution.

Findings

High accuracy in distinguishing cropped from original images

Effective estimation of original image resolution

Potential applications in digital security and image forensics

Abstract

{The study of frequency components derived from Discrete Cosine Transform (DCT) has been widely used in image analysis. In recent years it has been observed that significant information can be extrapolated from them about the lifecycle of the image, but no study has focused on the analysis between them and the source resolution of the image. In this work, we investigated a novel image resolution classifier that employs DCT statistics with the goal to detect the original resolution of images; in particular the insight was exploited to address the challenge of identifying cropped images. Training a Machine Learning (ML) classifier on entire images (not cropped), the generated model can leverage this information to detect cropping. The results demonstrate the classifier's reliability in distinguishing between cropped and not cropped images, providing a dependable estimation of their original resolution. This advancement has significant implications for image processing applications, including digital security, authenticity verification, and visual quality analysis, by offering a new tool for detecting image manipulations and enhancing qualitative image assessment. This work opens new perspectives in the field, with potential to transform image analysis and usage across multiple domains.}