Fake Colorized Image Detection

TL;DR

This paper introduces two novel forensic methods to detect colorized images by analyzing statistical differences in hue, saturation, dark, and bright channels, addressing a new challenge in digital image forensics.

Contribution

The paper presents the first techniques specifically designed to identify colorized images, leveraging statistical inconsistencies in multiple color channels.

Findings

Both methods outperform existing techniques in detecting colorized images.

The proposed methods are effective against multiple state-of-the-art colorization algorithms.

Detection accuracy remains high across diverse datasets.

Abstract

Image forensics aims to detect the manipulation of digital images. Currently, splicing detection, copy-move detection and image retouching detection are drawing much attentions from researchers. However, image editing techniques develop with time goes by. One emerging image editing technique is colorization, which can colorize grayscale images with realistic colors. Unfortunately, this technique may also be intentionally applied to certain images to confound object recognition algorithms. To the best of our knowledge, no forensic technique has yet been invented to identify whether an image is colorized. We observed that, compared to natural images, colorized images, which are generated by three state-of-the-art methods, possess statistical differences for the hue and saturation channels. Besides, we also observe statistical inconsistencies in the dark and bright channels, because the colorization process will inevitably affect the dark and bright channel values. Based on our observations, i.e., potential traces in the hue, saturation, dark and bright channels, we propose two simple yet effective detection methods for fake colorized images: Histogram based Fake Colorized Image Detection (FCID-HIST) and Feature Encoding based Fake Colorized Image Detection (FCID-FE). Experimental results demonstrate that both proposed methods exhibit a decent performance against multiple state-of-the-art colorization approaches.