COVERAGE — A novel database for copy-move forgery detection

TLDR

COVERAGE is designed to highlight and address tamper detection ambiguity of popular methods, caused by self‑similarity within natural images. We present COVERAGE, a novel database of copy‑move forged images and their originals with similar genuine objects, and propose a sparsity‑based metric for efficiently estimating forgery quality. COVERAGE annotates forged‑original pairs with duplicated and forged region masks and a tampering factor/similarity metric, and benchmarks forgery quality using computer‑vision methods and human detection performance. Experimental results show that popular forgery detection methods perform poorly on COVERAGE, while the proposed sparsity‑based metric best correlates with human detection performance, and the database is released to the research community.

Abstract

We present COVERAGE - a novel database containing copy-move forged images and their originals with similar but genuine objects. COVERAGE is designed to highlight and address tamper detection ambiguity of popular methods, caused by self-similarity within natural images. In COVERAGE, forged-original pairs are annotated with (i) the duplicated and forged region masks, and (ii) the tampering factor/similarity metric. For benchmarking, forgery quality is evaluated using (i) computer vision-based methods, and (ii) human detection performance. We also propose a novel sparsity-based metric for efficiently estimating forgery quality. Experimental results show that (a) popular forgery detection methods perform poorly over COVERAGE, and (b) the proposed sparsity based metric best correlates with human detection performance. We release the COVERAGE database to the research community.