Copy-Move Detection in Optical Microscopy: A Segmentation Network and A Dataset

TL;DR

This paper introduces CMSeg-Net, a novel segmentation network designed to detect copy-move forgeries in microscopic biomedical images, supported by a new dataset, FakeParaEgg, and demonstrates superior performance over existing methods.

Contribution

The paper presents CMSeg-Net, a new deep learning model with specialized modules for detecting unseen copy-move forgeries in microscopic images, and provides a new dataset for training and evaluation.

Findings

CMSeg-Net outperforms previous methods on multiple datasets.

The FakeParaEgg dataset supports robust training and evaluation.

Self-correlation and spatial-attention modules improve detection accuracy.

Abstract

With increasing revelations of academic fraud, detecting forged experimental images in the biomedical field has become a public concern. The challenge lies in the fact that copy-move targets can include background tissue, small foreground objects, or both, which may be out of the training domain and subject to unseen attacks, rendering standard object-detection-based approaches less effective. To address this, we reformulate the problem of detecting biomedical copy-move forgery regions as an intra-image co-saliency detection task and propose CMSeg-Net, a copy-move forgery segmentation network capable of identifying unseen duplicated areas. Built on a multi-resolution encoder-decoder architecture, CMSeg-Net incorporates self-correlation and correlation-assisted spatial-attention modules to detect intra-image regional similarities within feature tensors at each observation scale. This design helps distinguish even small copy-move targets in complex microscopic images from other similar objects. Furthermore, we created a copy-move forgery dataset of optical microscopic images, named FakeParaEgg, using open data from the ICIP 2022 Challenge to support CMSeg-Net's development and verify its performance. Extensive experiments demonstrate that our approach outperforms previous state-of-the-art methods on the FakeParaEgg dataset and other open copy-move detection datasets, including CASIA-CMFD, CoMoFoD, and CMF. The FakeParaEgg dataset, our source code, and the CMF dataset with our manually defined segmentation ground truths available at ``https://github.com/YoursEver/FakeParaEgg''.