Generation of Novelty Ground Truth Image Using Image Classification and Semantic Segmentation for Copy-Move Forgery Detection
Kang Hyeon Rhee
Abstract
Since the ground truth (GT) generated by CNN has pieces of patch information of the learned class, the accurate detection of Copy-Move is ambiguous. With various CNNs for image classification and semantic segmentation, the generated GT images are different yet similar to patch patterns for detecting forgery regions. It is difficult to determine which network model-generated GT image is suitable. Therefore, an optimal GT image is essential in image forensics. The proposed scheme in this paper generates a novelty GT image to solve this problem for the correct detection of Copy-Move forgery. The novelty GT image was configured using image classification and semantic segmentation. The variety of GT images is generated by adopting the state-of-the-art four image classifications and one semantic segmentation in the deep neural network. The proposed scheme implements mainly three tasks: 1) each network model generates the GT images (GT <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">net</i> ), 2) which are convergence synthesized into one (GT <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">conv</i> ), and 3) it decomposed again into GT images (GT <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">decomp</i> ) with a threshold value of the ‘Threshold Filter.’ Here, the GTnet images involve two pieces of information about the image classification and semantic segmentation of the forgery image. The GTconv has two pieces of information as one GT image. The GTdecomp is decomposed GTconv into various GT images by the threshold value, which is a permeated degree of the information about ‘Image classification’ and ‘Semantic segmentation.’ The proposed novelty GT image is accomplished with this operational flow for Copy-Move forgery detection. The results confirmed in the experiment for comparing the performance of the existing GT <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">net</i> image, and the GT <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">decomp</i> image of the proposed scheme showed that the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Accuracy</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F1 Score</i> of the proposed scheme had the maximum improvement rate of 0.4% and 0.2%, respectively. Also, by estimating the proposed CMFD scheme, Area Under the Curve (AUC) is graded as ‘ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Excellent</i> ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$A$ </tex-math></inline-formula> )’ with a value of 0.9 higher.