Abstract
Recently, fully convolutional network (FCN) has been successfully used to locate spliced regions in synthesized images. However, all the existing FCN-based algorithms use real-valued FCN to process each channel separately. As a consequence, they fail to capture the inherent correlation between color channels and the integrity of three channels. So, in this paper, quaternion fully convolutional network (QFCN) is proposed to generalize FCN to quaternion domain by replacing real-valued conventional blocks in FCN with quaternion conventional blocks. In addition, a new color image splicing localization algorithm is proposed by combining QFCNs and superpixel (SP)-enhanced pairwise conditional random field (CRF). QFCNs consider three different versions (QFCN32, QFCN16, and QFCN8) with different up-sampling layers. The SP-enhanced pairwise CRF is used to refine the results of QFCNs. Experimental results on three publicly available datasets demonstrate that the proposed algorithm outperforms the existing algorithms including some conventional algorithms and some deep learning-based algorithms.
Highlights
The popularity of cameras and the development of the Internet make digital images widely integrated into people's daily life
In this paper, we propose quaternion fully convolutional neural network (QFCN) to generalize fully convolutional network (FCN) to quaternion domain
In order to evaluate the efficiency of the proposed quaternion fully convolutional network (QFCN) over the conventional real-valued FCNs, the first experiment directly trains three QFCNs (QFCN32, QFCN16 and QFCN8) and FCNs (FCN32, FCN16 and FCN8) respectively for splicing localization on CASIA v2.0 dataset
Summary
The popularity of cameras and the development of the Internet make digital images widely integrated into people's daily life. There exist some clues that can be used to locate the splicing region, such as sensor noise [3,4,5], color filter array (CFA) artifacts [6,7,8], misaligned JPEG blocks [9,10,11,12], compression quantization artifacts [13] and resampling artifacts [14,15] All of these conventional algorithms are based on hand-crafted features. For color forged images, all these deep learning-based methods use real-valued CNNs to process each channel separately [25]. As a consequence, they fail to capture the inherent correlation between color channels and the integrity of three channels [26].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
