Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field
Document Type
Article
Publication Date
1-1-2019
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.
Identifier
85070741621 (Scopus)
Publication Title
Mathematical Biosciences and Engineering
External Full Text Location
https://doi.org/10.3934/mbe.2019346
e-ISSN
15510018
ISSN
15471063
PubMed ID
31698595
First Page
6907
Last Page
6922
Issue
6
Volume
16
Grant
61572258
Fund Ref
National Natural Science Foundation of China
Recommended Citation
    Chen, Beijing; Gao, Ye; Xu, Lingzheng; Hong, Xiaopeng; Zheng, Yuhui; and Shi, Yun Qing, "Color image splicing localization algorithm by quaternion fully convolutional networks and superpixel-enhanced pairwise conditional random field" (2019). Faculty Publications.  8108.
    
    
    
        https://digitalcommons.njit.edu/fac_pubs/8108
    
 
				 
					