Digital image forensics of non-uniform deblurring

被引:1
作者
Zhang, Qin [1 ]
Xiao, Huimei [2 ]
Xue, Fei [2 ]
Lu, Wei [1 ]
Liu, Hongmei [1 ]
Huang, Fangjun [1 ]
机构
[1] Sun Yat Sen Univ, Guangdong Key Lab Informat Secur Technol, Key Lab Machine Intelligence & Adv Comp, Sch Data & Comp Sci,Minist Educ, Guangzhou 510006, Guangdong, Peoples R China
[2] Sun Yat Sen Univ, Sch Elect & Informat Technol, Guangzhou 510006, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Digital image forensics; Non-uniform deblurring localization; Multi-derivative gray level co-occurrence matrix (MGLCM); Top-down multi-scale boundary fusion (TMBF); SUPERRESOLUTION IMAGE; SPARSE REPRESENTATION; BLIND DECONVOLUTION; SPLICING DETECTION; DCT; BLUR; FORGERIES; 1ST;
D O I
10.1016/j.image.2019.05.003
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Non-uniform image deblurring has been extensively studied, but forensics of whether an image is non-uniform deblurred is still an untouched area. In this paper, we firstly propose an approach to localize the non-uniform deblurring in digital images. Firstly, taking advantage of the properties of convolution derivation, multi-derivative gray level co-occurrence matrix (MGLCM) features are proposed to reveal the deblurring artifacts of images. The MGLCM features are extracted from the first and the second order derivative of images. Then sliding window strategy is used. For each sliding window, MGLCM features are extracted and SVMs are exploited to score the detection probability. By changing the scale of the sliding windows, a series of detection probability maps at different scales are obtained. Finally, top-down multi-scale boundary fusion (TMBF) is proposed to get the final detection map. The experimental results demonstrate that the proposed approach successfully localize the deblurred regions with a satisfactory performance.
引用
收藏
页码:167 / 177
页数:11
相关论文
共 62 条
[31]  
Levin A., 2011, 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), P2657, DOI 10.1109/CVPR.2011.5995308
[32]  
Levin A., 2007, Advances in Neural Information Processing Systems, P841
[33]   Image and depth from a conventional camera with a coded aperture [J].
Levin, Anat ;
Fergus, Rob ;
Durand, Fredo ;
Freeman, William T. .
ACM TRANSACTIONS ON GRAPHICS, 2007, 26 (03)
[34]  
Levin A, 2009, PROC CVPR IEEE, P1964, DOI 10.1109/CVPRW.2009.5206815
[35]   Blind image motion deblurring with L0-regularized priors [J].
Li, Jie ;
Lu, Wei .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 40 :14-23
[36]  
Liu RT, 2008, PROC CVPR IEEE, P954
[37]   Downscaling Factor Estimation on Pre-JPEG Compressed Images [J].
Liu, Xianjin ;
Lu, Wei ;
Zhang, Qin ;
Huang, Jiwu ;
Shi, Yun-Qing .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (03) :618-631
[38]   The Effects of Thiamine on Breast Cancer Cells [J].
Liu, Xiaowen ;
Montissol, Sophia ;
Uber, Amy ;
Ganley, Sarah ;
Grossestreuer, Anne V. ;
Berg, Katherine ;
Heydrick, Stanley ;
Donnino, Michael W. .
MOLECULES, 2018, 23 (06)
[39]   A bibliography on blind methods for identifying image forgery [J].
Mahdian, Babak ;
Saic, Stanislav .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 2010, 25 (06) :389-399
[40]  
Martinello M., 2011, 2011 18th IEEE International Conference on Image Processing (ICIP 2011), P3413, DOI 10.1109/ICIP.2011.6116444