@article{8d74c6654bf748abad528b5c6764b930,
title = "Smoothing identification for digital image forensics",
abstract = "With the explosive development in digital techniques, ordinary people without professional training are capable to edit digital images with applications. As a common image processing manipulation, smoothing is important in editing digital images for denoising and producing blur effect. Besides, in recent years, people prefer to retouch images with smoothing algorithms to pursue better appearance. Hence it is required to expose such manipulations in digital image forensics. In this paper, a new scheme for detecting the operation of smoothing is proposed. The proposed scheme is based on analyzing the statistical property which can be considered as computation efficiently when compares to machine learning algorithms. Furthermore, a method for texture analysis is also proposed to specify the algorithm that used for smoothing. The second method adopt the features extracted from edge area. The features are fed into support vector machine for classification.",
keywords = "Bilateral filter, Image forensics, Machine learning, Smoothing detection, Texture analysis",
author = "Feng Ding and Yuxi Shi and Guopu Zhu and Shi, {Yun Qing}",
note = "Funding Information: The authors greatly appreciate the anonymous reviewers for their valuable comments. This work was supported in part by the National Natural Science Foundation of China under Grant 61572489 and Grant 61872350, in part by the Basic Research Program of Shenzhen under Grant JCYJ20170818163403748, in part by the Youth Innovation Promotion Association of CAS under Grant 2015299, in part by the CAS Light of West China Program under Grant 2016-QNXZ-A-5, in part by the Science and Technology Planning Project of Guangdong Province under Grant 2017A050501027, and in part by the Shenzhen Discipline Construction Project for Urban Computing and Data Intelligence. Funding Information: Acknowledgments The authors greatly appreciate the anonymous reviewers for their valuable comments. This work was supported in part by the National Natural Science Foundation of China under Grant 61572489 and Grant 61872350, in part by the Basic Research Program of Shenzhen under Grant JCYJ20170818163403748, in part by the Youth Innovation Promotion Association of CAS under Grant 2015299, in part by the CAS Light of West China Program under Grant 2016-QNXZ-A-5, in part by the Science and Technology Planning Project of Guangdong Province under Grant 2017A050501027, and in part by the Shenzhen Discipline Construction Project for Urban Computing and Data Intelligence. Publisher Copyright: {\textcopyright} 2018, Springer Science+Business Media, LLC, part of Springer Nature.",
year = "2019",
month = apr,
day = "1",
doi = "10.1007/s11042-018-6807-6",
language = "English (US)",
volume = "78",
pages = "8225--8245",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "7",
}