期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：9
页码：2584-2595
出版社：Journal of Theoretical and Applied
摘要：In this paper, we propose new and robust 3D model watermarking method. Firstly, Fuzzy C-mean (FCM) algorithm clusters 3D mesh vertices into proper and improper regions for embedding the watermark to improve the imperceptibility. Afterward, the geometrical features are extracted using the mean curvature of vertices, area of triangular faces and angles between the faces normal and the average normal for rings around vertices. Further, the geometrical features are fed to fuzzy inference system (FIS) that give weights for vertices to indicate the relevance of the vertices to hiding the watermark and enhance the robustness. Finally, the watermark is blindly extracted without needing for the original models after the application of various types of attacks. The performance evaluation shows high imperceptibility and tolerance against attacks, such as addition of noise, smoothing, cropping, translation, and rotation. The proposed algorithm has been successfully designed, implemented, and tested.
关键词：3D model watermarking; Mean curvature; Geometrical properties; Fuzzy inference system; Fuzzy C;mean clustering
