A Robust 3D Mesh Watermarking Approach Based on Genetic Algorithm

In this paper, an optimized 3D watermark approach is be presented, the embedded process depends on modifying the statistical distribution radial parameter. The proposed approach consists of three Steps, the first Step depends on selecting the best vertices that will carry the watermark stream bits, these vertices called the Points of Interest (POIs). The second Step is the training process using the genetic algorithm (GA) to detect the best parameter lambda that will be used to modify the statistical distribution, this lambda grantee the optimal balance between the imperceptibility and robustness. The third Step is the embedded process by using this best lambda. The experimental results shows that the proposed approach is robust against different types of connectivity attack (like subdivision and simplifications attack) and geometrical attacks (like similarity transformation, smoothing and adding noise). The experimental results compared with the well-known method.

[1]  Mohamed Atri,et al.  3D mesh watermarking using salient points , 2018, Multimedia Tools and Applications.

[2]  Faramarz F. Samavati,et al.  3D watermarking robust to accessible attacks , 2007, IMMERSCOM.

[3]  Aboul Ella Hassanien,et al.  Interest Points Detection of 3D Mesh Model Using K Means and Shape Curvature , 2018, AISI.

[4]  Pierre Alliez,et al.  Triangle Surface Mesh Watermarking Based on a Constrained Optimization Framework , 2014, IEEE Transactions on Information Forensics and Security.

[5]  Wenyu Zhang,et al.  Double watermarks of 3D mesh model based on feature segmentation and redundancy information , 2012, Multimedia Tools and Applications.

[6]  Zhigeng Pan,et al.  A Watermarking Method for 3D Models Based on Feature Vertex Localization , 2018, IEEE Access.

[7]  Benjamin Bustos,et al.  Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes , 2011, The Visual Computer.

[8]  Ki-Ryong Kwon,et al.  A 3D Printing Model Watermarking Algorithm Based on 3D Slicing and Feature Points , 2018 .

[9]  Rémy Prost,et al.  An Oblivious Watermarking for 3-D Polygonal Meshes Using Distribution of Vertex Norms , 2007, IEEE Transactions on Signal Processing.

[10]  Umberto Castellani,et al.  Sparse points matching by combining 3D mesh saliency with statistical descriptors , 2008, Comput. Graph. Forum.

[11]  Afzal Godil,et al.  Salient local 3D features for 3D shape retrieval , 2011, Electronic Imaging.

[12]  Ligang Liu,et al.  Detecting 3D Points of Interest Using Multiple Features and Stacked Auto-encoder , 2019, IEEE Transactions on Visualization and Computer Graphics.

[13]  Aboul Ella Hassanien,et al.  A Robust 3D Mesh Watermarking Approach Using Genetic Algorithms , 2014, IEEE Conf. on Intelligent Systems.

[14]  Xiaoyang Mao,et al.  Watermarking 3D geometric models through triangle subdivision , 2001, IS&T/SPIE Electronic Imaging.