The use of support vector machines （SVM） for watermarking of 3D mesh models is investigated. SVMs have been widely explored for images, audio, and video watermarking but to date the potential of SVMs has not been ex...The use of support vector machines （SVM） for watermarking of 3D mesh models is investigated. SVMs have been widely explored for images, audio, and video watermarking but to date the potential of SVMs has not been explored in the 3D watermarking domain. The proposed approach utilizes SVM as a binary classifier for the selection of vertices for watermark embedding. The SVM is trained with feature vectors derived from the angular difference between the eigen normal and surface normals of a 1-ring neighborhood of vertices taken from normalized 3D mesh models. The SVM learns to classify vertices as appropriate or inappropriate candidates for modification in order to accommodate the watermark. Experimental results verify that the proposed algorithm is imperceptible and robust against attacks such as mesh smoothing, cropping and noise addition.展开更多
We propose a robust blind watermarking algorithm for three-dimensional(3D)mesh models based on vertex curvature to maintain good robustness and improve visual masking in 3D mesh models.In the embedding process,by usin...We propose a robust blind watermarking algorithm for three-dimensional(3D)mesh models based on vertex curvature to maintain good robustness and improve visual masking in 3D mesh models.In the embedding process,by using the local window of vertex,the root mean square curvature is calculated for every vertex of the 3D mesh model and an ordered set of fluctuation values is obtained.According to the ordered fluctuation values,the vertices are separated into bins.In each bin the fluctuation values are normalized.Finally,the mean of the root mean square curvature fluctuation values of the vertices in each bin is modulated to embed watermark information.In watermark detection,the algorithm uses a blind watermark extraction technique to extract the watermark information.The experimental results show that the algorithm has a very good performance for visual masking of the embedded model and that it can resist a variety of common attacks such as vertex rearrangement,rotation,translating,uniform scaling,noise,smoothing,quantization,and simplification.展开更多
文摘The use of support vector machines （SVM） for watermarking of 3D mesh models is investigated. SVMs have been widely explored for images, audio, and video watermarking but to date the potential of SVMs has not been explored in the 3D watermarking domain. The proposed approach utilizes SVM as a binary classifier for the selection of vertices for watermark embedding. The SVM is trained with feature vectors derived from the angular difference between the eigen normal and surface normals of a 1-ring neighborhood of vertices taken from normalized 3D mesh models. The SVM learns to classify vertices as appropriate or inappropriate candidates for modification in order to accommodate the watermark. Experimental results verify that the proposed algorithm is imperceptible and robust against attacks such as mesh smoothing, cropping and noise addition.
基金supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China(No.20113227110021)
文摘We propose a robust blind watermarking algorithm for three-dimensional(3D)mesh models based on vertex curvature to maintain good robustness and improve visual masking in 3D mesh models.In the embedding process,by using the local window of vertex,the root mean square curvature is calculated for every vertex of the 3D mesh model and an ordered set of fluctuation values is obtained.According to the ordered fluctuation values,the vertices are separated into bins.In each bin the fluctuation values are normalized.Finally,the mean of the root mean square curvature fluctuation values of the vertices in each bin is modulated to embed watermark information.In watermark detection,the algorithm uses a blind watermark extraction technique to extract the watermark information.The experimental results show that the algorithm has a very good performance for visual masking of the embedded model and that it can resist a variety of common attacks such as vertex rearrangement,rotation,translating,uniform scaling,noise,smoothing,quantization,and simplification.
