Research On Several Algorithms Of Mesh Saliency Detection

As the development of scanning technology and the improvement of computer performance ability, three-dimensional geometry model has become an emerging digital media and has been widely used in entertainment, biology information and Internet. Digital geometry processing is to process three-dimensional geometry model using computers and has become the focus of computer graphic. This dissertation does some researches on mesh saliency. The main works are listed as follows:1. This paper presents a novel mesh saliency detection approach based on manifold ranking in a descriptor space. Starting from the over-segmented patches of a mesh, we compute the local distinctness of each patch by a center-surround operator. Patches with small or high local dis-tinctness are named as background or foreground patches, respectively. Then, we estimate the saliency of patches based on their relevances to some of the most unsalient background patches, i.e. background patches with the smallest local distinctness, via manifold ranking. Finally, a Laplacian smoothing procedure is applied to spread the patch saliency to each vertex. Com-pared with ranking with some of the most salient foreground patches as queries, this improves the robustness of our method and contributes to make our method insensitive to the queries es-timated. The ranking is performed in the descriptor space of the patches by incorporating the manifold structure of the shape descriptors, which therefore is more applicable for mesh salien-cy since the salient regions of a mesh are often scattered in spatial domain. Comparisons with the state-of-the-art methods on a wide range of models show the effectiveness and robustness of our approach.2. We propose a mesh saliency detection approach using absorbing Markov chain. Our method employs feature variance to obtain insignificant regions and considers both background and foreground cues. Firstly, we partition an input mesh into a set of segments using Ncuts algorithm and then each segment is over segmented into patches based on Zernike coefficients. Afterwards, some background patches are selected by computing feature variance within the segments. Secondly, the absorbed time of each node is calculated via absorbing Markov chain with the background patches as absorbing nodes, which gives a preliminary saliency measure. Thirdly, a refined saliency result is generated in a similar way but with foreground nodes extract-ed from the preliminary saliency map as absorbing nodes, which inhibits the background and efficiently enhances salient foreground regions. Finally, a Laplacian-based smoothing procedure is utilized to spread the patch saliency to each vertex. Experimental results demonstrate that our scheme performs competitively against the state-of-the-art approaches.3. Visual saliency could be applied to guide many computer graphics tasks, including simplification, segmentation, smooth, viewpoint selection, and so on. According to the basic principles of human visual change, our method considers a center-surround operator. Since the entropy is to depict the chaos degree of system, it can be used to depict local change of the region. To calculate the entropy value of normal vector of all the vertex within the chosen vertex's local neighborhood, we adopt normal vector as the vertex descriptor. Our method is simple, fast, efficient and yields good results. We also incorporate mesh saliency in geometry processing applications.