3D Textured Objects Indexing by Mixing Texture and Shape Features

In this paper, a strategy combining advantages of view-based and model-based object recognition approaches has been developed. For this end, we investigate shape and texture features. First, the three-dimensional models have to consider spatial properties such as shape. We use curvature as an intuitive and powerful similarity index for three-dimensional objects which consists of a histogram of the principal curvatures of each face of the mesh. Next, we generate 2D views from multiple viewpoints. To describe the 2D view, the feature included in the texture associated to the view is used. We chose Gabor filter, which is widely used to extract textures features from image for image retrieval. An experimental evaluation demonstrates the satisfactory performance of our approach on a fifty three-dimensional models database