View Context: A 3D Model Feature for Retrieval

3D model feature extraction is an important issue for 3D object retrieval. We propose a novel 3D model feature named view context and based on this we construct a, view context shape descriptor for 3D model retrieval. The view context of a particular view captures the distribution of visual information differences between this view and a set of arranged views. We select a set of feature views, compute their view contexts and use them as the shape descriptor of a 3D model. In order to enhance the retrieval accuracy, we perform an approximate symmetric axis-based 3D model alignment and propose a combined shape distance between two models, by incorporating the dissimilarity between two view context shape descriptors and the Zernike moments feature difference between the feature views of two models. Experiment results show that the view context shape descriptor is comparable with the state-of-the-art descriptors in retrieval performance.