Abstract
The large amount of SIFT descriptors in an image and the high dimensionality of SIFT descriptor has made problems for large-scale image dataset in terms of speed and scalability. In this paper, we propose a descriptor selection algorithm via dictionary learning and only a small set of features are reserved, which we refer to as TOP-SIFT. We discover the inner relativity between the problem of descriptor selection and dictionary learning for sparse representation, and then turn our problem into dictionary learning. Compared with the earlier methods, our method is neither relying on the dataset nor losing important information, and the experiments have shown that our algorithm can save memory space and increase the retrieval speed efficiently while maintain the recognition performance as well.