Abstract

Fast keypoint recognition is essential to many vision tasks. In contrast to the classification-based approaches [1,2], we directly for- mulate the keypoint recognition as an image patch retrieval problem, which enjoys the merit of finding the matched keypoint and its pose simultaneously. A novel convolutional treelets approach is proposed to effectively extract the binary features from the patches. A correspond- ing sub-signature-based locality sensitive hashing scheme is employed for the fast approximate nearest neighbor search in patch retrieval. Exper- iments on both synthetic data and real-world images have shown that our method performs better than state-of-the-art descriptor-based and classification-based approaches.