Jonathan Ventura and Tobias Höllerer

In this paper we report an evaluation of keypoint descriptor compression using as little as 16 bits to describe a single keypoint. We use spectral hashing to compress keypoint descriptors, and match them using the Hamming distance. By indexing the keypoints in a binary tree, we can quickly recognize keypoints with a very small database, and efficiently insert new keypoints. Our tests using image datasets with perspective distortion show the method to enable fast keypoint recognition and image retrieval with a small code size, and point towards potential applications for scalable visual SLAM on mobile phones.

Ventura, J., and T. Höllerer, "Fast and Scalable Keypoint Recognition and Image Retrieval Using Binary Codes", IEEE Workshop on Motion and Video Computing (WMCV 2011), 2011.