Pixel Club: Siftpack: A Compact Representation for Efficient Sift Matching

Alexandra Gilinsky (EE, Technion)
Tuesday, 6.8.2013, 11:30
EE Meyer Building 861

Computing distances between large sets of SIFT descriptors is a basic step in numerous algorithms in computer vision. When the number of descriptors is large, as is often the case, computing these distances can be extremely time consuming. In this research we propose the SIFTpack: a compact way of storing SIFT descriptors, which enables significantly faster calculations between sets of SIFTs than the current solutions. SIFTpack can be used to represent SIFTs densely extracted from a single image or sparsely from multiple different images. We show that the SIFTpack representation saves both storage space and run time, for both finding nearest neighbors and for computing all distances between all descriptors. The usefulness of SIFTpack is demonstrated as an alternative implementation for K-means dictionaries of visual words and for image retrieval.

MSc seminar under the supervision of Prof. Lihi Zelnik Manor
The seminar will be delivered in Hebrew.

Back to the index of events