Title :
Low complexity SIFT compression techniques
Author :
Malaguti, Filippo ; Pau, Danilo ; Stefano, Luigi Di
Author_Institution :
D.E.I.S., Univ. di Bologna, Bologna, Italy
Abstract :
Visual search for mobile devices relies on transmitting wirelessly image descriptors to a remote server. Hence, descriptors needs to be compressed to reduce bandwidth occupancy and network latency. In this paper, we investigate on the compression ratio versus accuracy of two low complexity coding schemes, based on Arithmetic and Type coding, applied to SIFT local descriptors.
Keywords :
arithmetic codes; data compression; image coding; transform coding; vocabulary; SIFT local descriptor; arithmetic-type coding; bandwidth occupancy reduction; complexity coding scheme; image descriptor; low complexity SIFT compression technique; mobile device; network latency; remote server; scale invariant feature transform; visual search; wireless transmission; Accuracy; Encoding; Image coding; Pipelines; Quantization; Vectors; Visualization;
Conference_Titel :
Consumer Electronics - Berlin (ICCE-Berlin), 2012 IEEE International Conference on
Conference_Location :
Berlin
Print_ISBN :
978-1-4673-1546-3
DOI :
10.1109/ICCE-Berlin.2012.6336446
