The Community for Technology Leaders
Green Image
Issue No. 09 - Sept. (2012 vol. 34)
ISSN: 0162-8828
pp: 1704-1716
P. Perez , Technicolor, Cesson-Sevigne, France
J. Sanchez , Res. Centre in Inf. for Eng., UTN, Cόrdoba, Argentina
C. Schmid , INRIA, St. Ismier, France
M. Douze , INRIA, St. Ismier, France
H. Jegou , INRIA, Rennes, France
F. Perronnin , Xerox, Meylan, France
This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.
vectors, image representation, image retrieval, indexing, time 250 ms, local image descriptor aggregation, compact codes, large-scale image search, search accuracy, search efficiency, memory usage, Fisher kernel, reference bag-of-visual words approach, vector dimension, dimensionality reduction optimization, indexing optimization, vector comparison, compact representation, image representation, Vectors, Accuracy, Visualization, Kernel, Indexing, Image representation, indexing., Image search, image retrieval
P. Perez, J. Sanchez, C. Schmid, M. Douze, H. Jegou, F. Perronnin, "Aggregating Local Image Descriptors into Compact Codes", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1704-1716, Sept. 2012, doi:10.1109/TPAMI.2011.235
86 ms
(Ver 3.3 (11022016))