Aggregating Local Image Descriptors into Compact Codes

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 bet...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 34; no. 9; pp. 1704 - 1716
Main Authors: Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., Schmid, C.
Format: Journal Article Conference Proceeding
Language:English
Published: Los Alamitos, CA IEEE 01.09.2012
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Subjects:
Accuracy
Applied sciences
Artificial intelligence
Computer Science
Computer science; control theory; systems
Computer Vision and Pattern Recognition
Data processing. List processing. Character string processing
Exact sciences and technology
Image representation
image retrieval
Image search
Indexing
Kernel
Mathematical analysis
Memory organisation. Data processing
Microprocessors
Pattern analysis
Pattern recognition. Digital image processing. Computational geometry
Representations
Searching
Software
Vectors
Vectors (mathematics)
Visualization
Image retrieval
Image databank
High precision
Information retrieval
Fisher information
Kernel method
Image search
Dimension reduction
Bag of words
Image matching
Efficiency
Large scale
Content analysis
Indexing
indexing
image retrieval
image search
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2011.235