Authors:
Tomás Mardones
1
;
Héctor Allende
1
and
Claudio Moraga
2
Affiliations:
1
Universidad Técnica Federico Santa María, Chile
;
2
European Centre for Soft Computing, Spain
Keyword(s):
Fisher Vector, Image Retrieval, Feature Sampling Methods, Query by example.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Data Engineering
;
Image Understanding
;
Information Retrieval
;
Object Recognition
;
Ontologies and the Semantic Web
;
Pattern Recognition
;
Software Engineering
Abstract:
This paper addresses the problem of content-based image retrieval in a large-scale setting. Most works in
the area sample image patches using an affine invariant detector or in a dense fashion, but we show that
both sampling methods are complementary. By using Fisher Vectors we show how several sampling methods
can be combined in a simple fashion inquiring only in a small fixed computational cost while significantly
increasing the precision of the image retrieval system. As a second contribution, we show Fisher Vectors
using their variance component, normally ignored in image retrieval applications, have better performance
than their mean component under certain relevant settings. Experiments with up to 1 million images indicate
that the proposed method remains valid in large-scale image search.