Imperial College London


Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition



m.bronstein Website




569Huxley BuildingSouth Kensington Campus






BibTex format

author = {Bronstein, AM and Bronstein, MM},
doi = {10.1007/978-3-642-15552-9_15},
pages = {197--208},
title = {Spatially-sensitive affine-invariant image descriptors},
url = {},
year = {2010}

RIS format (EndNote, RefMan)

AB - Invariant image descriptors play an important role in many computer vision and pattern recognition problems such as image search and retrieval. A dominant paradigm today is that of "bags of features", a representation of images as distributions of primitive visual elements. The main disadvantage of this approach is the loss of spatial relations between features, which often carry important information about the image. In this paper, we show how to construct spatially-sensitive image descriptors in which both the features and their relation are affine-invariant. Our construction is based on a vocabulary of pairs of features coupled with a vocabulary of invariant spatial relations between the features. Experimental results show the advantage of our approach in image retrieval applications. © 2010 Springer-Verlag.
AU - Bronstein,AM
AU - Bronstein,MM
DO - 10.1007/978-3-642-15552-9_15
EP - 208
PY - 2010///
SN - 0302-9743
SP - 197
TI - Spatially-sensitive affine-invariant image descriptors
UR -
ER -