Imperial College London


Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Computer Vision



+44 (0)20 7594 6220k.mikolajczyk




Electrical EngineeringSouth Kensington Campus






BibTex format

author = {Boudissa, A and Tan, J and Kim, H and Ishikawa, S and Shinomiya, T and Mikolajczyk, K},
doi = {10.1007/978-3-642-40246-3_41},
pages = {332--337},
title = {A global-local approach to saliency detection},
url = {},
year = {2013}

RIS format (EndNote, RefMan)

AB - In this paper, we present a novel approach to saliency detection. We define a visually salient region with the following two properties; global saliency i.e. the spatial redundancy, and local saliency i.e. the region complexity. The former is its probability of occurrence within the image, whereas the latter defines how much information is contained within the region, and it is quantified by the entropy. By combining the global spatial redundancy measure and local entropy, we can achieve a simple, yet robust saliency detector. We evaluate it quantitatively and compare to Itti et al. [6] as well as to the spectral residual approach [5] on publicly available data where it shows a significant improvement. © 2013 Springer-Verlag.
AU - Boudissa,A
AU - Tan,J
AU - Kim,H
AU - Ishikawa,S
AU - Shinomiya,T
AU - Mikolajczyk,K
DO - 10.1007/978-3-642-40246-3_41
EP - 337
PY - 2013///
SN - 0302-9743
SP - 332
TI - A global-local approach to saliency detection
UR -
ER -