Visual saliency based on fast nonparametric multidimensional entropy estimation

Anh Cat Le Ngo; Guoping Qiu; Geoffrey Underwood; Li-Minn Ang; K P Seng

doi:10.1109/ICASSP.2012.6288129

Back

Visual saliency based on fast nonparametric multidimensional entropy estimation

Conference paper

Peer reviewed

Visual saliency based on fast nonparametric multidimensional entropy estimation

Anh Cat Le Ngo, Guoping Qiu, Geoffrey Underwood, Li-Minn Ang and K P Seng

Proceedings of the 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.1305-1308

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012 (Kyoto, Japan, 25-Mar-2012–30-Mar-2012)

Institute of Electrical and Electronics Engineers

2012

DOI: https://doi.org/10.1109/ICASSP.2012.6288129

Files and links (1)

url

https://doi.org/10.1109/ICASSP.2012.6288129View

Published Version

Abstract

visual saliency

conditional entropy

k-d tree

information theory

multidimensional entropy estimation

curse of dimensionality

entropy

fast nonparametric multidimensional entropy estimation

Bottom-up visual saliency can be computed through information theoretic models but existing methods face significant computational challenges. Whilst nonparametric methods suffer from the curse of dimensionality problem and are computationally expensive, parametric approaches have the difficulty of determining the shape parameters of the distribution models. This paper makes two contributions to information theoretic based visual saliency models. First, we formulate visual saliency as center surround conditional entropy which gives a direct and intuitive interpretation of the center surround mechanism under the information theoretic framework. Second, and more importantly, we introduce a fast nonparametric multidimensional entropy estimation solution to make information theoretic-based saliency models compu-tationally tractable and practicable in realtime applications. We present experimental results on publicly available eye-tracking image databases to demonstrate that the proposed method is competitive to state of the art.

Details

Title: Visual saliency based on fast nonparametric multidimensional entropy estimation
Authors: Anh Cat Le Ngo (Author) - University of Nottingham
Guoping Qiu (Author) - University of Nottingham
Geoffrey Underwood (Author) - University of Nottingham
Li-Minn Ang (Author) - University of Nottingham Malaysia Campus
K P Seng (Author) - University of Nottingham Malaysia Campus
Publication details: Proceedings of the 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.1305-1308
Conference details: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012 (Kyoto, Japan, 25-Mar-2012–30-Mar-2012)
Publisher: Institute of Electrical and Electronics Engineers
Date published: 2012
DOI: 10.1109/ICASSP.2012.6288129; 10.1109/ICASSP15465.2012
ISSN: 1520-6149; 1520-6149
ISBN: 9781467300469; 9781467300445
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99513900402621
Output Type: Conference paper

Metrics

14 Record Views