Multi-scale visual attention & saliency modelling with decision theory

A C Le Ngo; Li-Minn Ang; G Qiu; K P Seng

doi:10.1109/ICIP.2013.6738045

Back

Multi-scale visual attention & saliency modelling with decision theory

Conference paper

Peer reviewed

Multi-scale visual attention & saliency modelling with decision theory

A C Le Ngo, Li-Minn Ang, G Qiu and K P Seng

2013 20th IEEE International Conference on Image Processing, ICIP 2013, pp.216-220

IEEE International Conference on Image Processing, 2013 (Melbourne, Australia, 15-Sep-2013–18-Sep-2013)

Institute of Electrical and Electronics Engineers

2013

DOI: https://doi.org/10.1109/ICIP.2013.6738045

Files and links (1)

url

https://doi.org/10.1109/ICIP.2013.6738045View

Published Version

Abstract

Image processing

Discriminant power

Feature distribution

Mutual informations

Numerical tests

Qualitative evaluations

Quantitative comparison

Visual Attention

Visual examination

Recently, an information-based saliency technique which is biologically plausible and compu-tationally feasible called Discriminant Saliency (DIS) has been proposed. While DIS successfully defines discriminant saliency in the information theoretic sense, its implementation restraints the sampled features to a single fixed-size window and creates a bias towards objects with distinctive features fitted in the window size. This paper proposes a multi-scale discriminant saliency (MDIS) technique for visual attention which uses the wavelet transform for the multi-resolution framework. MDIS utilizes mutual information between classes and feature distribution to quantify classifying discriminant power as saliency value in multiple dyadic-scale structures. The paper will present simulations on Neil Bruce's image database with quantitative and qualitative results showing the advantages of MDIS over DIS. For quantitative comparisons, numerical tests AUC, NSS, LCC are measured and several plots are generated to visualized differences between simulation modes; meanwhile, qualitative evaluation is a visual examination of synthesized saliency maps of general natural scenes.

Details

Title: Multi-scale visual attention & saliency modelling with decision theory
Authors: A C Le Ngo (Author) - University of Nottingham
Li-Minn Ang (Author) - Edith Cowan University
G Qiu (Author) - University of Nottingham
K P Seng (Author) - Sunway University
Publication details: 2013 20th IEEE International Conference on Image Processing, ICIP 2013, pp.216-220
Conference details: IEEE International Conference on Image Processing, 2013 (Melbourne, Australia, 15-Sep-2013–18-Sep-2013)
Publisher: Institute of Electrical and Electronics Engineers
Date published: 2013
DOI: 10.1109/ICIP.2013.6738045
ISSN: 2381-8549; 1522-4880
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99513905102621
Output Type: Conference paper

Metrics

28 Record Views