Deakin University
Browse

File(s) under permanent embargo

Multi-scale visual attention and saliency modelling with decision theory

Version 2 2024-06-06, 11:43
Version 1 2019-06-28, 14:10
conference contribution
posted on 2024-06-06, 11:43 authored by AC Le Ngo, LM Ang, G Qiu, KP Seng
Recently, an information-based saliency technique which is biologically plausible and computationally 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.

History

Pagination

216-220

Location

Melbourne, Vic.

Start date

2013-09-15

End date

2013-09-18

ISBN-13

9781479923410

Language

eng

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2013, IEEE

Editor/Contributor(s)

[Unknown]

Title of proceedings

ICIP 2013 : Proceedings of the 2013 IEEE International Conference on Image Processing

Event

IEEE Signal Processing Society. Conference (2013 : Melbourne, Vic.)

Publisher

Institute of Electrical and Electronics Engineers

Place of publication

Piscataway, N.J.

Series

IEEE Signal Processing Society Conference

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC