Information-based scale saliency methods with wavelet sub-band energy density descriptors

Anh Cat Le Ngo; Li-Minn Ang; Guoping Qiu; Kah Phooi Seng

doi:10.1007/978-3-642-36543-0_38

Back

Information-based scale saliency methods with wavelet sub-band energy density descriptors

Conference paper

Peer reviewed

Information-based scale saliency methods with wavelet sub-band energy density descriptors

Anh Cat Le Ngo, Li-Minn Ang, Guoping Qiu and Kah Phooi Seng

Intelligent Information and Database Systems: 5th Asian Conference, ACIIDS 2013, Kuala Lumpur, Malaysia, March 18-20, 2013, Proceedings, Part II, pp.366-376

Asian Conference On Intelligent Information and Database Systems (ACIIDS), 5th (Kuala Lumpur, Malaysia, 18-Mar-2013–20-Mar-2013)

Lecture Notes in Artificial Intelligence, 7803, Springer

2013

DOI: https://doi.org/10.1007/978-3-642-36543-0_38

Files and links (1)

url

https://doi.org/10.1007/978-3-642-36543-0_38View

Published Version

Abstract

discrete wavelet transform

receiver operating characteristic

area under receiver operating characteristic curve

information estimation

quaternion Fourier transform

Pixel-based scale saliency (PSS) work bases on information estimation of data content and structure in multiscale analysis; its theoretical aspects as well as practical implementation are discussed by Kadir et al [11]. Scale Saliency framework [10] does not work only for pixels but other basis-projected descriptors as well. While wavelet atoms, localization in both time and frequency domain, are possible alternative descriptors, no theoretical analysis and practical solutions have been proposed yet. Our contribution is introducing a mathematical model of utilizing wavelet-based descriptors in a correspondent Wavelet-based Scale Saliency (WSS). It treats wavelet sub-band energy density of two popular discrete wavelet transform (DWT) and dual-tree complex wavelet transform (DTCWT) as basis descriptors instead of pixel-value descriptors for saliency map estimation. Then, ROC, AUC, and NSS quantitative analysis are comparing WSS against PSS as well as other state-of-the-art saliency methods ITT [9], SUN [18], SRS [8] on N. Bruce’s database [4] with human eye-tracking data as ground-truth. Furthermore, qualitative results, different saliency maps, are analyzed case by case for their pros and cons; especially their short-comings in specific situation or insensible results for human perception.

Details

Title: Information-based scale saliency methods with wavelet sub-band energy density descriptors
Authors: Anh Cat Le Ngo (Author) - University of Nottingham Malaysia Campus
Li-Minn Ang (Author) - Edith Cowan University
Guoping Qiu (Author) - University of Nottingham
Kah Phooi Seng (Author) - Sunway University
Contributors: Ali Selamat (Editor)
Ngoc Thanh Nguyen (Editor)
Habibollah Haron (Editor)
Publication details: Intelligent Information and Database Systems: 5th Asian Conference, ACIIDS 2013, Kuala Lumpur, Malaysia, March 18-20, 2013, Proceedings, Part II, pp.366-376
Conference details: Asian Conference On Intelligent Information and Database Systems (ACIIDS), 5th (Kuala Lumpur, Malaysia, 18-Mar-2013–20-Mar-2013)
Series: Lecture Notes in Artificial Intelligence; 7803
Publisher: Springer
Date published: 2013
DOI: 10.1007/978-3-642-36543-0_38; 10.1007/978-3-642-36543-0
ISSN: 0302-9743; 1611-3349; 0302-9743
ISBN: 9783642365430
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99513789602621
Output Type: Conference paper

Metrics

15 Record Views