Graph-based clustering for identifying region of interest in eye tracker data analysis

Kanghang He; Cheng Yang; Vladimir Stankovic; Lina Stankovic

doi:10.1109/MMSP.2017.8122264

Graph-based clustering for identifying region of interest in eye tracker data analysis

Kanghang He, Cheng Yang, Vladimir Stankovic, Lina Stankovic

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

3 Citations (Scopus)

140 Downloads (Pure)

Abstract

Localization of a viewer's region of interest (ROI) on eye gaze signal trajectories acquired by eye trackers is a widely used approach in scene analysis, image compression, and quality of experience assessment. In this paper, we propose a novel clustering approach for ROI estimation from potentially noisy raw eye gaze data, based on signal processing on graphs. The clustering approach adapts graph signal processing (GSP)-based classification by first cleverly selecting a starting data sample, and then classifying the remaining samples. Furthermore, Graph Fourier Transform is used to adjust GSP parameters on-the-fly to maximise accuracy. Experimental results show competitive clustering accuracy of our proposed scheme compared to Density-based spatial clustering of applications with noise (DB-SCAN), Distance-Threshold Identification (I-DT), and Mean-Shift on publicly available Shape Dataset and the potential of estimating ROI accurately on true eye tracker data.

Original language	English
Title of host publication	2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)
Place of Publication	Piscataway, NJ.
Publisher	IEEE
Number of pages	6
ISBN (Print)	9781509036509
DOIs	https://doi.org/10.1109/MMSP.2017.8122264
Publication status	Published - 1 Dec 2017
Event	19th IEEE International Workshop on Multimedia Signal Processing - Luton, United Kingdom Duration: 16 Oct 2017 → 18 Oct 2017 https://www.beds.ac.uk/mmsp2017

Workshop

Workshop	19th IEEE International Workshop on Multimedia Signal Processing
Abbreviated title	MMSP 2017
Country/Territory	United Kingdom
City	Luton
Period	16/10/17 → 18/10/17
Internet address	https://www.beds.ac.uk/mmsp2017

Keywords

noise measurement
robustness
clustering algorithms
signal processing
clustering methods
Laplace equations
Fourier transforms

Access to Document

10.1109/MMSP.2017.8122264

He-etal-MMSP-2017-Graph-based-clustering-for-identifying-region-of-interest-in-eye-tracker-data-analysisAccepted author manuscript, 1.95 MB

Graph Signal Processing Classification with Applications
Vladimir Stankovic (Speaker)
26 Nov 2018
Activity: Talk or presentation types › Invited talk

Cite this

@inproceedings{3ae0c869a2334208a2ee89b290a301da,

title = "Graph-based clustering for identifying region of interest in eye tracker data analysis",

abstract = "Localization of a viewer's region of interest (ROI) on eye gaze signal trajectories acquired by eye trackers is a widely used approach in scene analysis, image compression, and quality of experience assessment. In this paper, we propose a novel clustering approach for ROI estimation from potentially noisy raw eye gaze data, based on signal processing on graphs. The clustering approach adapts graph signal processing (GSP)-based classification by first cleverly selecting a starting data sample, and then classifying the remaining samples. Furthermore, Graph Fourier Transform is used to adjust GSP parameters on-the-fly to maximise accuracy. Experimental results show competitive clustering accuracy of our proposed scheme compared to Density-based spatial clustering of applications with noise (DB-SCAN), Distance-Threshold Identification (I-DT), and Mean-Shift on publicly available Shape Dataset and the potential of estimating ROI accurately on true eye tracker data.",

keywords = "noise measurement, robustness, clustering algorithms, signal processing, clustering methods, Laplace equations, Fourier transforms",

author = "Kanghang He and Cheng Yang and Vladimir Stankovic and Lina Stankovic",

note = "{\textcopyright} 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 19th IEEE International Workshop on Multimedia Signal Processing, MMSP 2017 ; Conference date: 16-10-2017 Through 18-10-2017",

year = "2017",

month = dec,

day = "1",

doi = "10.1109/MMSP.2017.8122264",

language = "English",

isbn = "9781509036509",

booktitle = "2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)",

publisher = "IEEE",

url = "https://www.beds.ac.uk/mmsp2017",

}

He, K, Yang, C, Stankovic, V & Stankovic, L 2017, Graph-based clustering for identifying region of interest in eye tracker data analysis. in 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP). IEEE, Piscataway, NJ., 19th IEEE International Workshop on Multimedia Signal Processing, Luton, United Kingdom, 16/10/17. https://doi.org/10.1109/MMSP.2017.8122264

TY - GEN

T1 - Graph-based clustering for identifying region of interest in eye tracker data analysis

AU - He, Kanghang

AU - Yang, Cheng

AU - Stankovic, Vladimir

AU - Stankovic, Lina

N1 - © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Localization of a viewer's region of interest (ROI) on eye gaze signal trajectories acquired by eye trackers is a widely used approach in scene analysis, image compression, and quality of experience assessment. In this paper, we propose a novel clustering approach for ROI estimation from potentially noisy raw eye gaze data, based on signal processing on graphs. The clustering approach adapts graph signal processing (GSP)-based classification by first cleverly selecting a starting data sample, and then classifying the remaining samples. Furthermore, Graph Fourier Transform is used to adjust GSP parameters on-the-fly to maximise accuracy. Experimental results show competitive clustering accuracy of our proposed scheme compared to Density-based spatial clustering of applications with noise (DB-SCAN), Distance-Threshold Identification (I-DT), and Mean-Shift on publicly available Shape Dataset and the potential of estimating ROI accurately on true eye tracker data.

AB - Localization of a viewer's region of interest (ROI) on eye gaze signal trajectories acquired by eye trackers is a widely used approach in scene analysis, image compression, and quality of experience assessment. In this paper, we propose a novel clustering approach for ROI estimation from potentially noisy raw eye gaze data, based on signal processing on graphs. The clustering approach adapts graph signal processing (GSP)-based classification by first cleverly selecting a starting data sample, and then classifying the remaining samples. Furthermore, Graph Fourier Transform is used to adjust GSP parameters on-the-fly to maximise accuracy. Experimental results show competitive clustering accuracy of our proposed scheme compared to Density-based spatial clustering of applications with noise (DB-SCAN), Distance-Threshold Identification (I-DT), and Mean-Shift on publicly available Shape Dataset and the potential of estimating ROI accurately on true eye tracker data.

KW - noise measurement

KW - robustness

KW - clustering algorithms

KW - signal processing

KW - clustering methods

KW - Laplace equations

KW - Fourier transforms

U2 - 10.1109/MMSP.2017.8122264

DO - 10.1109/MMSP.2017.8122264

M3 - Conference contribution book

SN - 9781509036509

BT - 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)

PB - IEEE

CY - Piscataway, NJ.

T2 - 19th IEEE International Workshop on Multimedia Signal Processing

Y2 - 16 October 2017 through 18 October 2017

ER -

Graph-based clustering for identifying region of interest in eye tracker data analysis

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Activities

Graph Signal Processing Classification with Applications

Cite this