Analysing inter-observer saliency variations in task-free viewing of natural images

Ulrich Engelke; Anthony Maeder; Hans-Jurgen Zepernick

doi:10.1109/ICIP.2010.5651009

Analysing inter-observer saliency variations in task-free viewing of natural images

Ulrich Engelke, Anthony Maeder, Hans-Jurgen Zepernick

Research output: Contribution to conference › Paper › peer-review

11 Citations (Scopus)

Abstract

We analyse variations of saliency between human observers when viewing natural image content. For this purpose, we conducted an eye tracking experiment to record gaze patterns of humans when viewing natural images. The resulting gaze patterns were used to create saliency maps for each observer and image. A correlation analysis is then conducted with the aim to quantify the variability of saliency between the observers and the different images. The results are considered to be a first step towards gaining a better understanding regarding the reliability of saliency maps for natural images.

Original language	English
Pages	1085-1088
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2010.5651009
Publication status	Published - 1 Dec 2010
Event	2010 17th IEEE International Conference on Image Processing - Duration: 26 Sept 2010 → …

Conference

Conference	2010 17th IEEE International Conference on Image Processing
Period	26/09/10 → …

Keywords

Correlation analysis
Eye tracking
Natural images
Saliency

Access to Document

10.1109/ICIP.2010.5651009

Cite this

@conference{fecc1b52053b4b6693ad7c9df0234140,

title = "Analysing inter-observer saliency variations in task-free viewing of natural images",

abstract = "We analyse variations of saliency between human observers when viewing natural image content. For this purpose, we conducted an eye tracking experiment to record gaze patterns of humans when viewing natural images. The resulting gaze patterns were used to create saliency maps for each observer and image. A correlation analysis is then conducted with the aim to quantify the variability of saliency between the observers and the different images. The results are considered to be a first step towards gaining a better understanding regarding the reliability of saliency maps for natural images.",

keywords = "Correlation analysis, Eye tracking, Natural images, Saliency",

author = "Ulrich Engelke and Anthony Maeder and Hans-Jurgen Zepernick",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/ICIP.2010.5651009",

language = "English",

pages = "1085--1088",

note = "2010 17th IEEE International Conference on Image Processing ; Conference date: 26-09-2010",

}

TY - CONF

T1 - Analysing inter-observer saliency variations in task-free viewing of natural images

AU - Engelke, Ulrich

AU - Maeder, Anthony

AU - Zepernick, Hans-Jurgen

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We analyse variations of saliency between human observers when viewing natural image content. For this purpose, we conducted an eye tracking experiment to record gaze patterns of humans when viewing natural images. The resulting gaze patterns were used to create saliency maps for each observer and image. A correlation analysis is then conducted with the aim to quantify the variability of saliency between the observers and the different images. The results are considered to be a first step towards gaining a better understanding regarding the reliability of saliency maps for natural images.

AB - We analyse variations of saliency between human observers when viewing natural image content. For this purpose, we conducted an eye tracking experiment to record gaze patterns of humans when viewing natural images. The resulting gaze patterns were used to create saliency maps for each observer and image. A correlation analysis is then conducted with the aim to quantify the variability of saliency between the observers and the different images. The results are considered to be a first step towards gaining a better understanding regarding the reliability of saliency maps for natural images.

KW - Correlation analysis

KW - Eye tracking

KW - Natural images

KW - Saliency

UR - http://www.scopus.com/inward/record.url?scp=78651071591&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5651009

DO - 10.1109/ICIP.2010.5651009

M3 - Paper

SP - 1085

EP - 1088

T2 - 2010 17th IEEE International Conference on Image Processing

Y2 - 26 September 2010

ER -

Analysing inter-observer saliency variations in task-free viewing of natural images

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this