Visualizing Natural Image Statistics

Hui Fang, Gary Tam, Rita Borgo, Andrew Aubrey, Phil Grant, Paul Rosin, Christian Wallraven, Douglas Cunningham, David Marshall, Min Chen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Natural image statistics is an important area of research in cognitive sciences and computer vision. Visualization of statistical results can help identify clusters and anomalies as well as analyze deviation, distribution, and correlation. Furthermore, they can provide visual abstractions and symbolism for categorized data. In this paper, we begin our study of visualization of image statistics by considering visual representations of power spectra, which are commonly used to visualize different categories of images. We show that they convey a limited amount of statistical information about image categories and their support for analytical tasks is ineffective. We then introduce several new visual representations, which convey different or more information about image statistics. We apply ANOVA to the image statistics to help select statistically more meaningful measurements in our design process. A task based user evaluation was carried out to compare the new visual representations with the conventional power spectra plots. Based on the results of the evaluation, we made further improvement of visualizations by introducing composite visual representations of image statistics.
Original languageEnglish
Pages (from-to)1228-1241
JournalIEEE Transactions on Visualization and Computer Graphics
Volume19
Issue number7
Publication statusPublished - Jul 2013

Fingerprint

Statistics
Visualization
Power spectrum
Analysis of variance (ANOVA)
Computer vision
Composite materials

Cite this

Fang, H., Tam, G., Borgo, R., Aubrey, A., Grant, P., Rosin, P., ... Chen, M. (2013). Visualizing Natural Image Statistics. IEEE Transactions on Visualization and Computer Graphics, 19(7), 1228-1241.
Fang, Hui ; Tam, Gary ; Borgo, Rita ; Aubrey, Andrew ; Grant, Phil ; Rosin, Paul ; Wallraven, Christian ; Cunningham, Douglas ; Marshall, David ; Chen, Min. / Visualizing Natural Image Statistics. In: IEEE Transactions on Visualization and Computer Graphics. 2013 ; Vol. 19, No. 7. pp. 1228-1241.
@article{05401966afcd4b0f80ea780e89035691,
title = "Visualizing Natural Image Statistics",
abstract = "Natural image statistics is an important area of research in cognitive sciences and computer vision. Visualization of statistical results can help identify clusters and anomalies as well as analyze deviation, distribution, and correlation. Furthermore, they can provide visual abstractions and symbolism for categorized data. In this paper, we begin our study of visualization of image statistics by considering visual representations of power spectra, which are commonly used to visualize different categories of images. We show that they convey a limited amount of statistical information about image categories and their support for analytical tasks is ineffective. We then introduce several new visual representations, which convey different or more information about image statistics. We apply ANOVA to the image statistics to help select statistically more meaningful measurements in our design process. A task based user evaluation was carried out to compare the new visual representations with the conventional power spectra plots. Based on the results of the evaluation, we made further improvement of visualizations by introducing composite visual representations of image statistics.",
author = "Hui Fang and Gary Tam and Rita Borgo and Andrew Aubrey and Phil Grant and Paul Rosin and Christian Wallraven and Douglas Cunningham and David Marshall and Min Chen",
year = "2013",
month = "7",
language = "English",
volume = "19",
pages = "1228--1241",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "Institute of Electrical and Electronics Engineers",
number = "7",

}

Fang, H, Tam, G, Borgo, R, Aubrey, A, Grant, P, Rosin, P, Wallraven, C, Cunningham, D, Marshall, D & Chen, M 2013, 'Visualizing Natural Image Statistics', IEEE Transactions on Visualization and Computer Graphics, vol. 19, no. 7, pp. 1228-1241.

Visualizing Natural Image Statistics. / Fang, Hui; Tam, Gary; Borgo, Rita; Aubrey, Andrew; Grant, Phil; Rosin, Paul; Wallraven, Christian; Cunningham, Douglas; Marshall, David; Chen, Min.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 19, No. 7, 07.2013, p. 1228-1241.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visualizing Natural Image Statistics

AU - Fang, Hui

AU - Tam, Gary

AU - Borgo, Rita

AU - Aubrey, Andrew

AU - Grant, Phil

AU - Rosin, Paul

AU - Wallraven, Christian

AU - Cunningham, Douglas

AU - Marshall, David

AU - Chen, Min

PY - 2013/7

Y1 - 2013/7

N2 - Natural image statistics is an important area of research in cognitive sciences and computer vision. Visualization of statistical results can help identify clusters and anomalies as well as analyze deviation, distribution, and correlation. Furthermore, they can provide visual abstractions and symbolism for categorized data. In this paper, we begin our study of visualization of image statistics by considering visual representations of power spectra, which are commonly used to visualize different categories of images. We show that they convey a limited amount of statistical information about image categories and their support for analytical tasks is ineffective. We then introduce several new visual representations, which convey different or more information about image statistics. We apply ANOVA to the image statistics to help select statistically more meaningful measurements in our design process. A task based user evaluation was carried out to compare the new visual representations with the conventional power spectra plots. Based on the results of the evaluation, we made further improvement of visualizations by introducing composite visual representations of image statistics.

AB - Natural image statistics is an important area of research in cognitive sciences and computer vision. Visualization of statistical results can help identify clusters and anomalies as well as analyze deviation, distribution, and correlation. Furthermore, they can provide visual abstractions and symbolism for categorized data. In this paper, we begin our study of visualization of image statistics by considering visual representations of power spectra, which are commonly used to visualize different categories of images. We show that they convey a limited amount of statistical information about image categories and their support for analytical tasks is ineffective. We then introduce several new visual representations, which convey different or more information about image statistics. We apply ANOVA to the image statistics to help select statistically more meaningful measurements in our design process. A task based user evaluation was carried out to compare the new visual representations with the conventional power spectra plots. Based on the results of the evaluation, we made further improvement of visualizations by introducing composite visual representations of image statistics.

M3 - Article

VL - 19

SP - 1228

EP - 1241

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 7

ER -

Fang H, Tam G, Borgo R, Aubrey A, Grant P, Rosin P et al. Visualizing Natural Image Statistics. IEEE Transactions on Visualization and Computer Graphics. 2013 Jul;19(7):1228-1241.