Assessing the naturalness of scenes: An approach using statistics of local features

Jeremiah D. Deng; Russell S.A. Brinkworth; David C. O'Carroll

doi:10.1109/IVCNZ.2008.4762129

Assessing the naturalness of scenes: An approach using statistics of local features

Jeremiah D. Deng, Russell S.A. Brinkworth, David C. O'Carroll

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

What statistics makes an image of natural scene different from that of an urban or artificial environment? This has been an intriguing research topic in recent years. In this paper, in contrast to the more popular approach of using global frequency spectral features, we propose to employ a few statistics measures derived from local edge and fractal features. Feature selection methods are used to reveal the relevance of the defined features. The effectiveness of the proposed feature scheme is demonstrated using benchmark digital image data as well as high dynamic range image data.

Original language	English
Title of host publication	International Conference Image and Vision Computing New Zealand, IVCNZ
DOIs	https://doi.org/10.1109/IVCNZ.2008.4762129
Publication status	Published - Nov 2008
Externally published	Yes
Event	2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ - Christchurch, New Zealand Duration: 26 Nov 2008 → 28 Nov 2008

Publication series

Name	2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ

Conference

Conference	2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ
Country/Territory	New Zealand
City	Christchurch
Period	26/11/08 → 28/11/08

Keywords

Classification
Feature selection
Fractal
Natural scenes

Access to Document

10.1109/IVCNZ.2008.4762129Licence: In Copyright

Cite this

@inproceedings{c3c6b27112da422184708047d6d23f34,

title = "Assessing the naturalness of scenes: An approach using statistics of local features",

abstract = "What statistics makes an image of natural scene different from that of an urban or artificial environment? This has been an intriguing research topic in recent years. In this paper, in contrast to the more popular approach of using global frequency spectral features, we propose to employ a few statistics measures derived from local edge and fractal features. Feature selection methods are used to reveal the relevance of the defined features. The effectiveness of the proposed feature scheme is demonstrated using benchmark digital image data as well as high dynamic range image data.",

keywords = "Classification, Feature selection, Fractal, Natural scenes",

author = "Deng, {Jeremiah D.} and Brinkworth, {Russell S.A.} and O'Carroll, {David C.}",

year = "2008",

month = nov,

doi = "10.1109/IVCNZ.2008.4762129",

language = "English",

isbn = "9781424425822",

series = "2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ",

booktitle = "International Conference Image and Vision Computing New Zealand, IVCNZ",

note = "2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ ; Conference date: 26-11-2008 Through 28-11-2008",

}

Deng, JD, Brinkworth, RSA & O'Carroll, DC 2008, Assessing the naturalness of scenes: An approach using statistics of local features. in International Conference Image and Vision Computing New Zealand, IVCNZ., 4762129, 2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ, 2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ, Christchurch, New Zealand, 26/11/08. https://doi.org/10.1109/IVCNZ.2008.4762129

Assessing the naturalness of scenes : An approach using statistics of local features. / Deng, Jeremiah D.; Brinkworth, Russell S.A.; O'Carroll, David C.

International Conference Image and Vision Computing New Zealand, IVCNZ. 2008. 4762129 (2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Assessing the naturalness of scenes

T2 - 2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ

AU - Deng, Jeremiah D.

AU - Brinkworth, Russell S.A.

AU - O'Carroll, David C.

PY - 2008/11

Y1 - 2008/11

N2 - What statistics makes an image of natural scene different from that of an urban or artificial environment? This has been an intriguing research topic in recent years. In this paper, in contrast to the more popular approach of using global frequency spectral features, we propose to employ a few statistics measures derived from local edge and fractal features. Feature selection methods are used to reveal the relevance of the defined features. The effectiveness of the proposed feature scheme is demonstrated using benchmark digital image data as well as high dynamic range image data.

AB - What statistics makes an image of natural scene different from that of an urban or artificial environment? This has been an intriguing research topic in recent years. In this paper, in contrast to the more popular approach of using global frequency spectral features, we propose to employ a few statistics measures derived from local edge and fractal features. Feature selection methods are used to reveal the relevance of the defined features. The effectiveness of the proposed feature scheme is demonstrated using benchmark digital image data as well as high dynamic range image data.

KW - Classification

KW - Feature selection

KW - Fractal

KW - Natural scenes

UR - http://www.scopus.com/inward/record.url?scp=63049092482&partnerID=8YFLogxK

U2 - 10.1109/IVCNZ.2008.4762129

DO - 10.1109/IVCNZ.2008.4762129

M3 - Conference contribution

AN - SCOPUS:63049092482

SN - 9781424425822

T3 - 2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ

BT - International Conference Image and Vision Computing New Zealand, IVCNZ

Y2 - 26 November 2008 through 28 November 2008

ER -

Assessing the naturalness of scenes: An approach using statistics of local features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this