Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/50956
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Assessing the naturalness of scenes: An approach using statistics of local features |
Author: | Deng, J. Brinkworth, R. O'Carroll, D. |
Citation: | 2008 23rd International Conference Image and Vision Computing New Zealand (IVCNZ) / Irie, K. (ed.): pp. 1-6 |
Publisher: | IEEE |
Publisher Place: | USA |
Issue Date: | 2008 |
ISBN: | 9781424437801 |
Conference Name: | International Conference on Image and Vision Computing New Zealand (23rd : 2008 : Christchurch, NZ) |
Statement of Responsibility: | Jeremiah D. Deng, Russell SA. Brinkworth, David C. O'Carroll |
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. © 2008 IEEE. |
Keywords: | natural scenes classification fractal feature selection |
Description: | © Copyright 2009 IEEE – All Rights Reserved |
DOI: | 10.1109/IVCNZ.2008.4762129 |
Description (link): | http://www.lvl.co.nz/IVCNZ2008/ |
Published version: | http://dx.doi.org/10.1109/ivcnz.2008.4762129 |
Appears in Collections: | Aurora harvest Molecular and Biomedical Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.