Title | ||
---|---|---|
Natural Versus Artificial Scene Classification by Ordering Discrete Fourier Power Spectra |
Abstract | ||
---|---|---|
Holistic representations of natural scenes is an effective and powerful source of information for semantic classification and analysis of arbitrary images. Recently, the frequency domain has been successfully exploited to holistically encode the content of natural scenes in order to obtain a robust representation for scene classification. In this paper, we present a new approach to naturalness classification of scenes using frequency domain. The proposed method is based on the ordering of the Discrete Fourier Power Spectra. Features extracted from this ordering are shown sufficient to build a robust holistic representation for Natural vs. Artificial scene classification. Experiments show that the proposed frequency domain method matches the accuracy of other state-of-the-art solutions. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89689-0_18 | SSPR/SPR |
Keywords | Field | DocType |
proposed frequency domain method,natural scene,frequency domain,natural versus artificial scene,scene classification,robust representation,robust holistic representation,semantic classification,ordering discrete fourier power,naturalness classification,holistic representation | Frequency domain,ENCODE,Computer vision,Pattern recognition,Computer science,Naturalness,Scene statistics,Spectral density,Artificial intelligence,Discrete Fourier transform,Visual Word | Conference |
Volume | ISSN | Citations |
5342 | 0302-9743 | 4 |
PageRank | References | Authors |
0.46 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Giovanni Maria Farinella | 1 | 412 | 57.13 |
Sebastiano Battiato | 2 | 659 | 78.73 |
G. Gallo | 3 | 223 | 20.06 |
Roberto Cipolla | 4 | 9413 | 827.88 |