Integrated image representation based natural scene classification

Guanghua Gu

doi:10.1016/j.eswa.2011.02.174

Return

Integrated image representation based natural scene classification

2011-09-01

PRE

DOI：10.1016/j.eswa.2011.02.174

Original

Original request for help

Save

Abstract

En 中文

Natural scene classification (NSC) is a challenging pattern classification problem. As one of state-of-the-art techniques, the bag-of-feature (BOF) model has received extensive considerations in characterizing the image. To boost the flexibility during visterm construction in BOF model, an integrated scheme for image representation is proposed by adaptive analysis on the local visual complexity of image itself. First, the flatness of each scene category is determined by the total flatness of all images belonging to this category. Then the new integrated image representation of the scene category is built by weighting the two representations (based on a pixels gray value descriptor and a dense SIFT descriptor) through the normalized coefficients computed by the flatness of the category. Finally, a hierarchical generative model is exploited to learn natural scene categories. Experimental results demonstrate that the satisfactory classification accuracy achieves about 83.67% on a large set of 15 categories of complex scenes. Crown Copyright (C) 2011 Published by Elsevier Ltd. All rights reserved.

Keywords:

Scene analysis

Image classification

Modeling

Image flatness

Integrated image representation

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.