Document info
Back


In: Computing and Informatics, vol. 27, no. 5


SVM Based Indoor/Mixed/Outdoor Classification for Digital Photo Annotation in a Ubiquitous Computing Environment

Ch. H. Song - S. J. Yoo - Ch. S. Won - H. G. Kim

ISSN 1335-9150 (print)
ISSN 2585-8807 (online)

Year, pages: 2008, 757-767

Published: 0000-00-00

Abstract:

This paper extends our previous framework for digital photo annotation by adding noble approach of indoor/mixed/outdoor image classification. We propose the best feature vectors for a support vector machine based indoor/mixed/ outdoor image classification. While previous research classifies photographs into indoor and outdoor, this study extends into three types, including indoor, mixed, and outdoor classes. This three-class method improves the performance of outdoor classification. This classification scheme showed 5--10% higher performance than previous research. This method is one of the components for digital image annotation. A digital camera or an annotation server connected to a ubiquitous computing network can automatically annotate captured photos using the proposed method.

How to cite:

ISO 690:
H. Song, C., J. Yoo, S., S. Won, C., G. Kim, H. 2008. SVM Based Indoor/Mixed/Outdoor Classification for Digital Photo Annotation in a Ubiquitous Computing Environment. In Computing and Informatics, vol. 27, no.5, pp. 757-767. 1335-9150.

APA:
H. Song, C., J. Yoo, S., S. Won, C., G. Kim, H. (2008). SVM Based Indoor/Mixed/Outdoor Classification for Digital Photo Annotation in a Ubiquitous Computing Environment. Computing and Informatics, 27(5), 757-767. 1335-9150.

Keywords: Image classification, support vector machine, low-level feature extraction