Welcome to the InfoSci Platform
Reference Hub2
Sparse Based Image Classification With Bag-of-Visual-Words Representations

Sparse Based Image Classification With Bag-of-Visual-Words Representations

Yuanyuan Zuo, Bo Zhang
Copyright: © 2011 |Volume: 3 |Issue: 1 |Pages: 15
ISSN: 1942-9045|EISSN: 1942-9037|EISBN13: 9781613509173|DOI: 10.4018/jssci.2011010101
Cite Article Cite Article

MLA

Zuo, Yuanyuan, and Bo Zhang. "Sparse Based Image Classification With Bag-of-Visual-Words Representations." IJSSCI vol.3, no.1 2011: pp.1-15. http://doi.org/10.4018/jssci.2011010101

APA

Zuo, Y. & Zhang, B. (2011). Sparse Based Image Classification With Bag-of-Visual-Words Representations. International Journal of Software Science and Computational Intelligence (IJSSCI), 3(1), 1-15. http://doi.org/10.4018/jssci.2011010101

Chicago

Zuo, Yuanyuan, and Bo Zhang. "Sparse Based Image Classification With Bag-of-Visual-Words Representations," International Journal of Software Science and Computational Intelligence (IJSSCI) 3, no.1: 1-15. http://doi.org/10.4018/jssci.2011010101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The sparse representation based classification algorithm has been used to solve the problem of human face recognition, but the image database is restricted to human frontal faces with only slight illumination and expression changes. This paper applies the sparse representation based algorithm to the problem of generic image classification, with a certain degree of intra-class variations and background clutter. Experiments are conducted with the sparse representation based algorithm and Support Vector Machine (SVM) classifiers on 25 object categories selected from the Caltech101 dataset. Experimental results show that without the time-consuming parameter optimization, the sparse representation based algorithm achieves comparable performance with SVM. The experiments also demonstrate that the algorithm is robust to a certain degree of background clutter and intra-class variations with the bag-of-visual-words representations. The sparse representation based algorithm can also be applied to generic image classification task when the appropriate image feature is used.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.