Share Email Print

Proceedings Paper

A comparison of SVMs with MLC algorithms on texture features
Author(s): Shuying Jin; Deren Li; Jianya Gong
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A study is presented concerning the performance of support vector machines (SVMs) and maximum likelihood classification (MLC) algorithms on texture features. A novel multivariate modeling method--partial least square regression (PLSR) is applied to obtain novel texture features from texture spectrum (TS). Three texture features, together with PLSR-combined TS features, are used in Brodatz texture classification tests. The experiments show: 1) SVM has higher classification precisions and better generalization abilities than MLC no matter what texture features used and more suits to small training set size (TSS) situations; 2) the new proposed feature combination method (PLSR) can greatly improve TS features discrimination ability for MLC, but not for SVM.

Paper Details

Date Published: 3 November 2005
PDF: 6 pages
Proc. SPIE 6044, MIPPR 2005: Image Analysis Techniques, 60442B (3 November 2005); doi: 10.1117/12.655313
Show Author Affiliations
Shuying Jin, Wuhan Univ. (China)
Deren Li, Wuhan Univ. (China)
Jianya Gong, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 6044:
MIPPR 2005: Image Analysis Techniques
Deren Li; Hongchao Ma, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?