Share Email Print

Proceedings Paper

Image classification by multi-instance learning with base sample selection
Author(s): Qiang Pan; Gang Zhang; Xiao-Yan Zhang; Zhi-Ming Huang; Jie Xiong
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose a similarity-based learning style algorithm by regarding each image as a multi-instance (MI) sample for image classification. An image featured as vectorial representation interesting regions is transferred to a MI sample. Then a similarity like matrix is constructed using MI kernel between given images and some carefully selected base images, as the new representation of given images. Three selection strategies are proposed to build the base images set to find an optimal solution. A Weka implementation decision tree is used as the main learner in this paper. Experiments on image data repository ALOI and Corel Image 2000 show the effectiveness of the proposed algorithm compared to some previous based line methods.

Paper Details

Date Published: 15 November 2011
PDF: 7 pages
Proc. SPIE 8335, 2012 International Workshop on Image Processing and Optical Engineering, 833519 (15 November 2011); doi: 10.1117/12.917409
Show Author Affiliations
Qiang Pan, Zhuhai City Polytechnic College (China)
Gang Zhang, GuangDong Univ. of Technology (China)
Xiao-Yan Zhang, GuangDong Univ. of Technology (China)
Zhi-Ming Huang, GuangDong Univ. of Technology (China)
Jie Xiong, Ximalu Primary School (China)

Published in SPIE Proceedings Vol. 8335:
2012 International Workshop on Image Processing and Optical Engineering
Hai Guo; Qun Ding, Editor(s)

© SPIE. Terms of Use
Back to Top