Share Email Print
cover

Proceedings Paper

Object recognition in images via a factor graph model
Author(s): Yong He; Long Wang; Zhaolin Wu; Haisu Zhang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Object recognition in images suffered from huge search space and uncertain object profile. Recently, the Bag-of- Words methods are utilized to solve these problems, especially the 2-dimension CRF(Conditional Random Field) model. In this paper we suggest the method based on a general and flexible fact graph model, which can catch the long-range correlation in Bag-of-Words by constructing a network learning framework contrasted from lattice in CRF. Furthermore, we explore a parameter learning algorithm based on the gradient descent and Loopy Sum-Product algorithms for the factor graph model. Experimental results on Graz 02 dataset show that, the recognition performance of our method in precision and recall is better than a state-of-art method and the original CRF model, demonstrating the effectiveness of the proposed method.

Paper Details

Date Published: 10 April 2018
PDF: 10 pages
Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061517 (10 April 2018); doi: 10.1117/12.2303409
Show Author Affiliations
Yong He, National Univ. of Defense Technology (China)
Long Wang, National Univ. of Defense Technology (China)
Zhaolin Wu, National Univ. of Defense Technology (China)
Haisu Zhang, National Univ. of Defense Technology (China)


Published in SPIE Proceedings Vol. 10615:
Ninth International Conference on Graphic and Image Processing (ICGIP 2017)
Hui Yu; Junyu Dong, Editor(s)

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