Object recognition in images via a factor graph model

Yong He; Long Wang; Zhaolin Wu; Haisu Zhang

doi:10.1117/12.2303409

10 April 2018 Object recognition in images via a factor graph model

Yong He, Long Wang, Zhaolin Wu, Haisu Zhang

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061517 (2018) https://doi.org/10.1117/12.2303409
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

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.

Citation Download Citation

Yong He, Long Wang, Zhaolin Wu, and Haisu Zhang "Object recognition in images via a factor graph model", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061517 (10 April 2018); https://doi.org/10.1117/12.2303409

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available