Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK)

Qinhuangdao,China,7.9-7.13,2010

ISBN: 978-1-935068-15-0 Scientific Research Publishing, USA

E-Book 840pp Pub. Date: July 2010

Category: Computer Science & Communications

Price: $120

Title: An Improved Image Edge Match Algorithm Based on Modified EMR
Source: Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK) (pp 85-89)
Author(s): Yansong Wang, School of Optoelectronic Engineering, Beijing Institute of Technology, Beijing
Weiqi Jin, School of Optoelectronic Engineering, Beijing Institute of Technology, Beijing
Chun’e Zhang, School of Computer and Information Technology, Beijing Jiaotong University, Beijing
Abstract: Aiming for a good image matching resistant to interference, this paper proposes a modified EMR method to improve image edge match. For the Edge Matching Rate (EMR) between the target image and the template, generalized area is defined and used as the calculation basis in our proposed approach. It also defines similarity of local occlusion and of local dither to measure interference degree. Not only edge points are considered but also non-edge points, occlusions and dithers. After the same image edge extraction and coarse registration, the experiments use traditional EMR and proposed EMR separately to get fine registration. The experiments show that our method achieves more stable registration and better precision.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top