The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 32-766
Full Name: Yan Li
Position: Doctor (Researcher)
Age: ON
Sex: Female
Address: School of Information Science and Engineering, Central South University, Changsha
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: liyanly@mail.csu.edu.cn
Other E-mails: liyanly234@sohu.com
Title of the Paper: Multi-modal Registration via High Scale Images
Authors as they appear in the Paper: Li Yan; Li Gang
Email addresses of all the authors: liyanly@mail.csu.edu.cn, csulg@163.com
Number of paper pages: 10
Abstract: A new method to get features for rigid registration is presented in this paper. Attribute scale spaces are constructed by attribute operators. The attribute thresholds and gray thresholds are obtained by the level set histogram automatically. The contour can be extracted in high scale image. The highest scale images are very similar. This method turns the multi-model registration into the mono-model. Some important properties of the method are proposed and proved. The simple similarity measurement and the global searching optimum algorithm is applied to match based on edge features extracted by our method. The new method has strong anti-noise and the edge of object keeps good. The experiment results show that using these features extracted by our method help to improve the aligning precision and the computing time.
Keywords: Edge extraction, Connected operators, Mathematics morphology, MR-CT, Similarity measurement, Multimodal registration
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 220.169.30.220
