Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

IMAGE REGISTRATION USING EDGE BASED MUTUAL INFORMATION

 

TITLE IMAGE REGISTRATION USING EDGE BASED MUTUAL INFORMATION
AUTHOR SUWISA KOPHON
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR SUKANYA PHONGSUPHAP
CO-ADVISOR SUPATANA AUETHAVEKIAT
 
ABSTRACT
Image registration is applied prior to image fusion. The quality of fusion depends on how accurate the two images are registered. Mutual information has been widely adopted for intermodal registration and offers a good registered result in medical image registration. However, mutual information is not effective when it is used as the criterion for registering visible light images to infrared images, because the information of the intensity in infrared images is not directly related to the one in visible light images. However, it is noticed that some boundaries of objects are shown in both infrared and visible light images. In this thesis, the registration of visible light images to infrared images by maximizing the mutual information of the area near the edges of objects was proposed. The edge is manually selected. The objective of the registration is to find a 2D rigid transform of the visible light image for the highest mutual information when the edge area shared by the two images is not too small. The modified three-step search was used and can be reapplied when necessary. The proposed method was evaluated. It performed better than the registration by maximizing the mutual information of the entire image when there were a number of different intensities in an image. A high number of intensity bins in the image led to difficulty in establishing the intensity relationship between image modes. The evaluation also indicated that the edges used for the mutual information calculation needed not be highly accurate leading to the possibility of an automatic edge extraction algorithm.
KEYWORD IMAGE REGISTRATION, MUTUAL INFORMATION, INFRARED IMAGE, EDGE

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333