The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 28-610
Full Name: ZHENGMAO YE
Position: Assistant Professor
Age: ON
Sex: Male
Address: 426 Pinchback Hall, Southern University, Baton Rouge, LA 70813
Country: UNITED STATES
Tel: 225-771-4172
Tel prefix:
Fax:
E-mail address: zhengmaoye@engr.subr.edu
Other E-mails: yzm001@hotmail.com
Title of the Paper: Evaluating Retina Image Fusion Based on Quantitative Approaches
Authors as they appear in the Paper: ZHENGMAO YE, HUA CAO, SITHARAMA IYENGAR, HABIB MOHAMADIAN
Email addresses of all the authors: zhengmaoye@engr.subr.edu
Number of paper pages: 10
Abstract: Image registration and fusion are conducted using an automated approach, which applies the automatic adaptation from frame to frame with the threshold parameters. Rather than qualitative approach, quantitative measures have been proposed to evaluate outcomes of retina image fusion. Concepts of the discrete entropy, discrete energy, relative entropy, mutual information, uncertainty coefficient and information redundancy have been introduced. Both the Canny edge detector and control point identification are employed to extract retinal vasculature using the adaptive exploratory algorithms. The shape similarity criteria have been selected for control point matching. The Mutual-Pixel-Count maximization based optimal procedure has also been developed to adjust the control points at the sub-pixel level. Then the global maxima equivalent result has been derived by calculating Mutual-Pixel-Count local maxima. For two cases of image fusion practices, the testing results are !
evaluated on a basis of information theories where the satisfactory outcomes have been made.
Keywords: Image Fusion, Image Registration, Histogram, Discrete Energy, Discrete Entropy, Relative Entropy, Mutual Information, Uncertainty Coefficient, Information Redundancy
EXTENSION of the file: .pdf
Special (Invited) Session: Quantitative Approach on Image Fusion Evaluation
Organizer of the Session: # 603-176
How Did you learn about congress:
IP ADDRESS: 192.207.173.150
