Abstract

Fusion of the medical images and registering them will improve the diagnosis and treatment for brain pathology. Image registration plays a major role because multimodal images intensity levels are to be aligned based on relationship between the images. Image registration is proposed where T1 image is a target image where T2 is registering image. Optical flow with SIFT is applied to register T2 image. The registered T2 image is fused with T1 image by applying curvelet transformation and averaging method. Entropy and Mutual Information (MI) parameter is used to evaluate the system performance. The results of the system give better entropy and MI value.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call