Abstract

Because of the rapid progress in image acquisition technologies, 3D images become increasingly popular in magnetic resonance imaging (MRI) and other applications. 3D image registration attracts more and more interesting researches. However, most existing image registration methods are based on 2D image processing. But, the structure of a typical 3D image is substantially more complicated than that of a typical 2D image. So, 3D image registration could be more challenging. Moreover, it is also a key challenge to choose good features because different applications should use different features accordingly. In this paper, we develop a 3D rigid image registration method which registers the 3D images using direct image intensity without any feature. It is shown that this method works well in various cases and greatly reduces the processed data size which makes it attractive for 3D image applications since 3D images often have a big data sizes and the reduction of size could significantly benefit follow-up processing for efficient computation.

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