Dissertation: Image Registration Algorithm: a Comparison

Image registration is an operation of image processing system. There are many applications on image registration specially medical image and remote sensing. My masters dissertation on image registration algorithm. The summary of my dissertation are given below:

Image registration is the fundamental task in image processing system. It has a lot of applications especially medical image and remote sensing. Image registration is the process of aligning two or more images into one coordinate system that taken at different times, from different sensors, or from different viewpoints. Image registration methods are classified according on different measurements (intensity-based vs. feature-based, similarity, transformation model) of images and four basic steps (feature detection, feature matching, transformation model design, and image transformation and re-sampling). The main purpose of this paper is to provide a comprehensive review and criticize of the existing literature available on image registration methods. I believe that it will be a useful document for researchers who will work on image registration regardless for specific applications or implement new image registration method.

I reviewed more than 80 papers based on image registration, surface registration, image reconstruction, 3D modeling etc. I was also implemented three algorithms based on image feature using MATLAB, C/C++. Finally I proposed a new feature based image registration technology that was given better results.)