GSoC 2022 Project Idea 16.4: Add mutual information for non-rigid registration (175 h)

Currently mutual information (MI) similarity metric is available only for affine registration and not nonrigid registration. The student will need to implement, compare and test MI for nonrigid registration. The existing implementation provides examples for SSD and Expectation Maximization metrics. The MI method is expected to work slightly better than our existing EM method for multimodal images. This project will focus on multimodal images. If time is permitted the student can also investigate a tensor based metric for registration.

Time: Half time

Difficulty: Beginner

Skills required: Familiarity with registration algorithms, Python, Cython or C/C++.

Mentors: Bramsh Qamar Chandio @bramsh, Shreyas Fadnavis @ShreyasFadnavis and Jong Sung Park @pjsjongsung

Tech keywords: Python, Cython, C/C++

Hello, I am Adit Mehta currently doing post graduation in Software Development. I have ample experience of Python and C++. I have been using it for more than 4 years. I have strong interest in data structure and algorithms and Digital image processing. I would like to contribute to this project your guidance for working on this would be very much helpful.