What is it about?
Point set registration is a fundamental problem in many computer vision, pattern recognition, and medical image analysis applications. Its goal is to find a spatial transformation that aligns two point sets. This paper proposed a robust registration method by integrating relative structure information into the coordinates of points. Extensive experiments on both synthesized and real data are carried out to confirm the robustness of our method.
Featured Image
Why is it important?
Our experiments show that the high-dimensional representation and the relative distances used in local features are able to significantly improve the performance of registration. Thus, the registration method by high-dimensional representation is more effective than previous algorithms.
Perspectives
Writing this article was a wonderful growing experience as I get so much out of it and cooperate with my partners. It also lead to researchers in the same field contacting me and ultimately to a greater involvement in non-rigid point registration. However, most importantly, I hope the article can help you in related fields.
Huimin Huang
Read the Original
This page is a summary of: Non-Rigid Point Set Registration by High-dimensional Representation , IET Image Processing, April 2018, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-ipr.2017.1363.
You can read the full text:
Contributors
The following have contributed to this page
