A robust and high-performance shape registration technique using characteristic functions

Cui, Zheng, Mahmoodi, Sasan and Bennett, Michael (2019) A robust and high-performance shape registration technique using characteristic functions. In 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS). IEEE. 6 pp . (doi:10.1109/IPAS.2018.8708883).

Record type: Conference or Workshop Item (Paper)

Abstract

We propose an innovative similarity registration method for volumetric shapes in this paper. This characteristic function-based method is intended to tackle the registration problem for the shapes containing sub-shapes in the presence of noise, and to strike a desirable balance between alignment performance and efficiency. In order to obtain the optimal parameters for scaling, rotation and translation in a reasonable time, radial moments and spherical coordinate system-based cross-correlation are exploited here. Moreover, an iterative method and principal component analysis are also employed to improve robustness of our algorithm. The shapes containing sub-shapes and the lung shapes from a CT dataset are employed in the experiments for validation. Compared with state-of-the-art algorithms, the characteristic function-based method manages to achieve excellent robustness at very low signal-to-noise ratio as well as superior registration speed, accuracy and stability in the medical shape data processing.

Text

A Robust and High-performance Shape Registration Technique Using Characteristic Functions - Accepted Manuscript

Restricted to Registered users only

Download (769kB)

Request a copy