Volume 8, Issue 1
A New Medical Image Registration

Meisen Pan, Fen Zhang & Jianjun Jiang

Journal of Fiber Bioengineering & Informatics, 8 (2015), pp. 151-159.

Published online: 2015-08

Preview Full PDF 594 2213
Export citation
  • Abstract

This proposed method calculates the centroids of two registering images by applying the moments for acquiring the original displacement parameters, and then uses modified K-means clustering to classify the image coordinates. Before clustering, the medical image coordinates is centralized, the two-row coordinate matrix is created to construct the 2-D sample set to be partitioned into two classes, the slope of a straight line fitted to the two classes is computed, and the rotation angle is computed by solving the arc tangent of the slope. The edges are detected by the edge convolution kernel and the binary images covering the characteristic points are extracted. Experimental results from aligning experiments reveal that, this approach has lower computation costs and a higher registration precision.

  • Keywords

Centroids Image Registration K-means Clustering Iterative Closest Points

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-8-151, author = {}, title = {A New Medical Image Registration}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2015}, volume = {8}, number = {1}, pages = {151--159}, abstract = {This proposed method calculates the centroids of two registering images by applying the moments for acquiring the original displacement parameters, and then uses modified K-means clustering to classify the image coordinates. Before clustering, the medical image coordinates is centralized, the two-row coordinate matrix is created to construct the 2-D sample set to be partitioned into two classes, the slope of a straight line fitted to the two classes is computed, and the rotation angle is computed by solving the arc tangent of the slope. The edges are detected by the edge convolution kernel and the binary images covering the characteristic points are extracted. Experimental results from aligning experiments reveal that, this approach has lower computation costs and a higher registration precision.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbi03201515}, url = {http://global-sci.org/intro/article_detail/jfbi/4695.html} }
TY - JOUR T1 - A New Medical Image Registration JO - Journal of Fiber Bioengineering and Informatics VL - 1 SP - 151 EP - 159 PY - 2015 DA - 2015/08 SN - 8 DO - http://doi.org/10.3993/jfbi03201515 UR - https://global-sci.org/intro/article_detail/jfbi/4695.html KW - Centroids KW - Image Registration KW - K-means Clustering KW - Iterative Closest Points AB - This proposed method calculates the centroids of two registering images by applying the moments for acquiring the original displacement parameters, and then uses modified K-means clustering to classify the image coordinates. Before clustering, the medical image coordinates is centralized, the two-row coordinate matrix is created to construct the 2-D sample set to be partitioned into two classes, the slope of a straight line fitted to the two classes is computed, and the rotation angle is computed by solving the arc tangent of the slope. The edges are detected by the edge convolution kernel and the binary images covering the characteristic points are extracted. Experimental results from aligning experiments reveal that, this approach has lower computation costs and a higher registration precision.
Meisen Pan, Fen Zhang & Jianjun Jiang. (2019). A New Medical Image Registration. Journal of Fiber Bioengineering and Informatics. 8 (1). 151-159. doi:10.3993/jfbi03201515
Copy to clipboard
The citation has been copied to your clipboard