bullet Sensors & Transducers Journal

    (ISSN: 2306-8515, e-ISSN 1726-5479)


   About this Journal

   Information for Authors

   Editorial Board

   Editorial Calendar

   Current Issue

   Browse Journal

S&T journal's cover

Submit Press Release

Submit White Paper

25 Top Downloaded Articles (2007-2012)


Contact Us





Vol. 208, Issue 1, January 2017, pp. 39-43




Non-rigid Point Matching using Topology Preserving Constraints
for Medical Computer Vision

Jong-Ha Lee

Keimyung University, School of Medicine, South Korea
Tel.: (82)-53-580-3736, fax: (82)-53-580-3746

E-mail: segeberg@kmu.ac.kr


Received: 22 November 2016 /Accepted: 30 December 2016 /Published: 31 January 2017

Digital Sensors and Sensor Sysstems


Abstract: This work presents a novel algorithm of finding correspondence using a relaxation labeling. For the variance experiments, the variance of all algorithms except the proposed algorithm is large. The largest variance of the proposed algorithm is +0.01 in the 0.08 deformation test of a character. Overall, the proposed algorithm outperforms compared to the rest of algorithms. Except the proposed algorithm, matching with neighborhood algorithm shows the best performance except an outlier to data ratio in a character test. The proposed algorithm shows the best performance as well as an outlier to data ratio in a character test.


Keywords: Non-rigid point matching, Image registration, Correspondence problem.


Acrobat reader logo Click <here> or title of paper to download the full pages article in pdf format



This work is licensed under a Creative Commons 4.0 International License


 Creative Commons License





1999 - 2017 Copyright , International Frequency Sensor Association (IFSA) Publishing, S.L. All Rights Reserved.

Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn