Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/38750
Title: SIFT approach to blood vessel matching
Authors: Tan, Ke Bin.
Keywords: DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences
Issue Date: 2010
Abstract: This report describes the author’s experience and progression in his final year project, titled, “SIFT Approach to Blood Vessel Matching”. During the project, the author learnt to apply the Scale-Invariant Feature Transform (SIFT) method to match pictures of blood vessels. The purpose of this project is to research on the SIFT method and applying it to the aspect of iris recognition and matching of blood vessels. The main requirement is to identify the key features of the blood vessels. From the start, the SIFT method is already been utilized in many applications. Therefore, by gathering information online, several versions of the implementation of the SIFT method can be found. Then, through intensive experimentation, the most efficient and suitable implementation is selected. The report covers mainly, the usage of the selected SIFT implementation to match blood vessels along with the image processing that is performed on the pictures to achieve the most desirable matching results. Experiment results show that the SIFT method, indeed, is not just applicable but efficient in detecting the key features of blood vessels and matching them. Finally, recommendations for future development are also elaborated by the author.
URI: http://hdl.handle.net/10356/38750
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
SCE09-0193.pdf
  Restricted Access
1.34 MBAdobe PDFView/Open

Page view(s)

232
checked on Sep 22, 2020

Download(s)

9
checked on Sep 22, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.