Abstract
dc:description.abstract<p>The purpose of my research is to provide a method to automatically classify fingerprints into three subgroups: whorl, loop and arch, which can help medical scientists to study the relationship between fingerprint patterns and medical disorders. In the research, two different kinds of approaches were developed. The first one is performing pattern recognition in the frequency domain, which uses the feature of Fourier spectrum. That is, prominent peaks in the spectrum give the principal direction of fingerprint patterns. Using the above feature, we can obtain the principal direction of every subregion, after which the pattern of the whole image can be determined. The other approach is in space domain, a procedure which uses chain code to compute the changing direction of every ridge. The frequency domain approach allows one to classify whorl faster and is less sensitive to the quality of fingerprint image, but it does not easily allow for the classification of arch and loop when triradii areas are too small. The space domain approach can classify the above three patterns more accurately, but is much slower and more sensitive to fingerprint quality, especially the quality of triradii areas.</p>
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Biomedical Engineering - (M.S.)
- Discipline thesis:degree_discipline
- Biomedical Engineering Committee
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- You, Feng
- Contributors dc:contributor
-
- Yun Q. Shi
- David S. Kristol
- Timothy Nam Chang
Subjects
dc:subject × 4Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.njit.edu/theses/2212