Fingerprint%20Recognition

1
Fingerprint Recognition

• Professor Ostrovsky
• Andrew Ackerman

2
The Idea

• Including Region information in minutiae matching
• Reduces amount of matches need
• Can help better identify matches
• Also, idea of Fingerprint of Fingerprint
• Run X amount of binary tests on a fingerprint and
  return a vector of size X. This binary vector
  would identify the finger print
• Matching prints would have similar vectors
  (hamming distance)
• Tests could include information about minutiae as
  well as regions

3
Current State

• Rejected Idea of Topological Equivalence (for
  now).
• Code Written for Region Detection
• Code Written for Fingerprint Thinning
• Multi Fingerprints Received
• Though no Partial prints
• Spring Break Checklist
• Edge Enhancement code
• Binarization Code

4
Code So Far

• Thinning code
• Code to take in a binary object and thin it.
• However, still bugs in code as well as spurious
  minutiae (minutiae created in thinning process)

5
Region Detection Code

• Works in O(nm) small constant in front
• Colors in regions

6
To do Spring Quarter

• Test idea against database of fingerprints
• Idea Number of regions between matching minutiae
  will be similar
• Write up results of Test
• If time
• Explore idea of fingerprint of fingerprint
• See if idea works for partial prints

7
Assessment of Work

• In all I think a good deal of work was done
  towards the project. Its seems most of the time
  was spent coming up with a novel idea that could
  be tested. I feel this project can easily be
  wrapped up by the end of spring quarter with a
  paper on the findings when including regions into
  the minutiae matching model of fingerprint
  recognition.