Skip to content Skip to navigation

Connexions

You are here: Home » Content » You Are Cleared for Access...

Navigation

Content Actions

  • Download module PDF
  • Add to ...
    Add the module to:
    • My Favorites
    • A lens
    • An external social bookmarking service
    • My Favorites (What is 'My Favorites'?)
      'My Favorites' is a special kind of lens which you can use to bookmark modules and collections directly in Connexions. 'My Favorites' can only be seen by you, and collections saved in 'My Favorites' can remember the last module you were on. You need a Connexions account to use 'My Favorites'.
    • A lens (What is a lens?)

      Definition of a lens

      Lenses

      A lens is a custom view of Connexions content. You can think of it as a fancy kind of list that will let you see Connexions through the eyes of organizations and people you trust.

      What is in a lens?

      Lens makers point to Connexions materials (modules and collections), creating a guide that includes their own comments and descriptive tags about the content.

      Who can create a lens?

      Any individual Connexions member, a community, or a respected organization.

    • External bookmarks
  • E-mail the authors

Lenses

What is a lens?

Definition of a lens

Lenses

A lens is a custom view of Connexions content. You can think of it as a fancy kind of list that will let you see Connexions through the eyes of organizations and people you trust.

What is in a lens?

Lens makers point to Connexions materials (modules and collections), creating a guide that includes their own comments and descriptive tags about the content.

Who can create a lens?

Any individual Connexions member, a community, or a respected organization.

This content is ...

Affiliated with (What does "Affiliated with" mean?)

This content is either by members of the organizations listed or about topics related to the organizations listed. Click each link to see a list of all content affiliated with the organization.
  • Rice University ELEC 301 Projects

    This module is included inLens: Rice University ELEC 301 Project Lens
    By: Rice University ELEC 301As a part of collection:"ELEC 301 Projects Fall 2004"

    Click the "Rice University ELEC 301 Projects" link to see all content affiliated with them.

Recently Viewed

This feature requires Javascript to be enabled.

You Are Cleared for Access...

Module by: Scott Harrison, Jeremy Beasley, Brent Carroll, Richard Baraniuk

Summary: This module refers to all of our results, problems we had, and conclusions we have made. Also included are acknowledgements.

Scanning...

From all the methods we used to identify and match images, we obtained the following results:

Figure 1: These are the correlations between various reference images (A1-D1) and our scanned images.
Results of Various Matching Processes
Results of Various Matching Processes (results.JPG)

Note:

that the Minutiae-Based Approach was not considered in the results because of time issues and complexity.
All of the results seem pretty similar except for the calculation times and the "False Positive" correlation. That is, depending on the image and method, the number of images that reported a "match" in the case of a non-match decreased between the two equivalent domain methods, and the Rotation+FFT Method. Image D1 also seems to be a fluke, since it reported perfect correlation and false positve matching.

Error. You are not in the database.

Fingerprint matching is not always a straightforward process with definite steps. Many different problems can arise to hamper the process such as, lack of proper scanning equipment, slow computers, and sheer size of a database. The main problem that arose, however, was the implementation of the Minutiae-based Method. This method is more along the lines of what security agencies like the FBI use, and their technology and algorithms are much more sophisticated than the simple tools we have to use. The complexity of implementing such a process was beyond our programming capabilities in Matlab and beyond our time frame given to work. Given more time and resources, our group might have been able to implement such a method.

Match Found. You May Proceed...

As a result of our research we have come to the following conclusions:

  • Image quality plays a huge role in match probability
  • Frequency domain analysis is generally faster for image recognition processes
  • The addition of the rotational matrix improved match probability and decreased error since it sweeps over various orientations of image
Some suggestions for further research include better classification algorithms, higher resolution scanners, and better unique feature data extraction. The most "optimal" method of matching images would be a combination of the Minutiae-based approach and the Rotation+FFT Method. This, however, can only be had with better technology and time. The normal tradeoff in the matching process is Time to Complete vs. Efficiency/Precision in Matching. When we consider this fact, the optimal case to use in signal processing matching is the Rotation + FFT Method .

Acknowledgements

We would like to thank and acknowledge the following people and sources:

  • Rice Univ. Dept. of Electrical Engineering: Dr. Richard Baraniuk, William Chan, Chris Rozell
  • Previous Elec 301 Groups (2002 - Fresh Prints of Rice, 2000 - Fingerprint Matching)
  • Cain Project: Dr. Linda Driskil
  • National Institute of Standards and Technology
  • Pattern Recognition and Image Processing Lab Department of Computer Science And Engineering Michigan State University: Umut Uludag and Anil Jain

Group Fingerprint: Scott Harrison, Brent Carroll, and Jeremy Beasley

Comments, questions, feedback, criticisms?

Send feedback