Date of Graduation


Document Type


Degree Type



Statler College of Engineering and Mineral Resources


Lane Department of Computer Science and Electrical Engineering

Committee Chair

Arun A. Ross.


Most fingerprint authentication systems utilize minutiae information to compare fingerprint images. During enrollment, the minutiae template of a user's fingerprint is extracted and stored in the database. In this work, we concern ourselves with the amount of fingerprint information that can be elicited from the minutiae template of a user's fingerprint. We demonstrate that minutiae information can reveal substantial details such as the orientation field and class of the (unseen) parent fingerprint that can potentially be used to reconstruct the original fingerprint image.;Given a minutiae template, the proposed method first estimates the orientation map of the parent fingerprint by constructing minutiae triplets. The estimated orientation map is observed to be remarkably consistent with the underlying ridge flow of the unseen parent fingerprint. We also discuss a fingerprint classification technique that utilizes only the minutiae information to determine the class of the fingerprint (Arch, Left loop, Right loop and Whorl). The proposed classifier utilizes various properties of the minutiae distribution such as angular histograms, density, relationship between minutiae pairs, etc. A classification accuracy of 82% is obtained on a subset of the NIST-4 database. This indicates that the seemingly random minutiae distribution of a fingerprint can reveal important class information. (Abstract shortened by UMI.).