Abstract:
The proposed online voting system with biometric authentication is an electronic
voting system which seeks to make use of the uniqueness of the minutiae of the
human fingerprint to further enhance the level of trust and confidentiality of the
voters in the system as well as making the actual process as universally accessible
as possible which would be achieved through the deployment on the Internet. It is
expected to solve the two critical issues facing student elections conducted within
the University of Embu community which serves as the project case study. For the
voter registration and authentication processes which are performed on the desktop
module, the voter is expected to have his or her fingerprints captured and the
minutiae extracted that is stored on the database. This is done to prevent the
occurrence of multiple registrations or identity. Thus, during the authentication
period, voters are expected to undergo a matching verification of their fingerprint
samples against the values stored in the database which is identified through the use
of a unique voter identification number assigned during registration. The project was
able to achieve a high success rate in the use for conducing elections as it was able
to stamp multiple registrations by voters through combined use of both the unique
voter identification number and their unique fingerprint effectively.This project was
developed using SIFT A1gorithm technique to perform voting operations. Scale
Invariant Features Transform (SIFT) is an algorithm in computer vision to detect
and describe local features in images. The features are invariant to image scaling and
rotation. They are well localized in both the spatial and frequency domains. The
features are highly distinctive, which allows a single feature to be correctly matched
with high probability against a large database of features, providing a basis for object
and scene recognition.
