INCREASING SECURITY AND OPTIMIZATION USING FINGERPRINT AND CLOUD COMPUTING IN ONLINE VOTING SYSTEM

Abstract

Election is a process in which voters choose their representatives and express their preferences for the way that they will be governed. Using the decade old voting system to collect votes is no longer considered efficient due to the various recurring errors. The advancement of information and telecommunications technologies allow for a fully automated online computerized election process. An electronic voting system defines rules for valid voting and gives an efficient method of counting votes, which are aggregated to yield a final result. Correctness, robustness to fraudulent behaviors, coherence, consistency, security, and transparency of voting are all key requirements for the integrity of an election process. Moreover, electronic voting systems can improve voter identification process by utilizing biometric recognition which provides more security. Biometrics is becoming an essential component of personal identification solutions, since biometric identifiers cannot be shared or misplaced, and they represent any individual’s identity. Fingerprint matching is a significant part of this process. This project work propose online security enhancement technique using level 3 fingerprint features and scale invariant feature transform algorithm for matching purpose. Firstly fingerprint of good quality are acquired by using optical scanner. Image normalization is done using Gaussian blurring and sliding window contrast adjustment. Pores are extracted and estimated. Using these estimated pores, matching is done from template database to stored database using SIFT algorithm. 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. The voter's fingerprint database is huge in size. To check the authentication of voter, input fingerprint template has to be matched against entire stored fingerprint database. To speedup the process and gain efficiency, fingerprint database will be uploaded on cloud where matching results can be retrieved fast as compare to matching on a single high computing power CPU.