00000ctmaa22000003a 4500 UP-1685675941123958234 Buklod 20180817122048.0 aa rb |||1 u| ta 180817s xx d r |||| u| (iLib)UPTAC-00019010354 UPVTC eng LG 993.5 2017 C66 N38 Navarro, Adam Adrian L. FingERT an offline fingerprint verification system using Extremely Randomized Trees. Adam Adrian L. Navarro 2018 Undergraduate thesis (B.S. Biology) -- University of the Philippines, Tacloban. Fingerprint is one of the most accepted and reliable biometric verification. However manual fingerprint verification is so tedious, time-consuming, and expensive that is incapable of meeting today's increasing performance requirements. That is why an automated fingerprint identification system is widely needed. Today, a number of approaches to this problem already exist but this study proposes a hybrid system using Extremely Randomized Trees (Extra-Trees). Features that were extracted from the fingerprint images including the most commonly used minutiae features (endings and bifurcations) were used to produce tree ensembles that classify whether the fingerprint matches or not. The results of this study show that the Extra-Trees algorithm together with the features extracted from the dataset is an effective solution to the problem. biometric. fingerprint. FI UP UPTAC UPTAC LG 993.5 2017 C66 N38 Thesis