Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

20211

Settings

Author: search.filters.author.Kılınç, Vahdettin OnurSubject: search.filters.subject.Fingerprints

Search Results

Now showing 1 - 1 of 1
  • Master Thesis
    Synthetic Fingerprint Generation With Gans
    (01. Izmir Institute of Technology, 2021) Kılınç, Vahdettin Onur; Erdoğmuş, Nesli; Erdoğmuş, Nesli; 01. Izmir Institute of Technology; 03.04. Department of Computer Engineering; 03. Faculty of Engineering
    Fingerprints regarded as the most reliable form of human identification for thousands of years. Even though the fingerprint collection process became more convenient with technological advancements, privacy concerns slowed down the researchers working on fingerprint biometrics. Like every other problem solved with deep learning, biometrics requires a sizable database to succeed. This study generates synthetic fingerprints to tackle bottlenecks created by privacy laws. First, the pipeline designed enhances images from a small publicly available fingerprint dataset. The new enhanced dataset is given as an input to a generative network to create candidate synthetic fingerprints. Fingerprint image quality models choose high-quality fingerprint images from the candidate set to form the synthetic fingerprint dataset. Numerous experiments were conducted to show the quality of the generated synthetics fingerprints using both real and synthetic fingerprint datasets available.Experimental results show that enhancing fingerprint images from real-life datasets helps integrate synthetic fingerprint images into real life. Synthetic fingerprints generated from the pipeline can generate large datasets with a representative quality close to their real-life counterparts without privacy concerns.