Master Degree / Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/11147/3008
Browse
2 results
Search Results
Master Thesis Analysis of fingerprint matching performance with deep neural networks(01. Izmir Institute of Technology, 2022) Göçen, Alper; Erdoğmuş, NesliFingerprints are unique biometric properties for each person. In the literature and industry, they are widely used for identification purposes. Collecting biometric datasets is a tedious work since it is not possible without the owners’ consent, and existing fingerprint datasets are either not sufficient to use in deep learning tasks by means of size or most of them are kept private to the collectors’ use. This increases the need of synthetic fingerprint images and their use in a variety of tasks especially for training deep learning models. In this study, the performance of a CNN architecture named Finger ConvNet[1] is compared to well-known networks and the question of whether a mixed dataset consisting of synthetically generated and real fingerprint images can reach a performance close or equal to ones having only real images is discussed. As a result of experiments, it is shown that the number of real images in the dataset is an important factor and that the performance of the mixed dataset was less than the one having only real images proposed in the referred study.Master Thesis Synthetic Fingerprint Generation With Gans(01. Izmir Institute of Technology, 2021) Kılınç, Vahdettin Onur; Erdoğmuş, NesliFingerprints 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.