J
Joshua J. Engelsma
Researcher at Michigan State University
Publications - 31
Citations - 447
Joshua J. Engelsma is an academic researcher from Michigan State University. The author has contributed to research in topics: Fingerprint recognition & Fingerprint. The author has an hindex of 8, co-authored 29 publications receiving 257 citations.
Papers
More filters
Proceedings ArticleDOI
Fingerprint Synthesis: Search with 100 Million Prints
TL;DR: The GAN incorporates an identity loss which guides the generator to synthesize fingerprints corresponding to more distinct identities, and the characteristics of the synthesized fingerprints are shown to be more similar to real fingerprints than existing meth- ods.
Posted Content
RaspiReader: Open Source Fingerprint Reader
TL;DR: This work proposes that this open source fingerprint reader will facilitate the exploration of novel fingerprint spoof detection techniques involving both hardware and software, and demonstrates one such spoof detection technique by specially customizing RaspiReader with two cameras for fingerprint image acquisition.
Posted Content
HERS: Homomorphically Encrypted Representation Search
TL;DR: Numerical results show that, for the first time, accurate and fast image search within the encrypted domain is feasible at scale (296 seconds; 46x speedup over state-of-the-art for face search against a background of 1 million).
Posted Content
Generalizing Fingerprint Spoof Detector: Learning a One-Class Classifier
Joshua J. Engelsma,Anil K. Jain +1 more
TL;DR: In this article, a one-class classification approach was proposed to detect spoofing attacks on the RaspiReader fingerprint reader by training multiple generative adversarial networks (GANs) on live fingerprint images acquired with the open-source, dual-camera, 1900 ppi RaspioReader fingerprint readers.
Journal ArticleDOI
PrintsGAN: Synthetic Fingerprint Generator
TL;DR: PrintsGAN as discussed by the authors is a synthetic fingerprint generator capable of generating unique fingerprints along with multiple impressions for a given fingerprint, which can be used to train a deep network to extract a fixed-length embedding from a fingerprint.