Fingerprint Pore Detection: A Survey

November 27, 2022 · Entered Twilight · 🏛 IEEE Transactions on Biometrics Behavior and Identity Science

Repo contents: L3SF_V2, LICENSE, README.md, architectures, dataset, datasetPores.py, dpf.py, entireImage.py, entryGiver.py, out_of_the_box_detect.py, out_of_the_box_detect, requirements.txt, scripts, train.py, util, validate.py

Authors Azim Ibragimov, Mauricio Pamplona Segundo arXiv ID 2211.14716 Category cs.CV: Computer Vision Citations 0 Venue IEEE Transactions on Biometrics Behavior and Identity Science Repository https://github.com/azimIbragimov/Fingerprint-Pore-Detection-A-Survey ⭐ 9 Last Checked 3 months ago

Abstract

This work presents the first survey on fingerprint pore detection. The survey provides a general overview of the field and discusses methods, datasets, and evaluation protocols. We also present a baseline method inspired on the state-of-the-art that implements a customizable Fully Convolutional Network, whose hyperparameters were tuned to achieve optimal pore detection rates. Finally, we also reimplementated three other approaches proposed in the literature for evaluation purposes. We have made the source code of (1) the baseline method, (2) the reimplemented approaches, and (3) the training and evaluation processes for two different datasets available to the public to attract more researchers to the field and to facilitate future comparisons under the same conditions. The code is available in the following repository: https://github.com/azimIbragimov/Fingerprint-Pore-Detection-A-Survey