Improving Fingerprint Pore Detection with a Small FCN
This work addresses the need for more efficient and accurate fingerprint pore detection, which is important for biometric security applications, but it is incremental as it builds on existing CNN approaches.
The authors tackled the problem of overparameterization in fingerprint pore detection by proposing a small fully convolutional neural network with fewer parameters, which, when combined with post-processing, outperformed previous methods in efficiency and performance.
In this work, we investigate if previously proposed CNNs for fingerprint pore detection overestimate the number of required model parameters for this task. We show that this is indeed the case by proposing a fully convolutional neural network that has significantly fewer parameters. We evaluate this model using a rigorous and reproducible protocol, which was, prior to our work, not available to the community. Using our protocol, we show that the proposed model, when combined with post-processing, performs better than previous methods, albeit being much more efficient. All our code is available at https://github.com/gdahia/fingerprint-pore-detection