Title: Latent fingerprint segmentation using multi-scale attention U-Net

Authors: P. Akhila; Shashidhar G. Koolagudi

Addresses: Department of Computer Science and Engineering, National Institute of Technology Karnataka, India ' Department of Computer Science and Engineering, National Institute of Technology Karnataka, India

Abstract: Latent fingerprints are the fingerprints lifted from crime scene surfaces. Segmentation of latent fingerprints from the background is an important preprocessing task which is challenging due to the poor quality of the fingerprints. Though fingerprint segmentation approaches based on their orientation and frequency are reported in the literature, they could not adequately address the problem. We propose a latent fingerprint segmentation model based on the U-Net attention network in this work. We added the Atrous Spatial Pyramid Pooling (ASPP) layer to the network to facilitate multi-scale fingerprint segmentation. Our approach could effectively segment the latent fingerprint region from the background and even detect occluded and partial fingerprints with simple network architecture. To evaluate the performance, we have compared our results with the manual ground truth using NIST SD27A dataset. Our segmentation model has improved matching accuracy on the NIST SD27A dataset.

Keywords: latent fingerprint segmentation? U-Net? attention? weighted cross entropy? multi-scale.

DOI: 10.1504/IJBM.2024.137070

International Journal of Biometrics, 2024 Vol.16 No.2, pp.195 - 215

Received: 19 Oct 2022
Accepted: 26 Feb 2023
Published online: 01 Mar 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article