What type of study is this?

September 10, 2025Open Access

FingerUNeSt++: Improving Fingertip Segmentation in Contactless Fingerprint Imaging Using Deep Learning

LRLaurenz RuzickaAustrian Institute of Technology BKBernhard KohnAustrian Institute of Technology CHClemens HeitzingerUniversity of Vienna

Key Points

The FingerUNeSt++ model improves fingertip segmentation, significantly outperforming traditional methods in contactless fingerprint accuracy.
Achieving high performance metrics, the model combines deep learning architectures ResNeSt and UNet++ for optimized inference speed.
Extensive data augmentation techniques bolster the model's robustness, enabling efficiency in various background conditions.
This advancement in biometric identification holds potential for enhancing contactless systems in diverse real-world applications.

Abstract

Biometric identification systems, particularly those utilizing fingerprints, have become essential as a means of authenticating users due to their reliability and uniqueness. The recent shift towards contactless fingerprint sensors requires precise fingertip segmentation with changing backgrounds, to maintain high accuracy. This study introduces a novel deep learning model combining ResNeSt and UNet++ architectures called FingerUNeSt++, aimed at improving segmentation accuracy and inference speed for contactless fingerprint images. Our model significantly outperforms traditional and state‐of‐the‐art methods, achieving superior performance metrics. Extensive data augmentation and an optimized model architecture contribute to its robustness and efficiency. This advancement holds promise for enhancing the effectiveness of contactless biometric systems in diverse real‐world applications.

Ask AI

Helpful

Bookmark

View Full Paper