TipSegNet: Fingertip Segmentation in Contactless Fingerprint Imaging

2025-01-09

AI Summary

In contactless fingerprint recognition, precise segmentation of the fingertip region remains challenging due to interference from complex backgrounds and highly variable hand poses. To address this, we propose an end-to-end deep learning–based fingertip segmentation method. Our approach innovatively integrates ResNeXt-101 with a Feature Pyramid Network (FPN) to construct a multi-scale feature fusion architecture, and introduces a customized data augmentation strategy specifically designed for contactless imaging conditions—thereby significantly enhancing model generalization across diverse hand poses and image qualities. Evaluated on a standard benchmark dataset, our method achieves a mean Intersection-over-Union (mIoU) of 0.987 and pixel accuracy of 0.999, outperforming existing state-of-the-art techniques. This work delivers a high-accuracy, robust front-end segmentation module for contactless fingerprint recognition systems, advancing the practical deployment of non-contact biometric acquisition.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Browser and end-point security

Abstract

Contactless fingerprint recognition systems offer a hygienic, user-friendly, and efficient alternative to traditional contact-based methods. However, their accuracy heavily relies on precise fingertip detection and segmentation, particularly under challenging background conditions. This paper introduces TipSegNet, a novel deep learning model that achieves state-of-the-art performance in segmenting fingertips directly from grayscale hand images. TipSegNet leverages a ResNeXt-101 backbone for robust feature extraction, combined with a Feature Pyramid Network (FPN) for multi-scale representation, enabling accurate segmentation across varying finger poses and image qualities. Furthermore, we employ an extensive data augmentation strategy to enhance the model's generalizability and robustness. TipSegNet outperforms existing methods, achieving a mean Intersection over Union (mIoU) of 0.987 and an accuracy of 0.999, representing a significant advancement in contactless fingerprint segmentation. This enhanced accuracy has the potential to substantially improve the reliability and effectiveness of contactless biometric systems in real-world applications.

Problem

• Non-contact Fingerprint Imaging
• Fingertip Localization
• Accuracy Enhancement

Innovation

• TipSegNet
• ResNeXt-101
• Feature Pyramid Network (FPN)