Residual Finger Feature Points UNet with Nonlinear Decay on Wet Partial Fingerprint Image Recognition in Tiny Sensor

Abstract—Fingerprint recognition technology has become

popular for mobile device authentication systems due to its

reliability and ease of use. As smartphones evolve, fingerprint

sensors are now integrated into smartphone power with a width

of 2.2 mm. However, tiny sensor sizes have led to limited finger

coverage and external factors such as sweat or water droplets

can cause image distortion, making user authentication more

challenging.

To address these issues, we propose the FFP-UNet, which uses

fingerprint feature points-based restoration and nonlinear decay

rate residual within a U-shape architecture to recognize blurry

and wet fingerprints within size constraints effectively. Our

approach aims to restore fingerprints effectively while avoiding

over-restoration and preserving local matching feature points,

which reduces the false rejection rate (FRR). We develop novel

residual blocks, which feature a nonlinear decay mechanism

that optimizes weight allocation between blocks to enhance

feature extraction capabilities. Furthermore, our residual feature

points fusion module restores contextual information by fusing

matching feature points and features from the previous level. To

overcome unaligned data in real-world scenarios, our approach

incorporates the residual MaxBlurPool module.

Through comprehensive experiments on real-world data, we

achieved a remarkable 9.4% reduction in FRR. Our method

outperforms the basic U-Net framework [1] by 50.52% in

overall performance. We improved 48.35% over FPDMNet [2]

and 58.77% over DenseUNet [3] which is trained with small

patches. Moreover, PGT-Net [4] is also used for small areas

of wet fingerprints, but our FFP-UNet outperformed it by

72.51%. Source code is available for research purposes at

https://github.com/aannn555/FFP-UNet.