English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fingerprint recognition on mobile devices is an important method for identityverification. However, real fingerprints usually contain sweat and moisturewhich leads to poor recognition performance. In addition, for rolling outslimmer and thinner phones, technology companies reduce the size of recognitionsensors by embedding them with the power button. Therefore, the limited size offingerprint data also increases the difficulty of recognition. Denoising thesmall-area wet fingerprint images to clean ones becomes crucial to improverecognition performance. In this paper, we propose an end-to-end trainableprogressive guided multi-task neural network (PGT-Net). The PGT-Net includes ashared stage and specific multi-task stages, enabling the network to trainbinary and non-binary fingerprints sequentially. The binary information isregarded as guidance for output enhancement which is enriched with the ridgeand valley details. Moreover, a novel residual scaling mechanism is introducedto stabilize the training process. Experiment results on the FW9395 andFT-lightnoised dataset provided by FocalTech shows that PGT-Net has promisingperformance on the wet-fingerprint denoising and significantly improves thefingerprint recognition rate (FRR). On the FT-lightnoised dataset, the FRR offingerprint recognition can be declined from 17.75% to 4.47%. On the FW9395dataset, the FRR of fingerprint recognition can be declined from 9.45% to1.09%.

PGT-Net: Progressive Guided Multi-task Neural Network for Small-area Wet Fingerprint Denoising and Recognition