Deep End-to-end Fingerprint Denoising and Inpainting

2018/07/31 by Youness Mansar, Mansar, Youness
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1807.11888

Winning solution to the Chalearn LAP In-painting Competition Track 3 / Accepted in the 2018 Chalearn Looking at People Satellite Workshop ECCV

arxiv created 2018/09/13 · arxiv updated 2018/09/14

Abstract

This work describes our winning solution for the Chalearn LAP In-painting Competition Track 3 - Fingerprint Denoising and In-painting. The objective of this competition is to reduce noise, remove the background pattern and replace missing parts of fingerprint images in order to simplify the verification made by humans or third-party software. In this paper, we use a U-Net like CNN model that performs all those steps end-to-end after being trained on the competition data in a fully supervised way. This architecture and training procedure achieved the best results on all three metrics of the competition.

Related

• FPD-M-net: Fingerprint Image Denoising and Inpainting Using M-Net Based Convolutional Neural Networks
• U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting
• Deep Encoder-Decoder Neural Network for Fingerprint Image Denoising and Inpainting
• PGT-Net: Progressive Guided Multi-task Neural Network for Small-area Wet Fingerprint Denoising and Recognition
• Fingerprint Feature Extraction by Combining Texture, Minutiae, and Frequency Spectrum Using Multi-Task CNN