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.
Abstract (translated)
这项工作描述了我们为Chalearn LAP In-painting竞赛第3轨 - 指纹去噪和绘画提供的成功解决方案。本次比赛的目的是减少噪音，删除背景图案并更换指纹图像的缺失部分，以简化人或第三方软件的验证。在本文中，我们使用像CNN模型这样的U-Net，在以完全监督的方式对竞争数据进行训练后，端到端地执行所有这些步骤。该架构和培训程序在竞争的所有三个指标上取得了最佳结果。
URL
https://arxiv.org/abs/1807.11888
