Masked Face Dataset Generation and Masked Face Recognition

TL;DR

This paper introduces a new challenging masked face dataset derived from LFW, and proposes fine-tuning advanced neural networks with data augmentation to improve masked face recognition accuracy, achieving 95% accuracy.

Contribution

The study creates a more challenging masked face dataset and demonstrates improved recognition performance by fine-tuning state-of-the-art networks with data augmentation.

Findings

Achieved 95% test accuracy on the new dataset.

Fine-tuning and data augmentation significantly improve recognition results.

Developed a more realistic masked face dataset from LFW.

Abstract

In the post-pandemic era, wearing face masks has posed great challenge to the ordinary face recognition. In the previous study, researchers has applied pretrained VGG16, and ResNet50 to extract features on the elaborate curated existing masked face recognition (MFR) datasets, RMFRD and SMFRD. To make the model more adaptable to the real world situation where the sample size is smaller and the camera environment has greater changes, we created a more challenging masked face dataset ourselves, by selecting 50 identities with 1702 images from Labelled Faces in the Wild (LFW) Dataset, and simulated face masks through key point detection. The another part of our study is to solve the masked face recognition problem, and we chose models by referring to the former state of the art results, instead of directly using pretrained models, we fine tuned the model on our new dataset and use the last linear layer to do the classification directly. Furthermore, we proposed using data augmentation strategy to further increase the test accuracy, and fine tuned a new networks beyond the former study, one of the most SOTA networks, Inception ResNet v1. The best test accuracy on 50 identity MFR has achieved 95%.