Occluded Facial Recognition for Surviellance Using Deep Learning

EasyChair Preprint 7585

Abstract

 Nowadays, due to the advancement in technology, facial recognition is becoming one of the methods to identify a person. One of the challenges arises due to occlusion or partial covering of face, especially with a facial mask or a scarf. In this project, we use deep neural networks to solve the problem of recognizing such an occluded face. For this work, we have used three publicly available facial datasets, namely Labelled Face Wild dataset, COMASK20 and Specs on Faces (with images having low illumination), cumulatively consisting more than 5000 facial images. We evaluated four existing facial detection classifiers namely OpenCV, SSD, MTCNN and RetinaFace. We found that MTCNN to be most relevant for our work. We proposed a new Convolutional Neural Networks (CNN) as part of this work. We got accuracy of 99.38% for LFW, 99.62% for COMASK20 and 98.33% for SOF dataset.

Keyphrases: Convolutional Neural Network, Deep Neural Network, Labelled Face Wild dataset, Specs on Face

@booklet{EasyChair:7585,
  author    = {Hameed Moqbel and Murali Parameswaran},
  title     = {Occluded Facial Recognition for Surviellance Using Deep Learning},
  howpublished = {EasyChair Preprint 7585},
  year      = {EasyChair, 2022}}