mlsanityData to 7 Oct 2026

Fused Deep Neural Network based Transfer Learning in Occluded Face Classification and Person re-Identification

arXiv 2205.07203 ↗First posted 15 May 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent period of pandemic has brought person identification even with occluded face image a great importance with increased number of mask usage. This paper aims to recognize the occlusion of one of four types in face images. Various transfer learning methods were tested, and the results show that MobileNet V2 with Gated Recurrent Unit(GRU) performs better than any other Transfer Learning methods, with a perfect accuracy of 99% in classification of images as with or without occlusion and if with occlusion, then the type of occlusion. In parallel, identifying the Region of interest from the device captured image is done. This extracted Region of interest is utilised in face identification. Such a face identification process is done using the ResNet model with its Caffe implementation. To reduce the execution time, after the face occlusion type was recognized the person was searched to confirm their face image in the registered database. The face label of the person obtained from both simultaneous processes was verified for their matching score. If the matching score was above 90, the recognized label of the person was logged into a file with their name, type of mask, date, and time of recognition. MobileNetV2 is a lightweight framework which can also be used in embedded or IoT devices to perform real time detection and identification in suspicious areas of investigations using CCTV footages. When MobileNetV2 was combined with GRU, a reliable accuracy was obtained. The data provided in the paper belong to two categories, being either collected from Google Images for occlusion classification, face recognition, and facial landmarks, or collected in fieldwork. The motive behind this research is to identify and log person details which could serve surveillance activities in society-based e-governance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 39 references that are in the map. First posted on arXiv 15 May 2022.

Builds on

13 of 39 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  6. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  7. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  8. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  9. 2015From Facial Parts Responses to Face Detection: A Deep Learning Approachcited by 42
  10. 2016Grid Loss: Detecting Occluded Facescited by 17
  11. 2016CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detectioncited by 14
  12. 2016Supervised Transformer Network for Efficient Face Detectioncited by 14
1 more
  1. 2014Scalable, High-Quality Object Detectioncited by 11

Built on by

Not cited yet.