A Raspberry Pi-Based Identity Verification Through Face Recognition Using Constrained Images

Abstract

In this paper, we proposed a novel, cost-effective and energy-efficient framework by introducing a Raspberry Pi-based identity verification through face recognition in an offline mode. A Raspberry Pi device and mobile phone is wirelessly connected to standard pocket WIFI to process the face detection and face verification. The experimental tests were done using 3000 public constrained images. The proposed method is implemented on Raspberry Pi 3 run in Python 3.7 where the datasets and trained datasets were experimented using LBP algorithm for face detection and face verification in five split testing. The result was interpreted using the confusion matrix and Area Under the Curve (AUC) and Receiver Operating Characteristics (ROC). To sum up, the proposed method showed an average result of 0.98135% accuracy, with 98% recall score and an F1-score of 0.9881. During the offline mode testing, the face detection and verification average timing is 1.4 s.