AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements

4 Dec 2020  ·  Mohit Raghavendra, Pravan Omprakash, B R Mukesh, Sowmya Kamath ·

Biometric systems based on Machine learning and Deep learning are being extensively used as authentication mechanisms in resource-constrained environments like smartphones and other small computing devices. These AI-powered facial recognition mechanisms have gained enormous popularity in recent years due to their transparent, contact-less and non-invasive nature. While they are effective to a large extent, there are ways to gain unauthorized access using photographs, masks, glasses, etc. In this paper, we propose an alternative authentication mechanism that uses both facial recognition and the unique movements of that particular face while uttering a password, that is, the temporal facial feature movements. The proposed model is not inhibited by language barriers because a user can set a password in any language. When evaluated on the standard MIRACL-VC1 dataset, the proposed model achieved an accuracy of 98.1%, underscoring its effectiveness as an effective and robust system. The proposed method is also data-efficient since the model gave good results even when trained with only 10 positive video samples. The competence of the training of the network is also demonstrated by benchmarking the proposed system against various compounded Facial recognition and Lip reading models.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Lip password classification on MIRACL-VC1 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Lip password classification MIRACL-VC1 AuthNet 2-Class Accuracy 0.981 # 1

Methods