Masked Face Image Classification with Sparse Representation based on Majority Voting Mechanism

TL;DR

This paper presents a method combining Orthogonal Matching Pursuit and Sparse Representation-based Classification with a majority voting mechanism to classify masked face images, achieving high accuracy on the AR dataset.

Contribution

It introduces a novel application of sparse representation and OMP algorithms with majority voting for masked face classification, demonstrating improved accuracy.

Findings

Achieved 98.4% accuracy on AR dataset

OMP combined with SRC outperforms other methods

Validates effectiveness of sparse representation in masked face recognition

Abstract

Sparse approximation is the problem to find the sparsest linear combination for a signal from a redundant dictionary, which is widely applied in signal processing and compressed sensing. In this project, I manage to implement the Orthogonal Matching Pursuit (OMP) algorithm and Sparse Representation-based Classification (SRC) algorithm, then use them to finish the task of masked image classification with majority voting. Here the experiment was token on the AR data-set, and the result shows the superiority of OMP algorithm combined with SRC algorithm over masked face image classification with an accuracy of 98.4%.