Description of Invention
Due to COVID-19 pandemic, face masks’ widespread adoption in public has spurred an urgent need to investigate masked face recognition systems' efficacy. Deep learning method has been suggested to potentially offer more precise result while sparse representation technique has been suggested as capable of addressing challenges arising from large block occlusions or disguised images. Thus, a new approach of leveraging sparse representation and deep learning techniques, termed Sparse CNN is proposed. This method utilises Tailored Convolutional Neural Network (Tailored CNN) as feature extractor and integrates Sparse Representation based Classification (SRC) as a classifier to improve masked face recognition systems' accuracy.