Title: Sparse local binary pattern histograms for face recognition with limited training samples
Abstract: One of the harder problems in facial recognition is the Single Sample per Person (SSPP) problem, where only one training image is available for a facial recognition model. Such a problem exists in practical applications such as the OSCARS which is a face recognition for classroom attendance checking. This study focuses on benchmarking different local binary pattern based algorithms for face recognition, with the goal of finding the best suited to the purposes of such an application. The study also proposes and shows that the Sparse Local Binary Pattern is consistently robust to variations in both changes in lighting and rotation when recognizing faces.
Publication Year: 2014
Publication Date: 2014-03-28
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot