Partial Face Identification using Local Feature Extraction Algorithm on Different Classifiers

Face identification is a complex problem with a long history and is currently the subject of much research in unconstrained conditions, including occlusion, facial expression, position change, and lighting. Nevertheless, the occlusion issue receives less attention in current studies. Many sophisticated deep learning and machine learning algorithms have been developed to enhance the identification of occlusion. A new face recognition method: Local Features Extraction with Logistic Classifier, designed to identify someone from the area of their face that is not covered. This proposed work extracts the features by taking the difference of patches and then generating the patch sequence using the k-means clustering algorithm and classifying them using different classifiers. This paper used five classifiers to check their effectiveness in matching the train and test patch sequence. Two public datasets, AR for natural occlusion and ORL for synthetic occlusion are used for experimental work.