Facial Features Identification Using Discrete Cosine Transform and K-Nearest Neighbor (KNN)

Source abstract

Face Recognition has gained a great deal of popularity because of its wide range of applications such as in entertainment, smart cards, information security, law enforcement and surveillance. In this paper, we proposed a face recognition system for the representation and identification of facial features of human images using Discrete Cosine Transform (DCT) for feature extraction and K-Nearest Neighbor (KNN) as the classifier. The proposed model, including baseline machine learning models, were trained and evaluated on Olivetti Research Laboratory (ORL) database. The results of the experimentation showed that proposed model achieved an overall best performance accuracy of 95% with high sensitivity (recall) of 95% and low FAR and FRR of 0.13% and 2.63% respectively. The model was deployed through a web interface built with flask, enabling real-time identification of human faces from the extracted features.