Open AccessA Hybrid Enhanced Real-Time Face Recognition Model using Machine Learning Method with Dimension Reduction
Author(s) -
Jaya Kumari,
Kailash C. Patidar,
Mr. Gourav Saxena,
Mr. Rishi Kushwaha
Publication year - 2021
Publication title -
indian journal of artificial intelligence and neural networking (ijainn)
Language(s) - English
Resource type - Journals
ISSN - 2582-7626
DOI - 10.54105/ijainn.b1027.061321
Subject(s) - scale invariant feature transform , artificial intelligence , computer science , principal component analysis , facial recognition system , pattern recognition (psychology) , face (sociological concept) , locality , feature (linguistics) , feature extraction , dimensionality reduction , computer vision , social science , linguistics , philosophy , sociology
Face recognition techniques play a crucial role in numerous disciplines of data security, verification, and authentication. The face recognition algorithm selects a face attribute from an image datasets. Recognize identification is an authentication device for verification as well as validation having both data analysis and feasible significance. The facerecognizing centered authentication framework can further be considered an AI technology implementation for instantly identifying a particular image. In this research, we are presenting a hybrid face recognition model (HFRM) using machine learning methods with “Speed Up Robust Features” (SURF), “scale-invariant feature transform” (SIFT), Locality Preserving Projections (LPP) &Principal component analysis (PCA) method. In the proposed HFRM model SURF method mainly detects the local feature efficiently. SIFT method mainly utilizes to detect the local features and recognize them. LPP retains the local framework of facial feature area which is generally quite meaningful than on the sequence kept by a ‘principal component analysis (PCA) as well as “linear discriminate analysis” (LDA). The proposed HFRM method is compared with the existing (H. Zaaraoui et al., 2020) method and the experimental result clearly shows the outstanding performance in terms of detection rate and accuracy % over existing methods.