Open AccessTest Accuracy Improvement in Face Recognition Using Convolutional Neural Networks
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b1286.0982s1119
Subject(s) - convolutional neural network , eigenface , facial recognition system , computer science , artificial intelligence , pattern recognition (psychology) , local binary patterns , three dimensional face recognition , face (sociological concept) , artificial neural network , histogram , speech recognition , face detection , social science , sociology , image (mathematics)
Now-a-days face recognition plays a major role in identifying face of the specific person. There are different face recognition algorithms such as Eigenfaces algorithm, Local binary pattern histograms, Fisherfaces algorithm. All these algorithms face the problem of subject independence as well as translation, rotation, and scale invariance in the recognition of facial expression. In this study, the face recognition using neural network and convolutional neural network (CNN) techniques were utilized and implemented with the help of Python software 3.6.6. It is noticed that the test accuracy is improved against translation, rotation, and scale invariance in face recognition using CNN.