Open AccessThe Determining Gender Using Facial Recognition Based On Neural Network With Backpropagation
Author(s) -
Fauziah Fauziah
Publication year - 2018
Language(s) - English
Resource type - Journals
ISSN - 2580-829X
DOI - 10.32734/jocai.v2.i1-96
Subject(s) - artificial intelligence , pattern recognition (psychology) , artificial neural network , facial recognition system , computer science , backpropagation , face (sociological concept) , mean squared error , speech recognition , feature extraction , mathematics , statistics , social science , sociology
One area of science that can apply facial recognition applications is artificial intelligence. The algorithms used in facial recognition are quite numerous and varied, but they all have the same three basic stages, face detection, facial extraction and facial recognition (Face Recognition) . Facial recognition applications using artificial intelligence as a major component, especially artificial neural networks for processing and facial identification are still not widely encountered. Ba ckpropagation is a learning algorithm to minimize the error rate by adjusting the weights based on the desired output and target differences. The test results of 30 images have the average value of mse is 0.14796 and the best value of mse on the test of man number 3 with mse value 0.1488 and mean 0.0047 while for the female number 2 with mse value 0.1497 and niali mean 0.0047.