International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 177 - Number 24 |
Year of Publication: 2019 |
Authors: Samarth Sarin, Siba Panda |
10.5120/ijca2019919693 |
Samarth Sarin, Siba Panda . A Convolution Neural Network for Classification of Indian Faces. International Journal of Computer Applications. 177, 24 ( Dec 2019), 7-11. DOI=10.5120/ijca2019919693
This paper is a modest attempt to compare different Indian faces into three categories that are North Indian, East Indian and South Indian. We have not taken West Indian into consideration as there are no distinct features in those faces. An artificial neural network is proposed for face classification in this paper. Images were collected from online resources and pre-processed before they were feed in the neural network. Experiments were conducted based on extracting features from the faces of Indian People belonging to different regions. The accuracy of face classification was up to 81% and the optimal choice of hyperparameters of the neural network for this task is discussed.