e-journal - First Pan IIT International Management Conference – 2018
14 PagesPosted: 21 Dec 2020
See all articles by Sanmoy Paul
Sanmoy Paul
NMIMS Mumbai
Sameer Kumar Acharya
NMIMS University - Data-Science Department
Date Written: December 21, 2020
Abstract
Facial recognition methods were first explored in security systems to identify and compare human faces and is far superior compared to biometric and iris recognition, this technique has been implemented in iris recognition, image detection etc. Recently these methods have been explored in other fields of study and have become a commercial identification and marketing tool. This paper describes the different algorithms of facial recognition and compared their recognition accuracies. The face is detected through Haar Cascades algorithm which is saved into a database, after that, the study intended to compare facial recognition accuracy of the well-known algorithms Eigen faces with PCA, SVM, KNN, and CNN. The results showed out of the three algorithms we used CNN yielded the maximum accuracy.
Keywords: Eigen Values Haar Cascades Facial Recognition Principal Component Analysis, Convolutional Neural Network (CNN) K-Nearest Neighbour (KNN) Support Vector Machine
Suggested Citation:Suggested Citation
Paul, Sanmoy and Acharya, Sameer Kumar, A Comparative Study on Facial Recognition Algorithms (December 21, 2020). e-journal - First Pan IIT International Management Conference – 2018, Available at SSRN: https://ssrn.com/abstract=3753064 or http://dx.doi.org/10.2139/ssrn.3753064
Sanmoy Paul (Contact Author)
NMIMS Mumbai ( email )
India
Sameer Kumar Acharya
NMIMS University - Data-Science Department ( email )
Mumbai
India