A Novel Face Spoofing Detection Using hand crafted MobileNet

Abstract

There are several uses for face spoofing detection, including human-robot communication, business, film, hotel services, and even politics. Despite the adoption of numerous supervised and unsupervised techniques in a wide range of domains, proper analysis is still lacking. As a result, we chose this difficulty as our study problem. We have put out a method for the effective and precise classification of face spoofing that may be used for a variety of everyday issues. This work attempts to investigate the ideal method and parameters to offer a solution for a powerful deep learning spoofing detection system. In this study, we used the LCC FASD dataset and deep learning algorithms to recognize faces from photos. Precision and accuracy are used as the evaluation measures to assess the performance of the CNN (Convolutional Neural Network) model. The results of the studies demonstrate that the model was effective at spoofing face picture detection. The accuracy of the CNN model was 0.98. Overall, the study's findings show that spoofing detection from photos using the LCC FASD dataset can be successfully performed utilizing deep learning algorithms. Yet, the findings of this study offer a strong framework for further investigation in this area.