Abstract
Artificial intelligence (AI) has captured the public’s imagination. Performance gains in computing hardware, and the ubiquity of data have enabled new innovations in the field. In 2014, Facebook’s DeepFace AI took the facial recognition industry by storm with its splendid performance on image recognition. While newer models exist, DeepFace was the first to achieve near-human level performance. To better understand how this breakthrough performance was achieved, we developed our own facial image detection models. In this paper, we developed and evaluated six Convolutional Neural Net (CNN) models inspired by the DeepFace architecture to explore facial feature identification. This research made use of the You Tube Faces (YTF) dataset which included 621,126 images consisting of 1,595 identities. Three models leveraged pretrained layers from VGG16 and InceptionResNetV2, whereas the other three did not. Our best model achieved a 84.6% accuracy on the test dataset.
Highlights
Facial recognition is a method of identifying an individual using his or her face from a digital image or a video clip
An overview of the rest of the paper is as follows: in Section 2 we reviewed some of the related work in the same research field with DeepFace; in Section 3, we introduce core techniques related to DeepFace: Deep Learning and Convolutional Neural Networks; Section 4 describes the 3D model-based face alignment method applied and the model architecture used; Section 5 talks about our deep learning model that follows the architecture of DeepFace’s and was trained on YouTube Faces (YTF) video data set
We demonstrated the power of learned features through six convolutional neural networks (CNNs)
Summary
Facial recognition is a method of identifying an individual using his or her face from a digital image or a video clip Such methods could be used for facial authentication by pinpointing and determining facial features from a given image, uniquely identifying the person. This was limited to desktop computers due to demanding computational power constraints. While facially driven learning has been widely used, critical commentators are beginning to question the pedagogical limitations of it They purposed multiple questions about facial recognition technology including the likelihood of it altering the nature of schools and schooling along divisive, authoritarian and oppressive lines, and what kind of law and regulatory mechanisms can help for eliminating the potential risks to consumers when they are making use of it [7].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
