Abstract
In this paper, we present a new face recognition algorithm based on weighted deep face learning. Our proposed method composes of two steps: face detection and face feature extraction. The aim of face detection is to find an accurate face position. The face alignment is then applied by finding the facial landmarks in the face rectangle. With the help of face alignment the error rate of face recognition can be reduced. Deep learning is employed to extract distinctive features of the face components. We create the weights for each face feature by optimizing the within class variations with respect to between class similarity measures. We achieved the lowest total error rate of 0.01429% on XM2VTS database. We also accomplished the 98.61% of accuracy on LFW database. For realtime face recognition we achieved 99.17% for our own video database.
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 callDisclaimer: 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.
