Abstract
Face morphing is by far the greatest threat to effective automatic boarder control systems. However, there is a lack of consideration and examination of a morphed face image frame as a blend of two images; hence, one image obstructs the other. To address this, we proposed a combination of an occlusion detection method, FSG-FD and a VGG19 neural network architecture to detect these face morphs. First, we designed our algorithms for each of our proposed systems; one for FSG-FD and the other for the VGG19 architecture. Then, we blended the two methods into a joined model by pre-training the neural network and increasing its convolutional layers by an additional three layers. The experiments showed that our algorithm achieved higher accuracy than other methods at detecting face morphs.
Sign-in/Register to access full text options 
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.
