WISE College Final Year Project 2024 - CSE - Title FACE MORPH ATTACKS DETECTION by D Amrutha

B. Durga (20PD1A0508)
A. Prince (20PD1A0505)
D . Amrutha (20PD1A0517)
M.L.D.Prasad (20PD1A0534)
B. Lavanya (20PD1A0512)
ABSTRACT

Failure of facial recognition and authentication system may lead to several unlawful activities. The current facial recognition systems are vulnerable to different biometric attacks. This project focuses on morphing attack detection. This proposes a robust detection mechanism that can deal with variations in age, illumination, eye and head gears. A deep learning-based feature extractor along with a classifier is adopted. Additionally, image enhancement and feature combination are proposed to augment the detection results. A versatile dataset that contains Morph-2 and Morph-3 images is also developed, created by sophisticated tools with manual intervention. Morph-3 images can give a more realistic appearance and are hence difficult to detect. Moreover, Morph-3 images are not considered in the literature before. Professional morphing software depicts a more realistic morph attack scenario as compared to the morphs generated in the previously developed systems. Eight face databases are used for the creation of morphs to encompass the variation. These databases are Celebrity2000, Extended Yale, FEL, FGNET, GT-DB, MULTI-PIE, FERET, and FRLL.. FaceMorpher, OpenCV, FaceFusion are used that generate morphed images automatically and the majority of created morphed images are easily detectable through visual inspection by a human.

Видео WISE College Final Year Project 2024 - CSE - Title FACE MORPH ATTACKS DETECTION by D Amrutha канала WISE ENGG COLLEGE