Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAng, Li Zheen_US
dc.description.abstractBiometric face recognition technology is vital in security. With social media platforms such as Facebook, Instagram, YouTube, obtaining an individual’s photo or video is easy. With ill intentions, these imageries can be abused and exploited to attack face recognition-based biometric systems. This research provides an overview of presentation attacks (PA) and explores anti-spoofing techniques enabled through machine learning. I approached the issue as a binary classification problem and obtained over 40000 images of different ethnicities, separated into their respective classes of real and fake. I have also explored different techniques such as Visual Geometry Group (VGG)-esque architecture, transfer learning and eye blinking detection using state-of-the-art technologies such as TensorFlow, Keras, OpenCV, Scikit-learn. The algorithms are written in Python. Based on my findings, the results obtained were significant – a 99% accuracy in differentiating between spoofed and real faces.en_US
dc.publisherNanyang Technological Universityen_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleFace spoofing indicator using deep learningen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorWen Changyunen_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeBachelor of Engineering (Electrical and Electronic Engineering)en_US
item.fulltextWith Fulltext-
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
Final Year Report.pdf
  Restricted Access
Face anti-spoofing is now drawing more and more attentions in both industrial and academic fields with the widely used applications in people’s daily lives like phone unlock, access control, and security systems. Objectives: Develop and train deep learning model(s) that can detect fake/spoofed faces, where the faces are not real person but photo shown in front of the camera. Expected Results: Deep learning model(s) in Keras/ Tensorflow/ Caffe that can indicate whether a detected face is real or a photo/phone images. Requirements: The trained model(s) should be robust to any face pose and more on faces captured with mobile camera. Also the accuracy of the model(s) should be guaranteed. Model(s)can be used in Python/C++/Matlab with Keras/Tensorflow/Caffe.2.5 MBAdobe PDFView/Open

Page view(s)

Updated on Feb 28, 2024

Download(s) 50

Updated on Feb 28, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.