Facial Image Encryption for Secure Face Recognition System

A biometric authentication system is more convenient and secure than graphical or textual passwords when accessing information systems. Unfortunately, systems have the disadvantage of being susceptible to spoofing attacks. Authentication schemes based on biometrics, including face recognition, are spoofing. This paper proposes an image encryption scheme counter attacks by integrating it into pipeline Linear Discriminant Analysis (LDA) recognition. The uses XOR pixels substitution cellular automata for scrambling. single key used encrypt training testing datasets in LDA recognition system. For added security, step requires input images faces be encrypted with correct before can recognize images. An random forest classifiers has achieved 96.25% accuracy ORL dataset classifying test In a where original were not keys feature databases, 8.75% only showing capable resisting