Spoofing Face Detection using LBP Descriptor and KNN Classifier in Image Processing

Abstract

Image processing in today’s world used for performing operations on images by using a process of making positive suggestion of face which can be in a photo or video in already existing face database. Extraction of face attributes is done in face detection from photos and also from videos. When any unauthorized person tries to enter in authentication system by presenting fraud image and video is termed as spoofing attack. Biometrics is a technology which recognizes characteristics of human and is prone to spoof attacks. The detection of spoofed faces by recognizing and exploring the fake face and genuine face images is called face spoof detection. The DWT method is used to inspect the textual attribute occurring within the test images. There is a possibility that some unusual disruptions are available like geometric disruption and the artificial texture disruption. Eigen face technique is applicable for taking out attributes. Histogram for every feature or attributes is determined and employed a collation of essence to find out face spoof detection. To explore even if the image is actual and gag, already used approach Support Vector Machine is used. To make face spoof detection more accurate KNN classifier will take the place of the SVM classifier. The Contrast are construct to inspect the performance of the suggest algorithm and the existing algorithm in two parameters accuracy and time of execution. Detection of spoofed faces can be used for security purpose, preventing crime, access control system.