Face Recognition for Ensuring Security in University Campus

Abstract

Face recognition is one of the most popular topics in research at present. It makes a new way in the biometrics field. It is possible for a machine to know individuals, known and unknown for this purpose called face recognition. So it introduces a lot of field to work that makes human life more secure, comfortable. We use a surveillance camera to ensure security purpose. But it takes too much time to identify that what we are looking for. Sometimes it was not accurate and sometimes it is impossible to find out about what we looking for. So, here face recognition can make an extra layer in this security purpose. It is widely acknowledged that face recognition has played an important role in the surveillance system. It starts a new era in security system perspective and ahead one step more in term of digitalization our country. Face recognition, the technique to determine the individuals using facial images, not only a favored topic for research but also has plentiful application in the area of biometrics, access control, information security, law enforcement, smart card, surveillance system etc. Bounteous favorable outcome has seen on special dataset through different model along with machine learning approaches. In the paper, our aim was to apply Histogram of Oriented Gradient (HOG) on our dataset for live streaming on surveillance system applicable for security purposes to detect known and unknown face in realtime data, and for this purpose, we found 86.96% accuracy rate.