EYE SPY Face Detection and Identification using YOLO

Abstract

YOLO (You Only Look Once) is a state of the art object detection system. The object detection algorithms of YOLO is taken and is used on a custom made dataset to identify the person on camera. This method will revolutionize surveillance and security methods. This paper addresses fundamental challenges faced in making the dataset. It also compares conventional methods with YOLO. YOLO is the fastest and most accurate object detection technique. This paper also states the applications of this technology along with its advantages and various disadvantages. It uses a multi-scale training method that can run at various sizes offering an excellent relation speed and accuracy. We have based our model on yolo v2 all the while bringing our own changes for shifting from object detection to Face identification.