Sketch based face recognition

Face recognition is a task of identifying an individual in an image using a set of images stored in a database. The applications of this activity are vast, few of them include automatic attendance marking system, security issues concerning smartphones and other smart devices, law enforcement and so on. Most of the existing systems focus on image to image face recognition, whereas our system can perform sketch to image recognition. The system can either implement Convolutional Neural Network (CNN) or Histogram of Oriented Gradients (HOG). Apart from recognizing a face in a sketch, this paper will also concentrate on testing the speed of execution of both algorithms. A graph will be determined to show the comparison between the two algorithms.