Robust partial face recognition using hog feature points matching and minimum distance classifier

Abstract

The most successful applications of the image processing, face recognition has a vital role in technical field especially in the field of security purpose. Face Recognition is the technique to verify whether the entered image or input is exactly similar to the available images present in the databases. The technique comes under the Artificial Intelligence. Updating to the existing technique and also new technique is introduced day by day. Different types of facial recognition techniques are Finding faces in images with controlled background, Finding faces by color, Finding faces by motion, Finding faces in unconstrained scenes etc. Each and every approach has its different techniques. Subsequently various algorithms are also exist which gives us result based as per our expectation. We are implementing Partial face recognition approach by using Viola Jones method, Histogram Of Gradient features (HOG) and Minimum Distance Classifier. The advantage of this algorithm is that we can apply it on partial or incomplete faces also, even if the given input is partial, then also we can use this method. Facial recognition or face recognition as it is often referred to as, analyses characteristics of a person's face image input through a camera. It measures overall facial structure, distances between eyes, nose, mouth, and jaw edges. These measurements are retained in a database and used as a comparison when a user stands before the camera. One of the strongest positive aspects of facial recognition is that it is non-intrusive. Verification or identification can be accomplished from two feet away or more, without requiring the user to wait for long periods of time or do anything more than look at the camera.