Deep Learning Techniques for Automation and Industrial Applications

7HOG and Haar Feature Extraction-Based Security System for Face Detection and Counting

Prachi Soni^1* and Viplav Soni²

¹School of Computer Studies, Sri Balaji University, Pune, Maharastra, India

²Shri Shankaracharya Group of Institution, Bhilai, India

Abstract

Several surveillance-based people-counting frameworks have been proposed to track multiple people in real-time. However, the framework needs accurate and real-time performance to count how many people are present at a particular moment in a particular frame. So, our counting framework automatically detects each person’s face and takes instantaneous decisions to count the number of persons in front of the camera or with a set of images. The work of individual counting can be done in two broad ways: First is the detection of faces; it will be compulsory to detect the faces. The second is the counting approach used to track and count the number of persons on that frame.

Keywords: Feature extraction, classifier, face detection, histogram

7.1 Introduction

While cybersecurity is important, one’s physical security is also important, if not more important. Keeping a site involves two primary functions: first, it detects the faces of people who are standing in front of the camera by sensing their motion through a sensor, and second, it counts the number of people in that frame by analyzing variations in different poses. This analysis is achieved using a combination of the histogram of oriented gradients (HOG) and Haar-like feature-extraction ...