Estimating the Number of People in Digital Still Images Based on Viola-Jones Face Detection Algorithms

Abstract

This paper focuses on the challenging task of counting the number of people in digital still images, which has important applications in many fields like security and management. This paper proposes a system that is based on the Viola-Jones face detection methods. This system consists of two parts: a) face detection and b) counting the detected faces. In the face detection part, the Viola-Jones (LBP and CART feature extraction) algorithm is applied to the input image. In the counting part, the detected faces are counted to predict the number of people in the given image. The Viola-Jones algorithm is applied using 133 images from the People Image Groups dataset, and the best precision achieved is 96.9%. Overall, this paper presents a promising system for accurately counting the number of people in digital static images using a simple and cost-effective approach.