Published April 25, 2022 | Version v1

The System for Estimating the Number of People in Digital Images Based on Skin Color Face Detection Algorithm

  • 1. Department of Computer Science, Faculty of Science, Garyan University, Garyan, Libya,

Description

Counting the number of people in many estimation systems, such as still images or video frames, is a buoyant research area that is challenging in the field of computer vision. It plays a considerable role in a variety of applications, such as security, management, education, and commerce. The purpose of this paper is to suggest a system to estimate the number of people in digital still images based on the Face Detection method.  This system composed of two parts: face detection and counting of detected faces. In the detection step, the Skin Color Face Detection method was applied on the input of a digital still image. In the counting part, the obtained detected faces by the Skin Color Face Detection method have counted to estimate the number of people in an input color image with simple software and simple low-cost hardware. The skin color face detection algorithm was tested using 133 images from the People Image Groups dataset, which contains about 2573 color images of people, to test the proposed system. based on the obtained results, the best precision achieved of the proposed Skin Color face detection algorithm was 85%

Files

AJMAS-051215225.pdf

Files (773.4 kB)

Name Size
md5:0dad2307a9ddd4165a9104d44a31585f
773.4 kB Preview Download