Face Detection Ensemble with Methods Using Depth Information to Filter False Positives.

Loris Nanni,Sheryl Brahnam,Alessandra Lumini

doi:10.3390/s19235242

Abstract

A fundamental problem in computer vision is face detection. In this paper, an experimentally derived ensemble made by a set of six face detectors is presented that maximizes the number of true positives while simultaneously reducing the number of false positives produced by the ensemble. False positives are removed using different filtering steps based primarily on the characteristics of the depth map related to the subwindows of the whole image that contain candidate faces. A new filtering approach based on processing the image with different wavelets is also proposed here. The experimental results show that the applied filtering steps used in our best ensemble reduce the number of false positives without decreasing the detection rate. This finding is validated on a combined dataset composed of four others for a total of 549 images, including 614 upright frontal faces acquired in unconstrained environments. The dataset provides both 2D and depth data. For further validation, the proposed ensemble is tested on the well-known BioID benchmark dataset, where it obtains a 100% detection rate with an acceptable number of false positives.

Highlights

One of the most fundamental yet difficult problems in computer vision and human–computer interaction is face detection, the object of which is to detect and locate all faces within a given image or video clip
The filters reduce the number of false positives produced by the ensemble while maximizing the detection rate
A set of seven filters based on the size, the flatness, or the unevenness of the candidate face regions, or on the size of the larger cluster of the depth map of the candidate face regions, or on eye detection or the degree of ellipse fitting are evaluated, including a new method proposed here that is based on processing the candidate region with different wavelets

Summary

Introduction

One of the most fundamental yet difficult problems in computer vision and human–computer interaction is face detection, the object of which is to detect and locate all faces within a given image or video clip. Must a capable and robust face detection system overcome these difficulties, but for many of today’s applications, it must be able to do so in real time. These challenges have resulted in a large body of literature reporting different methods for tackling the problem of face detection [11]. Yang et al [12], who published a survey of face detection algorithms developed in the last century, have divided these earlier algorithms into four categories: knowledge-based methods, feature invariant approaches, template-matching methods, and appearance-based methods, the latter demonstrating some superiority compared with the other

Objectives

Methods

Results

Conclusion