Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

Dat Nguyen,Min Kim,Ki Kim,Ja Koo,Kang Park,Hyung Hong

doi:10.3390/s17030637

Abstract

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Highlights

Surveillance systems have become highly popular and have many useful applications.A common application of surveillance systems is remote video monitoring in private houses, businesses, or outdoor environments [1,2,3] to monitor the premises and/or to prevent crime, as well as for monitoring the people who enter or leave
To overcome the limitations of the predesigned feature extractors, we propose a new gender recognition method that uses a more suitable feature extractor based on a convolutional neural network (CNN)
The remaining sections of this paper are organized as follows: in Section 2, we describe the overall procedure of our proposed gender recognition method using CNN for image feature extraction and support vector machine (SVM) for gender recognition

Summary

Introduction

A common application of surveillance systems is remote video monitoring in private houses, businesses, or outdoor environments [1,2,3] to monitor the premises and/or to prevent crime, as well as for monitoring the people who enter or leave. This type of information is important for security purposes. The gender information of a person is an important feature in surveillance systems [4,5]

Methods

Results

Conclusion