Gender recognition based on hand thermal characteristic

Abstract

Automatic gender recognition is one of the frequently solved tasks in computer vision. It is useful for analysing human behaviour, intelligent monitoring, or security. In this article, gender is recognized based on multispectral images of the hand. Hand images (palm and back) are obtained in the visible spectrum and thermal spectrum; then a fusion of images is performed. Some studies say that it is possible to distinguish male and female hands by some geometric features of the hand. The aim of this article is to determine whether it is possible to recognize gender by the thermal characteristics of the hand and at the same time, to find the best architecture for this recognition. The article compares several algorithms that can be used to resolve this issue. The Convolutional Neural Network - AlexNet is used for features extraction. Support Vector Machine (SVM), Linear Discriminant, Naive Bayes Classifier, and Neural Networks were used for subsequent classification. Only CNNs were used for both extraction and subsequent classification. All of these methods lead to the high accuracy of gender recognition. However, the most accurate are the Convolutional Neural Networks VGG-16 and VGG-19. The accuracy of gender recognition (test data) is 94.9% for the palm and 89.9% for the back. Experiments in comparative studies have shown promising results and have shown that multispectral hand images (thermal and visible) can be beneficial in gender recognition.