Celeb-FBI: A Benchmark Dataset on Human Full Body Images and Age, Gender, Height and Weight Estimation using Deep Learning Approach

TL;DR

This paper introduces the Celeb-FBI dataset with full-body images and attributes like age, gender, height, and weight, and evaluates deep learning models for attribute estimation, achieving high accuracy especially with ResNet-50.

Contribution

The creation of a comprehensive full-body image dataset with detailed attributes and the evaluation of deep learning models for attribute estimation are novel contributions.

Findings

ResNet-50 achieved 79.18% accuracy for age estimation.

Gender estimation accuracy was 95.43%.

Height and weight estimation accuracies were 85.60% and 81.91%, respectively.

Abstract

The scarcity of comprehensive datasets in surveillance, identification, image retrieval systems, and healthcare poses a significant challenge for researchers in exploring new methodologies and advancing knowledge in these respective fields. Furthermore, the need for full-body image datasets with detailed attributes like height, weight, age, and gender is particularly significant in areas such as fashion industry analytics, ergonomic design assessment, virtual reality avatar creation, and sports performance analysis. To address this gap, we have created the 'Celeb-FBI' dataset which contains 7,211 full-body images of individuals accompanied by detailed information on their height, age, weight, and gender. Following the dataset creation, we proceed with the preprocessing stages, including image cleaning, scaling, and the application of Synthetic Minority Oversampling Technique (SMOTE). Subsequently, utilizing this prepared dataset, we employed three deep learning approaches: Convolutional Neural Network (CNN), 50-layer ResNet, and 16-layer VGG, which are used for estimating height, weight, age, and gender from human full-body images. From the results obtained, ResNet-50 performed best for the system with an accuracy rate of 79.18% for age, 95.43% for gender, 85.60% for height and 81.91% for weight.