CelebHair: A New Large-Scale Dataset for Hairstyle Recommendation based on CelebA

TL;DR

This paper introduces CelebHair, a large-scale dataset derived from CelebA, with additional facial features and deep learning-based hairstyle classification, aiming to improve hairstyle recommendation systems.

Contribution

The paper presents CelebHair, a new extensive dataset with enhanced facial features and demonstrates its superiority over existing datasets for hairstyle recommendation tasks.

Findings

CelebHair outperforms existing datasets in variety, veracity, and volume.

Deep CNNs effectively classify hairstyles using the dataset.

The dataset proves robust and useful for hairstyle recommendation research.

Abstract

In this paper, we present a new large-scale dataset for hairstyle recommendation, CelebHair, based on the celebrity facial attributes dataset, CelebA. Our dataset inherited the majority of facial images along with some beauty-related facial attributes from CelebA. Additionally, we employed facial landmark detection techniques to extract extra features such as nose length and pupillary distance, and deep convolutional neural networks for face shape and hairstyle classification. Empirical comparison has demonstrated the superiority of our dataset to other existing hairstyle-related datasets regarding variety, veracity, and volume. Analysis and experiments have been conducted on the dataset in order to evaluate its robustness and usability.