A Novel Framework for Assessing Facial Attractiveness Based on Facial Proportions

Abstract

Abstract:In this paper, we present a novel framework for automatically assessing facial attractiveness that considers four ratio feature sets as objective elements of facial attractiveness. In our framework, these feature sets are combined with three regression-based predictors to estimate a facial beauty score. To enhance the system's performance to make it comparable with human scoring, we apply a score fusion technique. Experimental results show that the attractiveness score obtained by the proposed framework better correlates with human assessments than the scores from other predictors. The framework's modularity allows any features or predictors to be integrated into the facial attractiveness measure. Our proposed framework can be applied to many beauty-related fields, such as the plastic surgery, cosmetics, and entertainment industries.

Facial Beauty Prediction and Analysis based on Deep Convolutional Neural Network: A Review

“…• Multi-Modality Beauty (M2B) dataset: It comprises audio files, dressing images, and facial images of 1240 females. These images were ranked using different scores within an interval [1][2][3][4][5][6][7][8][9][10]. They were grouped into two ethnics: easterners and westerners (each group comprised 620 persons).…”

“…These had been validated based on self-consistency, consistency, standard deviation, and rating distribution. The beauty scores (rankings) fell within an interval of [1][2][3][4][5], resulting from an average of diverse scores. The scores were generated from 75 persons through a web-based device, taking 70 raters per image as an average [19], [20], [22].…”

“…

There is a growing interest in the automatic human-like Facial Attractiveness Prediction (FAP) or Face Beauty Prediction (FBP) amidst the domain of machine learning and computer vision. This is expected to have wider application cases, including make-up evaluation, facial image beautification, content-based face retrieval, and social network recommendation systems, cosmetic recommendation, aesthetic surgery planning, entertainment, photo retouching, and among others [1],[2], [3]. Psychology research displayed a consistent beauty perception amidst diverse people.

…”

Avaliação volumétrica da face: validação do sistema de captação de imagem facial tridimensional pela tecnologia de luz estruturada, estudo em cadáver

“…Esse processo teve duração de cerca de 1 minuto. Linear (3) Linear (6) Linear (10) expansor preenchido com 03 mL azul; 06 mL vermelho e 10 mL verde, demonstrando a correlação linear com declive positivo existente com o expansor sendo colocado no lado direito da face. Desse modo, o fato da malha 3D propiciar a captura de variações na superfície em coordenadas tridimensionais e não exclusivamente em representações pictóricas torna-a capaz de oferecer medições e informações matemáticas da conformação do objeto.…”

“…Informações adicionais disponíveis em https://www.github.com/cogitas3d/OrtogOnBlender 10. Informações adicionais disponíveis em https://www.github.com/cogitas3d/RhinOnBlender.…”