Toward graph-based semi-supervised face beauty prediction

Assessing beauty using facial images analysis is an emerging computer vision problem. To the best of our knowledge, all existing methods for automatic facial beauty scoring rely on fully supervised schemes. In this paper, we introduce the use of semi-supervised learning schemes for solving the probl...

Descripción completa

Detalles Bibliográficos
Autores: Dornaika, Fadi, Wang, Kunwei, Arganda Carreras, Ignacio, Elorza Deias, Anne, Moujahid, Abdelmalik
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:dnet:addi________::590328dd4099d2abc405fa37af4a0381
Acceso en línea:http://hdl.handle.net/10810/78684
Access Level:acceso abierto
Palabra clave:image-based face beauty analysis
graph-based semi-supervised learning
graph-based label propagation
deep face features
Descripción
Sumario:Assessing beauty using facial images analysis is an emerging computer vision problem. To the best of our knowledge, all existing methods for automatic facial beauty scoring rely on fully supervised schemes. In this paper, we introduce the use of semi-supervised learning schemes for solving the problem of face beauty scoring when the image descriptor is holistic and the score is given by a real number. The paper has two main contributions. Firstly, we introduce the use of graph-based semi-supervised learning for face beauty scoring. The proposed method is based on texture and utilizes continuous scores in a full range. Secondly, we adapt and kernelize an existing linear Flexible Manifold Embedding scheme (that works with discrete classes) to the case of real scores propagation. The resulting model can be used for transductive and inductive settings. The proposed semi-supervised schemes were evaluated on three recent public datasets for face beauty analysis: SCUT-FBP, M 2 B, and SCUT-FBP5500. The obtained experimental results, as well as many comparisons with fully supervised methods, demonstrate that the non-linear semi-supervised scheme compares favorably with many supervised schemes. The proposed semi-supervised scoring framework paves the way to virtually all applications to adopt continuous scores instead of the usual discrete labels.