Toward graph-based semi-supervised face beauty prediction
作者：
Highlights：
• A graph-based semi-supervised learning scheme is introduced for face beauty prediction.
• The introduced scheme is the first approach that performs beauty score propagation.
• The method is based on the use of face texture and continuous scores.
• Performance is assessed on three public datasets.
• Performance is assessed using supervised and semi-supervised schemes.
摘要
•A graph-based semi-supervised learning scheme is introduced for face beauty prediction.•The introduced scheme is the first approach that performs beauty score propagation.•The method is based on the use of face texture and continuous scores.•Performance is assessed on three public datasets.•Performance is assessed using supervised and semi-supervised schemes.
论文关键词：Image-based face beauty analysis,Graph-based semi-supervised learning,Graph-based label propagation,Deep face features,
论文评审过程：Received 18 February 2019, Revised 25 September 2019, Accepted 27 September 2019, Available online 5 October 2019, Version of Record 11 October 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.112990
