A hybrid approach to building face shape classifier for hairstyle recommender system
作者：
Highlights：
• A hairstyle recommender system that follows an expert’s guidelines using face shape.
• A set of geometric features for face shape identification is introduced.
• A new face shape open-dataset is created.
• Classifying face shape using a pre-trained model from a face recognition task.
• Fusing hand-crafted and deep features by multiple kernel learning to improve results.
摘要
•A hairstyle recommender system that follows an expert’s guidelines using face shape.•A set of geometric features for face shape identification is introduced.•A new face shape open-dataset is created.•Classifying face shape using a pre-trained model from a face recognition task.•Fusing hand-crafted and deep features by multiple kernel learning to improve results.
论文关键词：Face shape classification,Deep-learned feature,Hand-crafted feature,Hybrid feature-based approach,Feature combination
论文评审过程：Received 12 March 2018, Revised 12 September 2018, Accepted 6 November 2018, Available online 6 November 2018, Version of Record 16 November 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.011
