计算机工程 ›› 2019, Vol. 45 ›› Issue (8): 224-229.doi: 10.19678/j.issn.1000-3428.0051535

• 人工智能及识别技术 • 上一篇    下一篇

融合主观性与共识性信息的人脸吸引力预测

李金蔓a, 汪剑鸣b, 金光浩b   

  1. 天津工业大学 a. 电子与信息工程学院;b. 计算机科学与技术学院, 天津 300387
  • 收稿日期:2018-05-14 修回日期:2018-06-21 出版日期:2019-08-15 发布日期:2018-06-25
  • 作者简介:李金蔓(1993-),女,硕士研究生,主研方向为模式识别、计算机视觉;汪剑鸣,教授、博士;金光浩(通信作者),讲师、博士。
  • 基金项目:
    国家自然科学基金(61771340,61302127,61403278);中国博士后科学基金(2015M570228);天津市自然科学基金(16JCYBJC4 2300);天津市应用基础与前沿技术研究计划(15JCYBJC16600);天津市高等学校创新团队培养计划(TD13-5032)。

Facial Attractiveness Prediction Integrating Subjective and Consensus Information

LI Jinmana, WANG Jianmingb, JIN Guanghaob   

  1. a. School of Electronics and Information Engineering;b. School of Computer Science and Technology, Tianjin Polytechnic University, Tianjin 300387, China
  • Received:2018-05-14 Revised:2018-06-21 Online:2019-08-15 Published:2018-06-25

摘要: 为对特定对象的个性化审美偏好进行预测,将机器学习与深度学习相结合,提出融合共识性与主观性偏好信息的个性化人脸吸引力评估方法。从数据集中收集群体评分形成共识性信息,构建个人评分预测模型以反映主观性信息。结合这2种信息并发挥共识性信息的普遍性优势以及主观性信息的独特性,从而构建个性化人脸吸引力预测模型。在公开的SCUT-FBP和FaceScrub数据集上进行实验,结果表明,该方法的Pearson相关系数高达0.90,残差值低至0.25。

关键词: 特征融合, 个性化预测, 人脸吸引力, 共识性信息, 主观性信息, Pearson相关系数

Abstract: In order to predict the personalized aesthetic preferences of specific objects,machine learning and depth learning are combined,and a personalized facial attractiveness evaluation method that integrating consensus and subjective preference information is proposed.Group ratings are collected from the data set to form consensus information,and the prediction model of individual ratings is constructed to reflect subjective information.Combining these two kinds of information and giving full play to the universality of consensus information and the uniqueness of subjective information,a personalized facial attractiveness prediction model is constructed.Experiments on open SCUT-FBP and FaceScrub datasets show that the Pearson correlation coefficient of this method is as high as 0.90 and the residual value is only 0.25.

Key words: feature integration, personalized prediction, facial attractiveness, consensus information, subjective information, Pearson correlation coefficient

中图分类号: