Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (12): 3607-3611.DOI: 10.11772/j.issn.1001-9081.2018051040

Previous Articles     Next Articles

Facial attractiveness evaluation method based on fusion of feature-level and decision-level

LI Jinman1, WANG Jianming1,2, JIN Guanghao2   

  1. 1. School of Electronics and Information Engineering, Tianjin Polytechinic University, Tianjin 300387, China;
    2. School of Computer Science and Technology, Tianjin Polytechinic University, Tianjin 300387, China
  • Received:2018-05-21 Revised:2018-08-27 Online:2018-12-10 Published:2018-12-15
  • Contact: 金光浩
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61771340, 61302127, 61403278), the Postdoctoral Science Foundation of China (2015M570228), the Tianjin Research Program of Application Foundation and Advanced Technology (15JCYBJC16600), the Natural Science Foundation of Tianjin (16JCYBJC42300), the Tianjin Higher Education Innovation Team Training Program (TD13-5032).

基于特征级和决策级融合的人脸吸引力评价方法

李金蔓1, 汪剑鸣1,2, 金光浩2   

  1. 1. 天津工业大学 电子与信息工程学院, 天津 300387;
    2. 天津工业大学 计算机科学与技术学院, 天津 300387
  • 通讯作者: 金光浩
  • 作者简介:李金蔓(1993-),女,吉林长春人,硕士研究生,主要研究方向:人脸图像处理;汪剑鸣(1974-),男,河北隆尧人,教授,博士,CCF会员,主要研究方向:计算机视觉、智能信息处理;金光浩(1979-),男,吉林延吉人,讲师,博士,CCF会员,主要研究方向:大数据分析、计算机视觉。
  • 基金资助:
    国家自然科学基金资助项目(61771340,61302127,61403278);中国博士后科学基金资助项目(2015M570228);天津市应用基础与前沿技术研究计划项目(15JCYBJC16600);天津市自然科学基金资助项目(16JCYBJC42300);天津市高等学校创新团队培养计划项目(TD13-5032)。

Abstract: In the study of personalized facial attractiveness, due to lack of features and insufficient consideration of the influence factors of public aesthetics, the prediction of personal preferences cannot reach high prediction accuracy. In order to improve the prediction accuracy, a new personalized facial attractiveness prediction framework based on feature-level and decision-level information fusion was proposed. Firstly, the objective characteristics of different facial beauty features were fused together, and the representative facial attractive features were selected by a feature selection algorithm, the local and global features of face were fused by different information fusion strategies. Then, the traditional facial features were fused with the features extracted automatically through deep networks. At the same time, a variety of fusion strategies were proposed for comparison. The score information representing the public aesthetic preferences and the personalized score information representing the individual preferences were fused at the decision level. Finally, the personalized facial attractiveness prediction score was obtained. The experimental results show that, compared with the existing algorithms for personalized facial attractiveness evaluation, the proposed multi-level fusion method has a significant improvement in prediction accuracy, and can achieve the Pearson correlation coefficient more than 0.9. The proposed method can be used in the fields of personalized recommendation and face beautification.

Key words: facial attractiveness, feature-level fusion, decision-level fusion, personalized information, consensual information

摘要: 在个性化的人脸吸引力的研究中,由于特征缺失和对于大众审美的影响因素考虑不足,导致预测个人偏好无法到达很高的预测精度。为了提高预测精度,提出了一个基于特征级和决策级信息融合的个性化人脸吸引力预测框架。首先,将代表不同人脸美丽特征的客观特性融合到一起,利用特征选择算法挑选出具有代表性的人脸吸引力特征,并利用不同的信息融合策略将人脸局部、全局特征融合起来;然后,将传统的人脸特征与通过深度网络自动提取的特征融合起来。同时,提出多种融合策略进行对比,将代表着大众审美偏好的评分信息与代表个人偏好的个性化评分信息进行决策级融合,最终实现个性化的人脸吸引力预测评分。实验结果表明,相比现有针对个性化人脸吸引力评价研究的算法,所提的多层次融合方法在预测精度方面有显著的提升,能够达到Pearson相关系数0.9以上。该方法可用于个性化推荐、人脸美化等领域。

关键词: 人脸吸引力, 特征级融合, 决策级融合, 个性化信息, 共识性信息

CLC Number: