Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (4): 1184-1190.DOI: 10.11772/j.issn.1001-9081.2019091552

• Virtual reality and multimedia computing • Previous Articles     Next Articles

No-reference image quality assessment method for facial beautification image

ZHANG Junsheng, XU Jingjing, YU Wei   

  1. School of Information and Control Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221000, China
  • Received:2019-09-09 Revised:2019-10-11 Online:2020-04-10 Published:2019-10-21
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China(61771473),the Natural Science Foundation of Jiangsu Province(BK20181354).

面部美化图像质量无参考评价方法

张俊升, 徐晶晶, 余伟   

  1. 中国矿业大学 信息与控制工程学院, 江苏 徐州 221000
  • 通讯作者: 张俊升
  • 作者简介:张俊升(1995-),男,安徽宿州人,硕士研究生,主要研究方向:图像美学、图像质量评价;徐晶晶(1993-),女,安徽宿州人,硕士研究生,主要研究方向:图像情感分析、图像显著性检测;余伟(1993-),男,四川乐山人,硕士研究生,主要研究方向:图像质量评价、深度学习。
  • 基金资助:
    国家自然科学基金资助项目(61771473);江苏省自然科学基金资助项目(BK20181354)。

Abstract: In view of the fact that facial beautification has been widely studied,but the lack of effective beautification image quality evaluation methods limits the further development of beautification technology,a no-reference evaluation method for facial beautification image quality was proposed. In this method,the facial cognition and perception were combined with the facial beautification technologies to unearth the quality representation of beautified images. Firstly,a facial beautification image database was constructed,the facial image was decomposed to three areas:skin,eyes and mouth. Then,facial aesthetic features were extracted from five aspects:skin color,smoothness,illumination,grayscale difference and sharpness. Finally,Support Vector Regression(SVR)was used to train the facial beautification quality model and predict the quality of the beautified image. The experimental results show that the proposed method achieves 0. 920 5 and 0. 900 9 respectively in the Pearson linear correlation coefficient and Spearman RankOrder Correlation Coefficient(SROCC) on the proposed database,which are higher than those of image quality evaluation methods BIQI(Blind Image Quality Indices),and NIQE(Natural Image Quality Evaluation).

Key words: computer vision, image quality assessment, no reference, feature extraction, machine learning

摘要: 针对目前面部美化已被广泛研究,然而缺乏有效美化图像质量评价方法限制美化技术进一步发展的问题,提出一种面部美化图像质量的无参考评价方法。该方法结合面部美感的认知与感知和面部美化技术以挖掘美化图像的质量表示,首先构建面部美化图像数据库,将面部图像分解为皮肤、眼睛和嘴巴三种区域,然后从肤色、光滑度、光照、灰度差和清晰度等五个方面提取面部美学特征,最后用支持向量回归(SVR)训练面部美化质量模型并预测美化图像的质量。实验结果表明,所提方法在构建的数据库上Pearson线性相关系数和Spearman等级相关系数分别达到0.920 5和0.900 9,优于BIQI(Blind Image Quality Indices)、NIQE(Natural Image Quality Evaluation)图像质量评价方法。

关键词: 计算机视觉, 图像质量评价, 无参考, 特征提取, 机器学习

CLC Number: