Abstract
In this work we study the interrelation between, on the one hand, subjective perception of female facial aesthetics, and on the other hand, selected objective parameters that include facial features, photo-quality, as well as non-permanent facial characteristics. This study seeks to provide insight on the role of this specific set of features in affecting the way humans perceive facial images. The approach is novel in that it jointly considers both previous results on photo quality and beauty assessment, as well as non-permanent facial characteristics and expressions. Based on 37 such objective parameters, we construct a metric that aims to quantify modifiable parameters for aesthetics enhancement, as well as tunes systems that would seek to predict the way humans perceive facial aesthetics. The proposed metric is evaluated on a face dataset, that includes images with variations in illumination, image quality, as well as age, ethnicity and expression. We show that our approach outperforms two state of the art beauty estimation metrics. In addition we apply the designed metric in three interesting datasets, where we assess beauty in images of females before and after plastic surgery, of females across time, as well as of females famous for their beauty. We conclude by giving insight towards beauty prediction.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.