Supervisory Committee:
Drs. O. Ahmad, M. Kersten-Oertel, Y. Yan
Title: Facial Beauty Analysis Based on Computer Vision and Deep Learning Techniques
Date: Tuesday, March 31, 2020
Time: 13:30
Place: Via Zoom teleconference
ABSTRACT
Analysis of facial beauty has become an emerging research topic in recent years, and has fascinated researchers from various fields. The objective of facial beauty prediction is to develop a human-like model that automatically evaluates facial attractiveness.
Our research aims to provide new frameworks to analyze the attractiveness of human faces. First, two geometric facial measurements, including ratios and angles, as well as a stacking ensemble model are employed to predict female face attractiveness. Second, we introduce a new framework to analyze the attractiveness of female faces using transfer learning methodology as well as stacking ensemble model. Moreover, this study provides a new deep framework for simultaneous facial beauty assessment, gender recognition as well as ethnicity identification. Furthermore, a component-based facial beauty predictor is presented where specific regions of face images as well as the whole face are leveraged to evaluate beauty. Interestingly, our experimental results on the SCUT-FBP and SCUT- FBP5500 benchmark datasets indicate significant improvement in accuracy over the other state-of-the-art methods.