Geometric prior guided hybrid deep neural network for facial beauty analysis  

作　　者：Tianhao Peng Mu Li Fangmei Chen Yong Xu David Zhang 

机构地区：[1]The School of Computer Science and Technology,Guizhou University,Guiyang,China [2]Department of Automation,Moutai Institute,Renhuai,Guizhou,China [3]The School of Computer Science and Technology,Harbin Institute of Technology,Shenzhen,Shenzhen,China [4]The Information and Communication Engineering Department,Dalian Minzu University,Dalian,China [5]The School of Data Science,The Chinese University of Hong Kong,Shenzhen,Shenzhen,China

出　　处：《CAAI Transactions on Intelligence Technology》2024年第2期467-480,共14页智能技术学报（英文）

基　　金：Shenzhen Science and Technology Program,Grant/Award Number:ZDSYS20211021111415025;Shenzhen Institute of Artificial Intelligence and Robotics for Society;Youth Science and Technology Talents Development Project of Guizhou Education Department,Grant/Award Number:QianJiaoheKYZi[2018]459。

摘　　要：Facial beauty analysis is an important topic in human society.It may be used as a guidance for face beautification applications such as cosmetic surgery.Deep neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable performance.However,most existing DNN-based models regard facial beauty analysis as a normal classification task.They ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty analysis.To be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the decision.Inspired by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial parts.Additionally,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two branches.In model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric features.Experiments performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid network.To the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

关 键 词：deep neural networks face analysis face biometrics image analysis 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]