Floor-Ladder Framework for Human Face Beautification

In this paper, we propose a Floor-Ladder Framework (FLN) based on age evolution rules to generate beautified human faces. Beside the shape of faces, younger faces achieve more attractiveness. Thus we process the beautiful face by applying the reversed aging rules. Inspired by the layered optimization methods, the FLN adopts three floors and each floor contains two ladders: the Single Layer Older Neural Network (SLONN) and the extended Skull Model. The Peak Shift algorithm is designed to train the SLONN aiming to capture the reversed aging rules of the face skin. Due to the growth rules of the face shape, we extended the Skull Model by adding Marquardt Mask. Given the input portrait, our algorithm effectively produces a beautified human face without losing personal features.

[1]  Xiaochun Cao,et al.  Makeup Like a Superstar: Deep Localized Makeup Transfer Network , 2016, IJCAI.

[2]  David Zhang,et al.  Quantitative analysis of human facial beauty using geometric features , 2011, Pattern Recognit..

[3]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[4]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[5]  Jian Sun,et al.  Face Alignment by Explicit Shape Regression , 2012, International Journal of Computer Vision.

[6]  Timothy F. Cootes,et al.  Toward Automatic Simulation of Aging Effects on Face Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Hang-Bong Kang,et al.  A new digital face makeup method , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[8]  Karl Ricanek,et al.  A hierarchical approach to facial aging , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Tien D. Bui,et al.  Beyond Principal Components: Deep Boltzmann Machines for face modeling , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yu Liu,et al.  Learning Relaxed Deep Supervision for Better Edge Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Timo Bolkart,et al.  A Groupwise Multilinear Correspondence Optimization for 3D Faces , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Shuicheng Yan,et al.  "Wow! You Are So Beautiful Today!" , 2014, ACM Trans. Multim. Comput. Commun. Appl..

[14]  Nicu Sebe,et al.  Recurrent Face Aging , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Honglak Lee,et al.  Object Contour Detection with a Fully Convolutional Encoder-Decoder Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Xuelong Li,et al.  Facial Skin Beautification Using Adaptive Region-Aware Masks , 2014, IEEE Transactions on Cybernetics.

[17]  Dong Guo,et al.  Digital face makeup by example , 2009, CVPR.

[18]  Ira Kemelmacher-Shlizerman,et al.  Illumination-Aware Age Progression , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Shuicheng Yan,et al.  Deep Face Beautification , 2015, ACM Multimedia.

[20]  Xiaoou Tang,et al.  Deep Cascaded Bi-Network for Face Hallucination , 2016, ECCV.

[21]  Tien D. Bui,et al.  Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Hanjiang Lai,et al.  Personalized Age Progression with Aging Dictionary , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Dani Lischinski,et al.  Data-driven enhancement of facial attractiveness , 2008, SIGGRAPH 2008.

[24]  J. B. Pittenger,et al.  The perception of human growth. , 1980, Scientific American.

[25]  Yuting Zhang,et al.  Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).