A new face feature point matrix based on geometric features and illumination models for facial attraction analysis

Jian Zhao; Fang Deng; Jian Jia; Chunmeng Wu; Haibo Li; Yuan Shi; Shunli Zhang

doi:10.3934/dcdss.2019073

Article Contents

2019, Volume 12, Issue 4&5: 1065-1072. Doi: 10.3934/dcdss.2019073 open access

This issue Previous Article Major project risk assessment method based on BP neural network Next Article A dynamical system study for the ecological development of mineral resources in minority areas

A new face feature point matrix based on geometric features and illumination models for facial attraction analysis

School of Information Science and Technology, Northwest University, Xi'an, China

* Corresponding author: Jian Zhao
* Corresponding author: Jian Zhao

Received: June 30, 2017

Revised: November 30, 2017

Published: March 2019

The first author is supported by the National Natural Science Foundation of China grant 61379010, 61772421

Abstract Full Text(HTML) Figure(5) / Table(2) Related Papers Cited by

Abstract

In this paper, we propose a 81-point face feature points template that used for face attraction analysis. This template is proposed that based on the AAM model, according to the geometric characteristics and the illumination model. The experimental results demonstrate that, the attraction of human face can be analyzed by the feature vector analysis of human face image quantification and the influence of light intensity on the attraction of human face. By taking the appropriate algorithm, the concept of facial beauty attractiveness can be learned by machine with numeric expressions.

Keywords:

Mathematics Subject Classification: 68T01.

Citation:

FullText(HTML)

Figure 1. 68 feature points detected face map

Download: Full-size image PowerPoint slide

Figure 2. 7-dimensional geometric features

Download: Full-size image PowerPoint slide

Figure 3. The feature points of the geometric features in this paper

Download: Full-size image PowerPoint slide

Figure 4. The feature point diagram of the illumination model

Download: Full-size image PowerPoint slide

Figure 5. Improved light intensity map

Download: Full-size image PowerPoint slide

Table 1. 7-dimensional distance feature vector description.

Feature quantity number	Feature quantity symbol	Feature quantity description
1	F1	Nose and ears width (nose up to the top of the ear)
4	F4	Nose to the height of the forehead center
5	F5	Nose to the eyes of the angle
6	F6	Forehead center to the side of the distance
7	F7	The distance on both sides of the forehead

| Show Table

DownLoad: CSV

Table 2. The slope of the nose of the ears

Experimental sample	Slope 1	Slope 2	Difference
1	0.0280	0.0399	-0.0119
3	0.0196	-0.0402	0.0598
4	-00476	-0.0562	0.0086
5	0.0840	0.0224	0.0616
6	0.1369	0.1168	0.0201

| Show Table

DownLoad: CSV

Related Papers

Cited by

References

[1]	A. Asthana, S. Zafeiriou, S. Cheng and M. Pantic, Robust discriminative response map fitting with constrained local models, IEEE Conference on Computer Vision and Pattern Recognition, (2013), 3444-3451.
[2]	R. Basri and D. W. Jacobs, Lambertian reflectance and linear subspaces, IEEE Transactions on Pattern Analysis & Machine Intelligence, 25 (2003), 218-233.
[3]	F. Chen and D. Zhang, A benchmark for geometric facial beauty study, Lecture Notes in Computer Science, 6165 (2010), 21-32.
[4]	Y. Cheon and D. Kim, Natural facial expression recognition using differential-AAM and manifold learning, Pattern Recognition, 42 (2009), 1340-1350.
[5]	T. F. Cootes, G. J. Edwards and C. J. Taylor, Active appearance models, European Conference on Computer Vision, (2001), 484-498.
[6]	J. H. Langlois and L. A. Roggman, Attractive Faces Are Only Average, Psychological Science, 1 (1990), 115-121.
[7]	X.-F. Lu, Chinese research facial pattern types and techniques, China Academy of Fine Arts doctoral dissertation, 2010.
[8]	X.-F. Lu, Yuan Dynasty painter Wang Yi's "writing like a secret" and portrait program, Fine Arts., 18 (2005), 72-73.
[9]	H.-Y. Mao, Facial beauty attractive characteristics of the analysis and machine learning, South China University of Technology, 2011.
[10]	I. Matthews and S. Baker, Active appearance models revisited, International Journal of Computer Vision, 6165 (2004), 135-164.
[11]	S. C. Rhee and S. H. Koo, An objective system for measuring facial attractiveness, Plastic & Reconstructive Surgery, 119 (2006), 1953-1954.
[12]	A. J. Rubenstein, J. H. Langlois and L. A. Roggman, What makes a face attractive and why: The role of averageness in defining facial beauty, G Rhodes & L 62 Zebrowitz, Facial Attractiveness: Evolutionary, Cognitive, & Social Perspectives, 2002.
[13]	Y. Sato, M. D. Wheeler and K. Ikeuchi, Object Shape and Reflectance Modeling from Observation, Modeling from Reality. Springer US, (2001), 95-116.
[14]	G. Tzimiropoulos and M. Pantic, Optimization Problems for Fast AAM Fitting in-the-Wild, IEEE International Conference on Computer Vision, (2014), 593-600.
[15]	X.-M. Zhang, China United States, Beijing: Xinhua Publishing House, 2005.