Is principal component analysis an effective tool to predict face attractiveness? A contribution based on real 3D faces of highly selected attractive women, scanned with stereophotogrammetry

The True Appearance Behind Satisfaction in Young Women: A Study Using Stereophotogrammetry and FACE-Q

This cross-sectional observational study aimed to investigate the relationship between satisfaction with facial appearance among young women, as measured by the FACE-Q tool, and facial asymmetry quantified through stereophotogrammetry. A total of 50 women aged 18 to 30 years with a normal body mass index were recruited for the study. Participants were categorized as either symmetrical or asymmetrical based on facial asymmetry assessments obtained through clinical examination and stereophotogrammetry using the Vectra M3 system. Facial asymmetry was quantified using root mean square (RMS) distances, with participants classified into symmetrical (RMS ≤0.68) and asymmetrical (RMS >0.68) groups. The statistical analysis included the intraclass correlation coefficient (ICC) to assess the repeatability of RMS measurements (ICC=0.945), Receiver operating characteristic (ROC) curve analysis (area under the curve=0.900), and independent t tests to compare FACE-Q scores between groups. Results showed no significant differences in FACE-Q satisfaction scores between the symmetrical and asymmetrical groups. In addition, simple linear regression analysis indicated that RMS values were not predictive of FACE-Q scores, suggesting that facial asymmetry, as measured in this study, did not have a direct effect on self-reported satisfaction with appearance. These findings highlight the nuanced nature of individual satisfaction with facial appearance, suggesting that health care providers should combine clinical evaluation with empathetic communication to address both the aesthetic and functional concerns of patients more effectively.

Unsupervised inference approach to facial attractiveness

The perception of facial attractiveness is a complex phenomenon which depends on how the observer perceives not only individual facial features, but also their mutual influence and interplay. In the machine learning community, this problem is typically tackled as a problem of regression of the subject-averaged rating assigned to natural faces. However, it has been conjectured that this approach does not capture the complexity of the phenomenon. It has recently been shown that different human subjects can navigate the face-space and "sculpt" their preferred modification of a reference facial portrait. Here we present an unsupervised inference study of the set of sculpted facial vectors in such experiments. We first infer minimal, interpretable and accurate probabilistic models (through Maximum Entropy and artificial neural networks) of the preferred facial variations, that encode the inter-subject variance. The application of such generative models to the supervised classification of the gender of the subject that sculpted the face reveals that it may be predicted with astonishingly high accuracy. We observe that the classification accuracy improves by increasing the order of the non-linear effective interaction. This suggests that the cognitive mechanisms related to facial discrimination in the brain do not involve the positions of single facial landmarks only, but mainly the mutual influence of couples, and even triplets and quadruplets of landmarks. Furthermore, the high prediction accuracy of the subjects' gender suggests that much relevant information regarding the subjects may influence (and be elicited from) their facial preference criteria, in agreement with the multiple motive theory of attractiveness proposed in previous works.

A Fast and Low-Cost Human Body 3D Scanner Using 100 Cameras

The human body is one of the most complicated objects to model because of its complex features, non-rigidity, and the time required to take body measurements. Basic technologies available in this field range from small and low-cost scanners that must be moved around the body to large and high-cost scanners that can capture all sides of the body simultaneously. This paper presents an image-based scanning system which employs the structure-from-motion method. The design and development process of the scanner includes its physical structure, electronic components, and the algorithms used for extracting 3D data. In addition to the accuracy, which is one of the main parameters to consider when choosing a 3D scanner, the time and cost of the system are among the most important parameters for evaluating a scanner system in the field of human scanning. Because of the non-static nature of the human body, the scanning time is particularly important. On the other hand, a high-cost system may lead to limited use of such systems. The design developed in this paper, which utilizes 100 cameras, facilitates the acquisition of geometric data in a fraction of a second (0.001 s) and provides the capabilities of large, freestanding scanners at a price akin to that of smaller, mobile ones.

Subjectivity and complexity of facial attractiveness

The origin and meaning of facial beauty represent a longstanding puzzle. Despite the profuse literature devoted to facial attractiveness, its very nature, its determinants and the nature of inter-person differences remain controversial issues. Here we tackle such questions proposing a novel experimental approach in which human subjects, instead of rating natural faces, are allowed to efficiently explore the face-space and "sculpt" their favorite variation of a reference facial image. The results reveal that different subjects prefer distinguishable regions of the face-space, highlighting the essential subjectivity of the phenomenon. The different sculpted facial vectors exhibit strong correlations among pairs of facial distances, characterising the underlying universality and complexity of the cognitive processes, and the relative relevance and robustness of the different facial distances.

Art or Science? An Evidence-Based Approach to Human Facial Beauty a Quantitative Analysis Towards an Informed Clinical Aesthetic Practice

BACKGROUND

Patients often seek guidance from the aesthetic practitioners regarding treatments to enhance their 'beauty'. Is there a science behind the art of assessment and if so is it measurable? Through the centuries, this question has challenged scholars, artists and surgeons.

AIMS AND OBJECTIVES

This study aims to undertake a review of the evidence behind quantitative facial measurements in assessing beauty to help the practitioner in everyday aesthetic practice.

METHODS

A Medline, Embase search for beauty, facial features and quantitative analysis was undertaken.

SELECTION CRITERIA

Inclusion criteria were studies on adults, and exclusions included studies undertaken for dental, cleft lip, oncology, burns or reconstructive surgeries. The abstracts and papers were appraised, and further studies excluded that were considered inappropriate. The data were extracted using a standardised table. The final dataset was appraised in accordance with the PRISMA checklist and Holland and Rees' critique tools.

RESULTS

Of the 1253 studies screened, 1139 were excluded from abstracts and a further 70 excluded from full text articles. The remaining 44 were assessed qualitatively and quantitatively. It became evident that the datasets were not comparable. Nevertheless, common themes were obvious, and these were summarised.

CONCLUSION

Despite measures of the beauty of individual components to the sum of all the parts, such as symmetry and the golden ratio, we are yet far from establishing what truly constitutes quantitative beauty. Perhaps beauty is truly in the 'eyes of the beholder' (and perhaps in the eyes of the subject too).

LEVEL OF EVIDENCE V

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Application of off-the-shelf stereo-cameras for the 3D assessment of morphometric variations caused by rhinoplasty

The present paper shows how a non-invasive and low-cost photogrammetric stereo device allows the assessment of morphometric variations of the nose following rhinoplasty. Six female patients, aged between 24 and 37 years, underwent 3D stereo-photogrammetric scanning. Three-dimensional computerised models were generated, extracting also information related to the coordinates of facial landmarks, distances between landmarks, angles, in pre- and postoperative situation. Two kinds of analysis were carried out: (i) statistical correlation between size variations and (ii) morphometric analysis, including General Procrustes Analysis (GPA), Principal Components Analysis (PCA) and Warping. The study shows the usefulness of the stereo-photogrammetric facial digitisation for morphometric analysis of the human face. Three-dimensional computerised models are also an important tool for the assessment of the surgeon's performance in the event of dispute between doctor and patient. Moreover, confirmation of the PCA as an analytical tool for the identification of components characterising the morphometric structure of the nose is highlighted.

A three-dimensional photogrammetric analysis of the facial esthetics of the Miss Korea pageant contestants

Objective

The aims of this study were to measure and compare the facial dimensions of the Miss Korea pageant contestants and a selected group of women from the general population by using three-dimensional (3D) image analysis, as well as to compare various facial ratios to the golden ratio within each group.

Methods

Three-dimensional images of 52 Miss Korea pageant contestants (MK group) and 41 young female adults selected from the general population (GP group) were acquired. Fifty-four variables and ratios were measured and calculated. Intergroup comparisons were performed using multivariate analysis of variance.

Results

Compared to the GP group, the MK group showed greater total facial height and eye width, lesser lower-facial height, and lesser facial, lower-facial, and nasal widths. Moreover, compared to the GP group, the MK group had more protruded noses with greater nasolabial angle, greater vertical curvature of the foreheads, lesser horizontal curvature of the cheek, and lesser lower-lip-and-chin volume.

Conclusions

The MK group had longer faces but smaller lower lips and chins than did the GP group. The golden ratio was not matching the current facial esthetic standards. These data might be beneficial for treatment planning of patients undergoing orthognathic and plastic surgeries.

Three-Dimensional Anthropometric Database of Attractive Caucasian Women: Standards and Comparisons

The aim of this paper is to develop a database to determine a new biomorphometric standard of attractiveness. Sampling was carried out using noninvasive three-dimensional relief methods to measure the soft tissues of the face. These anthropometric measurements were analyzed to verify the existence of any canons with respect to shape, size, and measurement proportions which proved to be significant with regard to the aesthetics of the face. Finally, the anthropometric parameters obtained were compared with findings described in the international literature.

The study sample was made up competitors in the Miss Italy 2010 and 2009 beauty contest. The three-dimensional (3D) scanning of soft tissue surfaces allowed 3D digital models of the faces and the spatial 3D coordinates of 25 anthropometric landmarks to be obtained and used to calculate linear and angular measurements. A paired Student t test for the analysis of the means allowed 3 key questions in the study of biomorphometric parameters of the face to be addressed through comparison with the data available in the literature.

The question of statistical evidence for the samples analyzed being members of the populations samples reported in literature was also addressed.

The critical analysis of the data helped to identify the anthropometric measurements of the upper, middle, and lower thirds of the face, variations in which have a major influence on the attractiveness of the face. These changes involve facial width, height, and depth. Changes in measurements of length, angles, and proportions found in the sample considered were also analyzed.

Nasal or canthal-alar parentheses: A study of the facial base of the nose

OBJECTIVES

The facial implantation of the osseous nasal pyramid corresponds to the piriform aperture, the shape of which is projected on the facial skin in the form of bracket-shaped parentheses. The objective of this study was to compare inter-parenthesis width with subjective visibility on frontal photographs.

MATERIAL AND METHODS

The "patient" group came from a retrospective cohort of photographs taken ahead of septorhinoplasty. The "model" group photographs were collected from the Web or magazines. Nasal parentheses were first judged subjectively as frank or faint. Then, independently, parenthesis width was measured by computer in pixels and converted into millimeters by iris-dependent calibration. Inter-parenthesis width was compared statistically with the frank/faint assessment, according to gender and group.

RESULTS

A total of 113 photographs were included: 46 patients (19 women, 27 men) and 67 models (43 women, 24 men). Sixty-seven of the 113 nasal parentheses appeared frank (59.3%), more frequently in men than women (70.6% vs 50.0%, P=0.02) and in patients than models (69.6% vs 52.2%, P=0.06). Inter-parenthesis width was significantly greater in frank than faint presentations (34.9±3.5mm vs 30.7±3.4mm, P<0.0001), in men than women (35.2±4.1mm vs 31.5±3.1mm, P<0.0001), and in patients than models (34.9±4.0mm vs 32.0±3.6mm, P<0.0001).

CONCLUSION

Frank nasal parentheses correspond to wider facial implantation of the nose.