Subjectivity and complexity of facial attractiveness

Study of Lip Anthropology in Young Adult Males and Females in Jazan, Saudi Arabia

BACKGROUND

The lips serve crucial functions for the face, including facial expression, speech, eating, and esthetics. Surgeons who repair or reconstruct facial deformities often rely on the anatomy and dimensions of these structures.

OBJECTIVE

This study aimed to collect diverse data on lip morphology.

DESIGN

Cross-sectional study.

SETTINGS

College of Dentistry, Jazan.

METHODS

The current study included randomly selected Saudi adults with complete dentition with ages ranging from 18 to 30 years. The lips or their surrounding areas of patients with abnormalities, malformations, deformities, inflammation, trauma, or surgical scars (cleft lip operations) were omitted.

MAIN OUTCOME MEASURES

Average lip size of male and female population in Jazan, KSA.

SAMPLE SIZE

400 (200 males and 200 females).

RESULTS

The mean height of the upper vermilion was 14.38 mm in males and 13.78 mm in females. The height of the upper lip (Sn-Sto) was measured, with males having a mean value of 24.05 ± 4.02 mm (range, 15-32 mm) and females having a mean value of 20.66 ± 4.12 mm. The difference between the sexes was statistically significant. The medial vertical height of the cutaneous lower lip (Li-SI) of females had a mean value of 10.63 ± 1.59 mm, and that of males had a mean value of 11.55 ± 2.25 mm. The height of the lower lip of males was 20.28 ± 5.2 mm and that of females was 16.95 ± 3.03 mm, and the differences were statistically significant.

CONCLUSION

Significant differences in lip measurements between males and females (indicating sexual dimorphism) were observed. Additionally, the upper vermilion tends to be thinner than the lower vermilion in both sexes, with this being the most prominent feature of the region. Furthermore, the height of the cutaneous upper lip was greater than that of the cutaneous lower lip, and the medial vertical height of the upper lip was greater than that of the lower lip in both sexes.

Forward-backward translation, content validity, face validity, construct validity, criterion validity, test-retest reliability, and internal consistency of a questionnaire on patient acceptance of orthodontic retainer

This study aimed to assess the validity and reliability of a questionnaire on patient acceptance of orthodontic retainers. The original questionnaire was forward- and backward-translated, followed by four validity tests (content validity, face validity, construct validity, criterion validity) and two reliability tests (test-retest reliability, internal consistency). Content validity was assessed by nine orthodontists who appraised the questionnaire's representativeness, relevance, clarity, and necessity. Face validity was established through semi-structured in-depth interviews with 35 English-literate participants currently wearing orthodontic retainers. Construct validity was established through Exploratory Factor Analysis (EFA). For criterion validity, 107 participants concurrently answered the questionnaire and the Retainer-modified Malaysian Oral Health Impact Profile questionnaire. Test-retest reliability was verified by 34 subjects who responded to the questionnaire again after a two-week interval. Six revised items passed the threshold value of 0.78 for Item-Content Validity Index and Content Validity Ratio and were revised based on findings from the face validity test. Principal Component Analysis of EFA extracted information on only one component, and all items were positively correlated with the component matrix. Spearman's rho value (rs = 0.490 and rs = 0.416) indicated a moderate correlation between the two questionnaires for criterion validity. Intraclass Correlation Coefficient ranged from 0.687 to 0.913, indicating moderate to excellent test-retest reliability. Cronbach's alpha ranged from 0.687 to 0.913 indicating that none of the questionnaire items showed unacceptable or poor internal consistency. The questionnaire on patient acceptance of orthodontic retainers has been validated and can be used in both clinical and research settings.

Artificial Intelligence-based Assessment of Facial Symmetry Aesthetics of Saudi Arabian Population

The purpose of this study is to investigate facial symmetry aesthetics (FSA) in the Saudi Arabian population using artificial intelligence (AI).Two hundred and ten people from a range of demographic backgrounds participated in an observational cross-sectional study that was done at a hospital. Standardized posed photos of the face and smile were taken using a Canon camera utilizing a stratified random sample approach. Webceph software (Korea) with AI was used to evaluate macro, micro, and tiny aesthetic factors. The data were analyzed using paired t-tests, post hoc Bonferroni testing, analysis of variance (ANOVA), and descriptive statistics. The computation of intraclass correlation coefficients (ICCs) was utilized to assess the dependability of AI evaluations.All variables had ICCs of more than 0.97, indicating exceptional dependability for the AI-based evaluations. Between the Class I and Class III malocclusion groups, there were significant variations in right mandibular body length (p < 0.001), with Class III patients exhibiting greater values. While no significant changes were identified for other characteristics, paired t-tests showed a significant divergence in mandibular body length between the right and left sides (p = 0.001). In Class III malocclusion, there was a significant preference for right deviation in the direction of mandibular deviation (p = 0.005). These results imply that AI is capable of accurately identifying some anatomical characteristics associated with face aesthetics, especially when it comes to differentiating between Class III malocclusions.In conclusion, the Saudi Arabian population's facial symmetry assessments via AI have demonstrated a high degree of reliability and consistency. Notably, the length of the mandible on the right side has emerged as a crucial feature in discriminating between malocclusion classes. The study emphasizes how AI might improve the accuracy of assessments of face aesthetics and our knowledge of facial features connected to malocclusion.

Information-theoretical analysis of the neural code for decoupled face representation

Processing faces accurately and efficiently is a key capability of humans and other animals that engage in sophisticated social tasks. Recent studies reported a decoupled coding for faces in the primate inferotemporal cortex, with two separate neural populations coding for the geometric position of (texture-free) facial landmarks and for the image texture at fixed landmark positions, respectively. Here, we formally assess the efficiency of this decoupled coding by appealing to the information-theoretic notion of description length, which quantifies the amount of information that is saved when encoding novel facial images, with a given precision. We show that despite decoupled coding describes the facial images in terms of two sets of principal components (of landmark shape and image texture), it is more efficient (i.e., yields more information compression) than the encoding in terms of the image principal components only, which corresponds to the widely used eigenface method. The advantage of decoupled coding over eigenface coding increases with image resolution and is especially prominent when coding variants of training set images that only differ in facial expressions. Moreover, we demonstrate that decoupled coding entails better performance in three different tasks: the representation of facial images, the (daydream) sampling of novel facial images, and the recognition of facial identities and gender. In summary, our study provides a first principle perspective on the efficiency and accuracy of the decoupled coding of facial stimuli reported in the primate inferotemporal cortex.

Improvement in facial aesthetics of orthognathic patients after surgery-first approach

Facial appearance significantly affects psychosocial wellbeing, and an improvement in facial aesthetics is considered an essential outcome of orthognathic treatment. The surgery-first approach (SFA) has emerged as a promising alternative to the conventional orthodontics-first approach (OFA) due to its potential advantages in reducing treatment duration and cost, delivering early aesthetic improvement, and increasing patient satisfaction. However, its impact on final facial aesthetics and how it compares with the OFA has, to our knowledge, not yet been investigated. This retrospective study aimed to compare the improvement in facial aesthetics after orthognathic surgery in an SFA and an OFA group. Preoperative and postoperative 3-dimensional stereophotogrammetry facial images of 40 patients were evaluated by five professional assessors using the Global Aesthetic Improvement Scale (GAIS). Similar aesthetic improvement outcomes were found in both the SFA and OFA groups. The GAIS score significantly correlated with the following facial variables: upper lip projection, chin prominence, facial proportions, paranasal hollowing, lip competence, mandibular projection, and facial profile. No significant correlation was found between a change in aesthetic score and the surgical variables. There was a positive association between overall GAIS score and the gender and experience level of the individual assessors. This study suggests that aesthetic facial improvement achieved with the SFA is satisfactory and comparable to that of the OFA.

Multidimensional Indicators as Enablers on Perception of Facial Beauty and Appearance among Indian Population: A Descriptive Cross-Sectional Study

Background

Facial appearance has been a flagbearer of "beauty" since time immemorial. Perception of beauty is highly influenced by cultural, interpersonal, and intra-personal variations.

Objectives

This study aimed to assess the perception of facial beauty and appearance through multidimensional influencing indicators among the Indian population, and to determine whether the physically attractive person possesses more personal and socially desirable traits than the comparatively less attractive individual.

Materials and Methods

A study population of 474 with equal male and female population of Indian origin was selected. Their perception was assessed based on the prevalidated, self-administered questionnaire using a tool with five major multidimensional indicators. Six images were selected, three each of male and female subjects, and labeled as A, B, and C, in descending order of attractiveness. The multidimensional influencing indicator tool was self-administered to the participants and the responses were recorded individually.

Results

Photograph A scored the highest out of the three grading scales in both males and females.

Conclusion

The most attractive photograph, in both males and females, was deemed to be associated with higher scores of attractiveness and success.

The effect of orthodontic treatment on smile attractiveness: a systematic review

BACKGROUND

Smile attractiveness is a primary factor for patients to seek orthodontic treatment, however, there is yet no systematic evaluation of this topic in the literature.

OBJECTIVES

To assess the current evidence on the effect of orthodontic treatment on smile attractiveness.

SEARCH METHODS

Seven electronic databases (MEDLINE, Cochrane Library, Virtual Health Library, SCOPUS, Web of Science, Google Scholar and Embase) were searched on 14 September 2022.

SELECTION CRITERIA

Studies evaluating smile attractiveness before and after orthodontic treatment or only after completion of orthodontic treatment.

DATA COLLECTION AND ANALYSIS

Extracted data included study design and setting, sample size and demographics, malocclusion type, treatment modality and method for outcome assessment. Risk of bias was assessed with the ROBINS-I tool for non-randomised studies. Random-effects meta-analyses of mean differences and their 95% confidence intervals (CIs) were planned a priori.

METHODS

After elimination of duplicate studies, data extraction and risk of bias assessment according to the Cochrane guidelines, an evaluation of the overall evidence was performed. The included studies were evaluated based on the characteristics of their study and control groups and based on their main research question. Also, all outcome measures were standardized into a common assessment scale (0-100), in order to obtain more easily interpretable results.

RESULTS

Ten studies were included in this review, nine of which were assessed as being at serious risk of bias and one at moderate risk of bias. The large heterogeneity between the included studies did not allow for a meta-analysis. Orthodontic treatment has a moderately positive effect on smile attractiveness. When compared to no treatment, orthodontic treatment with premolar extractions improves smile attractiveness by 22%. Also, surgical correction of Class III cases increases smile attractiveness by 7.5% more than camouflage treatment. No other significant differences were shown between different types of treatment.

CONCLUSION

Based on the available data, orthodontic treatment seems to moderately improve the attractiveness of the smile. There is significant bias in the current literature assessing the effect of orthodontics on smile attractiveness; therefore, the results cannot be accepted with certainty.

Comparing the esthetic impact of virtual mandibular advancement, bichectomy, jawline, and their combination

INTRODUCTION

The purpose of this study was to compare the effects of mandibular advancement (MA), bichectomy, jawline, and their combination on facial attractiveness. The 3-dimensional (3D) visual sculpting is a method to perform the task.

METHODS

FaceBuilder software, a Blender 2.93 LTS add-on, was used to generate a 3D head and face model of a female patient with Class II Division I malocclusion. MA, bichectomy, jawline, and combination modifications were performed on the model using a 3D virtual sculpting tab, and 4 new head models were created. Five hundred thirteen participants scored lateral and frontal views of the modified and reference models. The Mann-Whitney U, Kruskal-Wallis, and Wilcoxon tests were used for statistical analysis.

RESULTS

MA modification received the highest frontal and lateral image scores. The raters found the jawline frontal photograph to be the least attractive. Significant differences were observed between the lateral and frontal attractiveness scores in all modifications except bichectomy. The combination of 3 modifications in both frontal and lateral images received the second-lowest score.

CONCLUSIONS

Facial esthetic modifications receive different attractiveness scores in lateral or frontal evaluations. MA outperforms bichectomy and jawline augmentation in terms of improving facial attractiveness.

The Effect of Wearing a Mask on Facial Attractiveness

Background

The COVID-19 pandemic necessitated masking in public spaces. Masks may impact the perceived attractiveness of individuals and hence, interpersonal relations.

Objectives

To determine if facial coverings affect attractiveness.

Methods

An online survey was conducted using 114 headshot images, 2 each-unmasked and masked-of 57 individuals. Two hundred and seven participants rated them on an ordinal scale from 1 (least attractive) to 10 (most attractive). Parametric and nonparametric tests were performed, as appropriate, for comparison.

Results

For the first quartile, the average rating increased significantly when wearing a mask (5.89 ± 0.29 and 6.54 ± 0.67; P = 0.01). For control images ranked within the fourth quartile, the average rating decreased significantly when wearing a mask (7.60 ± 0.26 and 6.62 ± 0.55; P < 0.001). In the female subgroup (n = 34), there was a small increase in average rating when masked, whereas in the male subgroup (n = 23), there was a small decrease in average rating when masked, but the change was not statistically significant (P > 0.05). For unmasked female images ranked within the first quartile, the average rating increased significantly when wearing a mask (5.77 ± 0.27 and 6.76 ± 0.36; P = 0.001). For the female subgroup with mean ratings within the fourth quartile, the average decreased significantly when wearing a medical mask (7.53 ± 0.30 and 6.77 ± 0.53; P < 0.05). For unmasked male images ranked within the first quartile, the average rating increased when wearing a medical mask but the change was not statistically significant (P > 0.05), whereas for the control male images within the fourth quartile, the average rating decreased significantly when masked (7.72 ± 0.18 and 6.50 ± 0.54; P < 0.05).

Conclusions

While wearing a facial covering significantly increased attractiveness for images less attractive at baseline, and decreased attractiveness for those that are more attractive at baseline; it did not cause a significant overall change in attractiveness in the study population.

Level of Evidence 5

The effect of orthodontic treatment on facial attractiveness: a systematic review and meta-analysis

BACKGROUND

Facial and smile attractiveness are significant motivating factor for patients to seek orthodontic treatment. Although there is a general belief that orthodontic treatment improves facial appearance, this has yet not been systematically evaluated.

OBJECTIVE

The objective of this study was to assess the current evidence on the effect of orthodontic treatment on facial attractiveness.

SEARCH METHODS

Systematic and unrestricted search of nine databases were performed up to January 2022.

SELECTION CRITERIA

Studies evaluating facial attractiveness before and after orthodontic treatment.

DATA COLLECTION AND ANALYSIS

Extracted data included study design and setting, sample size and demographics, malocclusion type, treatment modality, and method for outcome assessment. Risk of bias was assessed with the ROBINS-I tool for non-randomized studies and with RoB-2 for randomized controlled trials (RCTs). Random-effects meta-analyses of mean differences and their 95% confidence intervals (CIs) were performed.

RESULTS

Twenty studies were included in data synthesis; three randomized controlled clinical trials and 17 non-randomized clinical studies of retrospective or prospective design. One of the RCTs was found to have low risk of bias, one presented some concerns and the third showed a high risk of bias. All non-randomized studies showed either unclear or high risk of bias. Data syntheses showed that orthodontic treatment improved facial attractiveness ratings by 9% when compared with untreated controls (MD: 9.05/95% CI: 4.71; 13.39). A combination of orthodontics and orthognathic surgery also showed a positive effect of 5.5% (MD: 5.51/95% CI: 1.55; 9.47) when compared with orthodontic treatment alone. There was no difference in effect between extraction and non-extraction treatments (MD: -0.89/ 95% CI: -8.72; 6.94) or between different types of Class II correctors (MD: 2.21/95% CI: -16.51; 20.93).

LIMITATIONS

With the exception of two RCTs, included studies were of unclear or low quality.

CONCLUSIONS

Orthodontic treatment has a clinically weak effect on facial attractiveness when compared to no treatment. The same is true when a combined orthodontic/surgical treatment is compared to orthodontics alone.

REGISTRATION

PROSPERO #: CRD42020169904.

The perception of odor pleasantness is shared across cultures

Humans share sensory systems with a common anatomical blueprint, but individual sensory experience nevertheless varies. In olfaction, it is not known to what degree sensory perception, particularly the perception of odor pleasantness, is founded on universal principles,1-5 dictated by culture,6-13 or merely a matter of personal taste.6,8-10,12,14 To address this, we asked 225 individuals from 9 diverse nonwestern cultures-hunter-gatherer to urban dwelling-to rank the monomolecular odorants from most to least pleasant. Contrary to expectations, culture explained only 6% of the variance in pleasantness rankings, whereas individual variability or personal taste explained 54%. Importantly, there was substantial global consistency, with molecular identity explaining 41% of the variance in odor pleasantness rankings. Critically, these universal rankings were predicted by the physicochemical properties of out-of-sample molecules and out-of-sample pleasantness ratings given by a tenth group of western urban participants. Taken together, this shows human olfactory perception is strongly constrained by universal principles.

Puzzle Facelift: A non-surgical, whole treatment for facial modelling and rejuvenation

The assessment of correct anatomy of face and the evaluation of the dynamic interplay between anatomy and function, in order to get an overall improvement, is a leading topic in aesthetic surgery and has increased its impact in the recent years. A non-surgical impact technique reduces both post-treatment discomfort and the overall cost. Obtaining the simultaneous correction in forehead, nose, lips and chin means obtaining an overall improvement in face view. Likewise, the high predictability of the procedure and the absence of alloplastic implant, bone re-absorption and scars have to be considered in non-surgical aesthetic medicine. In conclusion, a single-session of profile correction using HA filler should be proposed to patient, every time the aesthetic practitioner sees a coexistence of forehead, nose lips and chin defects.

I See Faces! A Review on Face Perception and Attractiveness with a Prosthodontic Peek at Cognitive Psychology

A human face contains a wealth of information about an individual, with which an observer can instinctively make a judgment on the attractiveness of the face. However, despite the profuse literature on facial and smile attractiveness, their origins, determinants, and perceptions remain controversial. The axiom in face processing research is that a face is perceived as an amalgamation of its features, and is referred to as "whole" or "holistic" perception. It is pertinent to the clinician involved in the provision of esthetic restorations to understand this holistic process of face recognition and perception of smile attractiveness. This review paper addresses face recognition and perception of attractiveness by reviewing the holistic perception of faces, including the multidimensional face-space model, and also reviews the smile and facial attractiveness according to the average, multiple motive, and secondary sex characteristics theories.

The Impact of Dental Midline on Asymmetric Faces: Perspective of Laypersons and Dentists

Background: The objective was to determine if asymmetric facial features, nasal and chin deviations, affect the perception of attractiveness of a dental midline angulation, and if it is consistent among both dentists and laypeople. It was also analyzed if factors, such as the sex, age group of the participants and the dentist’s area of operation are relevant in their assessment. Methods: A cross-sectional study, approved by the Ethics Committee of Fernando Pessoa University. From a symmetrical facial model (SFM) image, a natural-looking asymmetrical face was created. Based on this asymmetric facial model six images were created, with different directions and degrees of inclination of the dental midline. In total, 236 laypersons and 242 dentists completed the online questionnaire where they rated the self-perception of attractiveness of the eight images (VAS scale from 0 to 10). Non-parametric comparisons (IBM© SPSS Statistics vs. 27.0, p < 0.05). Results: The results showed a significant difference in the perception of attractiveness between laypeople and dentists. This finding was consistent regarding every image, except for the SFM. The factors, sex of the people participating and dentist’s area of operation, seemed only to contribute to a significant difference in the perception when it came to the SFM. The perceived attractiveness of the images, for dentists and laypersons, did not differ by age group of the participant, apart from images 6 and 8. Conclusions: Dentists are more rigorous about dental midline inclinations than laypersons. The perception of attractiveness was affected by the age group and sex of the participants and the dentist’s area of operation.

Colorants in cosmetic applications

The color cosmetic market, even though highly dependent on color, is driven by texture. Pigment and color innovation are predominantly taking place in the field of inorganic effect pigments, as colorants are regulated within the different cosmetic directives and toxicological profiles have to be established prior to use. Therefore, the formulation and the packaging are the relevant innovative factors. Nevertheless, color cosmetics are driven by fashion and trends. One of the main drivers for sales is social networks. They are image based and therefore the ideal platform to spread these trends, boosting sales of color cosmetics recently.

Even though, color cosmetics seem to be very simple in composition, the development, production and quality control are far from that. In color cosmetics, all cosmetic disciplines cumulate: dispersion strategies, emulsion technologies, molding and extruding of sticks and pencil leads, mixing and compressing of powders, liquid inks and so on. And almost every discipline requires separate production vessels, resulting in a rather complex manufacturing process.

Modeling individual preferences reveals that face beauty is not universally perceived across cultures

Facial attractiveness confers considerable advantages in social interactions,^1,2 with preferences likely reflecting psychobiological mechanisms shaped by natural selection. Theories of universal beauty propose that attractive faces comprise features that are closer to the population average³ while optimizing sexual dimorphism.⁴ However, emerging evidence questions this model as an accurate representation of facial attractiveness,5, 6, 7 including representing the diversity of beauty preferences within and across cultures.8, 9, 10, 11, 12 Here, we demonstrate that Western Europeans (WEs) and East Asians (EAs) evaluate facial beauty using culture-specific features, contradicting theories of universality. With a data-driven method, we modeled, at both the individual and group levels, the attractive face features of young females (25 years old) in two matched groups each of 40 young male WE and EA participants. Specifically, we generated a broad range of same- and other-ethnicity female faces with naturally varying shapes and complexions. Participants rated each on attractiveness. We then reverse correlated the face features that drive perception of attractiveness in each participant. From these individual face models, we reconstructed a facial attractiveness representation space that explains preference variations. We show that facial attractiveness is distinct both from averageness and from sexual dimorphism in both cultures. Finally, we disentangled attractive face features into those shared across cultures, culture specific, and specific to individual participants, thereby revealing their diversity. Our results have direct theoretical and methodological impact for representing diversity in social perception and for the design of culturally and ethnically sensitive socially interactive digital agents.

•

We modeled individual preferences for attractive faces in two cultures

•

Attractive face features differ from the face average and sexual dimorphism

•

Instead, culture and individual preferences shape attractive face features

•

Attractive face features from a culture are used to judge other-ethnicity faces

Assessing Facial Symmetry and Attractiveness using Augmented Reality

Facial symmetry is a key component in quantifying the perception of beauty. In this paper, we propose a set of facial features computed from facial landmarks which can be extracted at a low computational cost. We quantitatively evaluated the proposed features for predicting perceived attractiveness from human portraits on four benchmark datasets (SCUT-FBP, SCUT-FBP5500, FACES and Chicago Face Database). Experimental results showed that the performance of the proposed features is comparable to those extracted from a set with much denser facial landmarks. The computation of facial features was also implemented as an augmented reality (AR) app developed on Android OS. The app overlays four types of measurements and guidelines over a live video stream, while the facial measurements are computed from the tracked facial landmarks at run time. The developed app can be used to assist plastic surgeons in assessing facial symmetry when planning reconstructive facial surgeries.

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 novel facial attractiveness evaluation system based on face shape, facial structure features and skin

Facial attractiveness is an important research direction of genetic psychology and cognitive psychology, and its results are significant for the study of face evolution and human evolution. However, previous studies have not put forward a comprehensive evaluation system of facial attractiveness. Traditionally, the establishment of facial attractiveness evaluation system was based on facial geometric features, without facial skin features. In this paper, combined with big data analysis, evaluation of face in real society and literature research, we found that skin also have a significant impact on facial attractiveness, because skin could reflect age, wrinkles and healthful qualities, thus affected the human perception of facial attractiveness. Therefore, we propose a comprehensive and novel facial attractiveness evaluation system based on face shape structural features, facial structure features and skin texture feature. In order to apply face shape structural features to the evaluation of facial attractiveness, the classification of face shape is the first step. Face image dataset is divided according to face shape, and then facial structure features and skin texture features that represent facial attractiveness are extracted and fused. The machine learning algorithm with the best prediction performance is selected in the face shape structural subsets to predict facial attractiveness. Experimental results show that the facial attractiveness evaluation performance can be improved by the method based on classification of face shape and multi-features fusion, the facial attractiveness scores obtained by the proposed system correlates better with human ratings. Our evaluation system can help people project their cognition of facial attractiveness into artificial agents they interact with.