Differences in visual perception of age and attractiveness of female facial and body skin

Predicting human chronological age via AI analysis of dorsal hand versus facial images: A study in a cohort of Indian females

Predicting a person's chronological age (CA) from visible skin features using artificial intelligence (AI) is now commonplace. Often, convolutional neural network (CNN) models are built using images of the face as biometric data. However, hands hold telltale signs of a person's age. To determine the utility of using only hand images in predicting CA, we developed two deep CNNs based on 1) dorsal hand images (H) and 2) frontal face images (F). Subjects (n = 1454) were Indian women, 20-80 years, across three geographic cohorts (Mumbai, New Delhi and Bangalore) and having a broad variation in skin tones. Images were randomised: 70% of F and 70% of H were used to train CNNs. The remaining 30% of F and H were retained for validation. CNN validation showed mean absolute error for predicting CA using F and H of 4.1 and 4.7 years, respectively. In both cases correlations of predicted and actual age were statistically significant (r(F) = 0.93, r(H) = 0.90). The CNNs for F and H were validated for dark and light skin tones. Finally, by blurring or accentuating visible features on specific regions of the hand and face, we identified those features that contributed to the CNN models. For the face, areas of the inner eye corner and around the mouth were most important for age prediction. For the hands, knuckle texture was a key driver for age prediction. Collectively, for AI estimates of CA, CNNs based solely on hand images are a viable alternative and comparable to CNNs based on facial images.

Skin patch based makeup finish assessment technique by deep neural network

BACKGROUND

Skin color and texture play a significant role in influencing impressions. To understand the influence of skin appearance and to develop better makeup products, objective evaluation methods for makeup finish have been explored. This study aims to apply machine learning technology, specifically deep neural network (DNN), to accurately analyze and evaluate delicate and complex cosmetic skin textures.

METHODS

"Skin patch datasets" were extracted from facial images and used to train a DNN model. The advantages of using skin patches include retaining fine texture, eliminating false correlations from non-skin features, and enabling visualization of the inferred results for the entire face. The DNN was trained in two ways: a classification task to classify skin attributes and a regression task to predict the visual assessment of experts. The trained DNNs were applied for the evaluation of actual makeup conditions.

RESULTS

In the classification task training, skin patch-based classifiers for age range, presence or absence of base makeup, formulation type (powder/liquid) of the applied base makeup, and immediate/while after makeup application were developed. The trained DNNs on regression task showed high prediction accuracy for the experts' visual assessment. Application of DNN to the evaluation of actual makeup conditions clearly showed appropriate evaluation results in line with the appearance of the makeup finish.

CONCLUSION

The proposed method of using DNNs trained on skin patches effectively evaluates makeup finish. This approach has potential applications in visual science research and cosmetics development. Further studies can explore the analysis of different skin conditions and the development of personalized cosmetics.

The Esthetics of the Nasolabial Fold and Age in the Elderly Via Eye-Tracking

Background

Facial aging is associated with the loss of soft tissue fullness. Perioral signs of facial aging can add years to individuals' appearances and even affect their facial expressions in smiling and nonsmiling images.

Aims

To evaluate the influence of the nasolabial fold on the visual perception of esthetics and age in the elderly, eye-tracking and a visual analog scale were used.

Material and Methods

This study applied a cross-sectional study using 40 laypeople. Facial images of an elderly woman were modified to include facial expression lines such as nasolabial folds and marionette lines with no folds, intermediate, and accentuated depths folds. Eye tracking was implemented to measure the average number of fixations. Heat maps and dot maps were generated using eye-tracking software. A visual analog scale of attractiveness and age perception questionnaire were also incorporated into the study. Statistical analysis was performed using a significance of (P<0.05).

Results

The majority of visual attention was paid to the eye and mouth areas. In the images with no folds, the right eye attracted a greater degree of fixation. In the images in which nasolabial folds were accentuated, the mouth area served as an area of high fixation. No statistical difference was observed between the groups in which smiling images were viewed. Nonsmiling images demonstrated significant differences between groups for variables including time until first fixation, complete fixation time, and number of fixations on the eyes and hemifaces. Old age and diminished attractiveness were associated with attenuated nasolabial folds, especially in nonsmiling images.

Conclusion

The facial lines and expressions of elderly female individuals were assessed by laypeople using eye-tracking, showing that the deeper one's nasolabial folds, the more aged and less attractive one appears, especially in nonsmiling images. Smiling pictures were perceived to be more attractive and youthful; these perceptions should be considered in the search for improved esthetic results, whether in dental or facial esthetic treatments.

Quantification of perception towards facial skin ideal complexion in multiple ethnic populations from clinical imaging cues

OBJECTIVE

Ideal complexion is a perceptual skin quality that is strongly influenced by cultural and ethnic background. The objectives of this study are to quantitatively characterize skin ideal complexion based on clinical image cues and to compare the perceptions of ideal complexion among multiple ethnicities.

METHODS

Facial images of Indian, Chinese, Caucasian and Latino females collected using VISIA®-CR were presented to naïve panels of the same ethnicity following a two-alternative forced choice design and responses on skin "ideal complexion" were obtained from 336 panelists. Panel perception was transformed logistically (d') and projected onto a continuum (ω) following Bradley-Terry model. Image cues including skin color and unevenness, skin shine and surface smoothness, and pigmentary blotches and spots were computed using image analysis and their relationship with ω were evaluated through multiple regression analysis. A novel skin index namely ideal complexion score (ICS) was developed and correlated against age using linear regression. Finally, ICS was applied to evaluate treatment efficacy of a skin brightening kit on 35 female Caucasian subjects.

RESULTS

Panel perception d' showed statistically significant (p < 0.05) correlation with the contrast of image cues for all ethnic panels (R² = 0.74, 0.76, 0.62 and 0.46 for Indian, Chinese, Caucasian and Latino respectively) and strong correlations between perception ω and linear combinations of image cues were observed (R² > 0.88 for all). Main effects of facial image visual cues on ideal complexion were compared: contrast of skin redness and pigmented spots and visual smoothness were important in determining ICS for all ethnicities; skin color unevenness was more pronounced for Indian and Caucasian; skin lightness was important for Indian and Chinese; skin shine was critical for Chinese and Latino; and skin hue angle ranked higher for Caucasian. Correlations between ICS and age were observed for Indian and Caucasian (R² = 0.55) in which ICS decreased as age increased. Twenty-nine percent improvement on ICS was observed after 12 weeks' treatment using the brightening kit compared to the baseline.

CONCLUSION

Mathematical models were successfully established to describe subjective perception towards skin ideal complexion based on objectively measured image cues for multiple ethnicities.

How Old Do I Look? Exploring the Facial Cues of Age in a Tasked Eye-Tracking Study

Importance: This is the first eye-tracking study to use a tasked age estimation paradigm to explore the facial cues of age as seen by casual observers. Objectives: Determine where observers gaze on faces when tasked with estimating an individual's age. Design, Setting, and Participants: This was a prospective controlled experiment, which took place at an academic tertiary referral center. In total, 220 casual observers (80 untasked, 140 tasked) viewed frontal facial images of women while an infrared eye-tracking monitor recorded their eye movements and fixations in real time. Main Outcomes and Measures: Multivariate Hotelling's analysis followed by planned posthypothesis testing was used to compare fixation durations for predefined regions of interest, including the central triangle, upper face, midface, lower face, and neck between tasked and untasked observers. Results: A total of 80 observers (mean age 23.6 years, 53% female) successfully completed the first untasked eye-tracking experiment. A total of 140 observers (mean age 26.1 years, 60% female) successfully completed the second age estimation experiment. On multivariate analysis, there were significant differences in the distribution of attention between observers in the two experiments (T² = 99.70; F(5,2084) = 19.9012, p < 0.0001). On planned posthypothesis testing, observers attended significantly more to the lower third of the face (0.20 s, p < 0.0001, 95% confidence interval (CI) 0.14-0.27 s) and neck (0.05 s, p = 0.0074, 95% CI 0.01-0.08 s) and less to the upper third of the face (-0.27 s, p < 0.0001, 95% CI -0.40 to -0.14 s) when tasked. There was no significant difference in time spent on the whole face in the two experiments, suggesting that peripheral elements such as hair color or jewelry did not significantly influence gaze patterns. Conclusions and Relevance: Humans form judgments about others every day of their lives, and age perception colors their every interaction. To our knowledge, this study is the first to use eye tracking to investigate facial cues of age. The results showed that when tasked with estimating age, casual observer visual attention was shifted toward the lower face when compared with those who were untasked. These data inform our understanding of facial age perception and potential areas to target for facial rejuvenation. Level of Evidence: NA.

It felt fluent but I did not like it: fluency effects in faces versus patterns

Whether you like a person or not is often appraised in a glance. However, under such short presentation durations stimuli are harder to perceive and, according to hedonic fluency theory-which holds that higher fluency is linked to higher liking-thus, are liked less. Given that liking considerably influences person perception, we tested how shorter and longer presentation durations affect liking for faces and compared this with abstract patterns. To capture facets of fluency of processing we assessed felt fluency, liking, and certainty ratings. Following predictions of fluency theory, longer presentation durations led to higher felt fluency, certainty, and positively affected liking judgments in the abstract patterns. In faces, felt fluency and certainty also increased with longer durations. However, with longer durations, faces were liked less, and liking was not related to felt fluency. In other words, in contrast to hedonic fluency theory, faces are more attractive when only seen for a short amount of time. Thus, fluency does not inevitably lead to more positive evaluations—it rather depends on the stimulus category. We discuss these findings in terms of the special status that faces have with regard to human perception and evaluation.

The impact of baby schema on perceived attractiveness, beauty, and cuteness in female adults

Beauty and cuteness are considered to represent different aspects of attractiveness and to be distinguishable from each other by their respective reliance on neonate and sexually mature features found in attractive faces. In this study, we investigated whether baby schema features in adult faces affect not only cuteness, but also beauty and attractiveness. We also investigated possible differences among attractiveness, beauty, and cuteness, and possible effects of perceived youth on these judgments. Results showed that baby schema features affected judgments of attractiveness, beauty, and cuteness, but that perceived youth did not significantly influence these judgments. Furthermore, the effect of each facial feature differed across rating types with the participants' naïve interpretation of rating categories. This suggests that beauty predominantly refers to sexual attraction, while attractiveness refers to a non-sexual attraction regardless of participants' gender. However, gender differences may exist in judging cuteness. Therefore, expressions related to attractiveness may incorporate different elements and this distinction may not be fully shared across gender.

Exploring the effects of non-medical versus medical approaches to the management of skin aging in women over sixty

This study was a pilot project, set up to assess ageing skin using a multi-disciplinary approach. The main aim of this study was to evaluate whether the use of more radical ('medical') treatments in the management of skin ageing would bring superior results and ultimately make people look younger, than the use of cosmetics ('non-medical' treatments). A simple post-hoc study design was used, whereby medical treatments varied within the group, all of them completed at least 2 weeks before the start of the study. In addition, it was of interest to assess the suitability of the proposed combination of methods. A total of 21 female participants were recruited for this study: 11 for the non-medical and 10 for the medical group. The multi-disciplinary approach consisted of instrumental measurements, self-assessment, expert assessment by Merz scales and a public perception survey. The majority of nearly 70 sets of instrumental skin data obtained in this study did not differ significantly between the non-medical and the medical group. However, the medical group gave higher self-assessment scores for their faces. The scores for hands were lower than scores for faces by both groups. This was partly supported by instrumental data (lower skin hydration on hands than on the face). The findings of the public perception survey of nine matched pairs of subjects scored the non-medical group as younger looking. Data analysis has shown that the judgement of youthfulness did not depend on either the gender or the age of observers.