The relevance and accuracy of an AI algorithm-based descriptor on 23 facial attributes in a diverse female US population.

BACKGROUND: The response of AI in situations that mimic real life scenarios is poorly explored in populations of high diversity. OBJECTIVE: To assess the accuracy and validate the relevance of an automated, algorithm-based analysis geared toward facial attributes devoted to the adornment routines of women. METHODS: In a cross-sectional study, two diversified groups presenting similar distributions such as age, ancestry, skin phototype, and geographical location was created from the selfie images of 1041 female in a US population. 521 images were analyzed as part of a new training dataset aimed to improve the original algorithm and 520 were aimed to validate the performance of the AI. From a total 23 facial attributes (16 continuous and 7 categorical), all images were analyzed by 24 make-up experts and by the automated descriptor tool. RESULTS: For all facial attributes, the new and the original automated tool both surpassed the grading of the experts on a diverse population of women. For the 16 continuous attributes, the gradings obtained by the new system strongly correlated with the assessment made by make-up experts (r ≥ 0.80; p < 0.0001) and supported by a low error rate. For the seven categorical attributes, the overall accuracy of the AI-facial descriptor was improved via enrichment of the training dataset. However, some weaker performance in spotting specific facial attributes were noted. CONCLUSION: In conclusion, the AI-automatic facial descriptor tool was deemed accurate for analysis of facial attributes for diverse women although some skin complexion, eye color, and hair features required some further finetuning.

Objective and automatic grading system of facial signs from smartphones' pictures in South African men: Validation versus dermatologists and characterization of changes with age.

OBJECTIVE: To evaluate the capacity of the automatic detection system to accurately grade, from selfie pictures, the severity of eight facial signs in South African men. METHODS: Selfie pictures (obtained from frontal and back cameras) of 281 South African men differently aged (20-70 years) were obtained and analyzed by an automatic artificial intelligence (AI)-based automatic grading system. Data were compared with the clinical gradings made by experts and dermatologists. RESULTS: In all facial signs, both series of gradings were found highly correlated with, however, different coefficients (0.59-0.95), those of marionette lines and cheek pores being of lower values. No differences were observed between data obtained by frontal and back cameras. With age, in most cases, gradings show up to the 50-59 year age-class, linear-like changes. When compared to men of other ancestries, South African men present lower wrinkles/texture, pigmentation, and ptosis/sagging scores till 50-59 years, albeit not much different in the cheek pores sign. The early onset (mean age) of visibility of wrinkles/texture for South African men were (i.e., reaching grade >1) 39 and 45 years for ptosis/sagging. CONCLUSION: This study completes and enlarges the previous works conducted on men of other ancestries by showing some South African specificities and slight differences with men of comparable phototypes (Afro American).

Comparing the self-perceived effects of a facial anti-aging product to those automatically detected from selfie images of Chinese women of different ages and cities.

OBJECTIVE: To assess the agreement, after 1-month application of a popular and efficient anti-aging product, between self-perceived facial signs of aging and those detected and graded by an automatic A.I-based system, using smartphones' selfie images. MATERIAL AND METHODS: Of 1065 Chinese women, aged 18-60 years, from eight different Chinese cities were recruited. They were asked to apply daily, for 1 month, a referential anti-aging product onto their whole face. Selfie images were taken by all subjects at D0 and D28 and sent to our facilities for being analyzed through 10 different facial signs. At D28 , all subjects were asked to fill a questionnaire on the status of their faces, through six general statements. RESULTS: A global agreement between both approaches is reached, particularly among women older than 40 years where the severity of facial signs is already more pronounced or among younger women who present at least facial signs scored above one grading units. This limit becomes, therefore, a prerequisite in the recruitment of Chinese subjects in the case of anti-aging applied studies and possible automatically based on automatic grading system. When respecting such conditions, the positive effects of the product on most facial signs can be demonstrated after 28 days of successive applications. CONCLUSION: Such methodological approach paves the road in fulfilling the need of consumers of a better transparency in the claims of an anti-aging product.

The continuous development of a complete and objective automatic grading system of facial signs from selfie pictures: Asian validation study and application to women of three ethnic origins, differently aged.

OBJECTIVE: To evaluate the capacity of the automatic detection system to accurately grade, from smartphones' selfie pictures, the severity of seven new facial signs added to the nine previously integrated. METHODS: A two-step approach was conducted: first, to check on 112 Korean women, how the AI-based automatic grading system may correlate with dermatological assessments, taken as reference; second, to confirm on 1140 women of three ancestries (African, Asian, and Caucasian) the relevance of the newly input facial signs. RESULTS: The sixteen specific Asian facial signs, detected automatically, were found significantly (P < .0001) highly correlated with the clinical evaluations made by two Korean dermatologists (wrinkles: r = .90; sagging: r = .75-.95; vascular: r = .85; pores: r = .60; pigmentation: r = .50-.80). When applied at a larger scale on women of different ethnicities, new signs were found of good accuracy and reproducibility, albeit depending on ethnicity. Due to contrast with the innate skin complexion, the facial signs dealing with skin pigmentation were found of a much higher relevance among Asian women than African or Caucasian women. The automatic gradings were even found of a slightly higher accuracy than the clinical gradings. CONCLUSION: The previously used automatic grading system is now completed by adding new facial signs apt at being detected. The continuous development is now integrating some limitations with regard to the constitutive skin complexion of the self-pictured subjects. Presenting reproducible assessments, highly correlated with medical grading, this system could change tremendously clinical researches, like in epidemiological studies, where it offers an easy, fast, affordable, and confidential approach in the objective quantification of facial signs.

The Impact of Electrode Density and Precision on Brain-Computer Interfaces.

In this paper, we review several advances in different fields that provide new potential for brain-computer interfaces enabled by directly interfacing biological neural networks with electrodes, including recent successes with liquid injected conductive channels and mesh electronics supported by 3D scaffolds. Based on this review, it is clear that the success of biological neural connectivity is dependent on the precision and density of the inserted electrodes. In order to better understand the dynamics of this relationship, we propose a simple impedance-based electrode connectivity model, based on which we perform a simulation of the impact of both electrode density and electrode precision on the amount of information lost as part of the connection. Although the examples illustrated are more informative rather than conclusive, the fundamental takeaway from this work is that electrode density is a substantially important parameter while electrode precision is necessarily helpful.

A new procedure, free from human assessment that automatically grades some facial skin structural signs. Comparison with assessments by experts, using referential atlases of skin ageing.

OBJECTIVE: To develop an automatic system that grades the severity of facial signs through 'selfies' pictures taken by women of different ages and ethnics. METHODS: 1140 women from three ethnics (African-American, Asian, Caucasian), of different ages (18-80 years old), took 'selfies' by high resolution smartphones cameras under different conditions of lighting or facial expressions. A dedicated software, was developed, based on a Convolutional Neural Network (CNN) that integrates training data from referential Skin Aging Atlases. The latter allows to an immediate quantification of the severity of nine facial signs according to the ethnicity declared by the subject. These automatic grading were confronted to those assessed by 12 trained experts and dermatologists either on 'selfies' pictures or in live conditions on a smaller cohort of women. RESULTS: The system appears weakly influenced by lighting conditions or facial expressions (coefficients of variations ranging 10-13% for most signs) and leads to global agreements with experts' assessments, even showing a better reproducibility on some facial signs. CONCLUSION: This automatic scoring system, still in development, seems offering a new quantitative approach in the quantified description of facial signs, independent from human vision, in many applications, being individual, cosmetic oriented or dermatological with regard to the follow-up of medical anti-ageing corrective strategies.

OBJECTIF: De développer un système automatique qui quantifie la sévérité de certains signes du visage à partir de photographies de type 'selfies' pris par des femmes d'origine ethnique et d'âge différents. MÉTHODES: 1140 femmes de trois ethnies différentes (Afro-Américaines, Asiatiques, Caucasiennes), d'âges différents (18-80 ans) ont pris des selfies sous différentes conditions d'éclairage et d'expressions faciales. Un logiciel dédié a été développé, basé sur un réseau de convolution neuronal et intégrant les données d'annotations utilisant les Atlas de Vieillissement Cutané. Ce système quantifie immédiatement la sévérité de 9 signes faciaux selon l'ethnie déclarée par le sujet. Ces scores ont été confrontés à ceux de 12 experts et dermatologistes soit à partir des 'selfies' ou en conditions réelles sur un groupe plus restreint de femmes. RÉSULTATS: Le système apparaît faiblement influencé par les conditions d'éclairage et les expressions faciales (coefficients de variation de l'ordre de 10-13%) et conduit à des valeurs comparables de celles des experts, voire même de meilleure reproductibilité dans certains cas. CONCLUSION: Ce système de scorage automatique, encore en développement, semble offrir une nouvelle approche dans la description quantitative de signes du visage, indépendante de l'œil humain, dans de nombreuses applications, comme la personnalisation, à visée cosmétique ou dermatologique, dans le suivi de certaines stratégies médicales de l'antivieillissement cutané.

Hair Segmentation Using Heuristically-Trained Neural Networks.

We present a method for binary classification using neural networks (NNs) that performs training and classification on the same data using the help of a pretraining heuristic classifier. The heuristic classifier is initially used to segment data into three clusters of high-confidence positives, high-confidence negatives, and low-confidence sets. The high-confidence sets are used to train an NN, which is then used to classify the low-confidence set. Applying this method to the binary classification of hair versus nonhair patches, we obtain a 2.2% performance increase using the heuristically trained NN over the current state-of-the-art hair segmentation method.

A quantitative evaluation of alcohol withdrawal tremors.

This paper evaluates the relation between Alcohol Withdrawal Syndrome tremors in the left and right hands of patients. By analyzing 122 recordings from 61 patients in emergency departments, we found a weak relationship between the left and right hand tremor frequencies (correlation coefficient of 0.63). We found a much stronger relationship between the expert physician tremor ratings (on CIWA-Ar 0-7 scale) of the two hands, with a correlation coefficient of 0.923. Next, using a smartphone to collect the tremor data and using a previously developed model for obtaining estimated tremor ratings, we also found a strong correlation (correlation coefficient of 0.852) between the estimates of each hand. Finally, we evaluated different methods of combining the data from the two hands for obtaining a single tremor rating estimate, and found that simply averaging the tremor ratings of the two hands results in the lowest tremor estimate error (an RMSE of 0.977). Looking at the frequency dependence of this error, we found that higher frequency tremors had a much lower estimation error (an RMSE of 1.102 for tremors with frequencies in the 3-6Hz range as compared to 0.625 for tremors with frequencies in the 7-10Hz range).

Tiny videos: a large data set for nonparametric video retrieval and frame classification.

In this paper, we present a large database of over 50,000 user-labeled videos collected from YouTube. We develop a compact representation called "tiny videos" that achieves high video compression rates while retaining the overall visual appearance of the video as it varies over time. We show that frame sampling using affinity propagation-an exemplar-based clustering algorithm-achieves the best trade-off between compression and video recall. We use this large collection of user-labeled videos in conjunction with simple data mining techniques to perform related video retrieval, as well as classification of images and video frames. The classification results achieved by tiny videos are compared with the tiny images framework [24] for a variety of recognition tasks. The tiny images data set consists of 80 million images collected from the Internet. These are the largest labeled research data sets of videos and images available to date. We show that tiny videos are better suited for classifying scenery and sports activities, while tiny images perform better at recognizing objects. Furthermore, we demonstrate that combining the tiny images and tiny videos data sets improves classification precision in a wider range of categories.

Real-time face detection and lip feature extraction using field-programmable gate arrays.

This paper proposes a new technique for face detection and lip feature extraction. A real-time field-programmable gate array (FPGA) implementation of the two proposed techniques is also presented. Face detection is based on a naive Bayes classifier that classifies an edge-extracted representation of an image. Using edge representation significantly reduces the model's size to only 5184 B, which is 2417 times smaller than a comparable statistical modeling technique, while achieving an 86.6% correct detection rate under various lighting conditions. Lip feature extraction uses the contrast around the lip contour to extract the height and width of the mouth, metrics that are useful for speech filtering. The proposed FPGA system occupies only 15050 logic cells, or about six times less than a current comparable FPGA face detection system.

Phase-based dual-microphone robust speech enhancement.

A dual-microphone speech-signal enhancement algorithm, utilizing phase-error based filters that depend only on the phase of the signals, is proposed. This algorithm involves obtaining time-varying, or alternatively, time-frequency (TF), phase-error filters based on prior knowledge regarding the time difference of arrival (TDOA) of the speech source of interest and the phases of the signals recorded by the microphones. It is shown that by masking the TF representation of the speech signals, the noise components are distorted beyond recognition while the speech source of interest maintains its perceptual quality. This is supported by digit recognition experiments which show a substantial recognition accuracy rate improvement over prior multimicrophone speech enhancement algorithms. For example, for a case with two speakers with a 0.1 s reverberation time, the phase-error based technique results in a 28.9% recognition rate gain over the single channel noisy signal, a gain of 22.0% over superdirective beamforming, and a gain of 8.5% over postfiltering.

Enhanced sound localization.

A new approach to sound localization, known as enhanced sound localization, is introduced, offering two major benefits over state-of-the-art algorithms. First, higher localization accuracy can be achieved compared to existing methods. Second, an estimate of the source orientation is obtained jointly, as a consequence of the proposed sound localization technique. The orientation estimates and improved localizations are a result of explicitly modeling the various factors that affect a microphone's level of access to different spatial positions and orientations in an acoustic environment. Three primary factors are accounted for, namely the source directivity, microphone directivity, and source-microphone distances. Using this model of the acoustic environment, several different enhanced sound localization algorithms are derived. Experiments are carried out in a real environment whose reverberation time is 0.1 seconds, with the average microphone SNR ranging between 10-20 dB. Using a 24-element microphone array, a weighted version of the SRP-PHAT algorithm is found to give an average localization error of 13.7 cm with 3.7% anomalies, compared to 14.7 cm and 7.8% anomalies with the standard SRP-PHAT technique.

Localization-based sensor validation using the Kullback-Leibler divergence.

A sensor validation criteria based on the sensor's object localization accuracy is proposed. Assuming that the true probability distribution of an object or event in space f(x) is known and a spatial likelihood function (SLF) psi(x) for the same object or event in space is obtained from a sensor, then the expected value of the SLF E[psi(x)] is proposed as a suitable validity metric for the sensor, where the expectation is performed over the distribution f(x). It is shown that for the class of increasing linear log likelihood SLFs, the proposed validity metric is equivalent to the Kullback-Leibler distance between f(x) and the unknown sensor-based distribution g(x) where the SLF psi(x) is an observable increasing function of the unobservable g(x). The proposed technique is illustrated through several simulated and experimental examples.