A bi-prototype theory of facial attractiveness

The attractiveness of human faces can be predicted with a high degree of accuracy if we represent the faces as feature vectors and compute their relative distances from two prototypes: the average of attractive faces and the average of unattractive faces. Moreover, the degree of attractiveness, defined in terms of the relative distance, exhibits a high degree of correlation with the average rating scores given by human assessors. These findings motivate a bi-prototype theory that relates facial attractiveness to the averages of attractive and unattractive faces rather than the average of all faces, as previously hypothesized by some researchers.     

Advances in computational facial attractiveness methods

Attractiveness of a face plays an important role in many social endeavors. It influences careers like digital entertainment, modeling and acting, as well as person’s career prospect, financial status, and personal relationships. Computational approaches to exploring the nature and components of face attractiveness have been proposed, and have become an emerging topic in facial analysis research. Integrating techniques from image processing, computer vision and machine learning, this subarea aims to develop computational methods to quantify and investigate the attractiveness of a face. This paper summarizes the most recent advances in four related aspects of face attractiveness: (a) facial attractiveness prediction, (b) facial attractiveness enhancement, (c) lateral facial attractiveness and (d) 3D facial attractiveness. The motivations, innovative techniques, and significant results are summarized and discussed. The open problems in these areas and directions for future work are also briefly stated.     

Learning Bayesian network classifiers from label proportions

This paper deals with a classification problem known as learning from label proportions. The provided dataset is composed of unlabeled instances and is divided into disjoint groups. General class information is given within the groups: the proportion of instances of the group that belong to each class.We have developed a method based on the Structural EM strategy that learns Bayesian network classifiers to deal with the exposed problem. Four versions of our proposal are evaluated on synthetic data, and compared with state-of-the-art approaches on real datasets from public repositories. The results obtained show a competitive behavior for the proposed algorithm.     

Prediction of human eye movements in facial discrimination tasks

Under natural viewing conditions, human observers selectively allocate their attention to subsets of the visual input. Since overt allocation of attention appears as eye movements, the mechanism of selective attention can be uncovered through computational studies of eyemovement predictions. Since top-down attentional control in a task is expected to modulate eye movements significantly, the models that take a bottom-up approach based on low-level local properties are not expected to suffice for prediction. In this study, we introduce two representative models, apply them to a facial discrimination task with morphed face images, and evaluate their performance by comparing them with the human eye-movement data. The result shows that they are not good at predicting eye movements in this task.     

The cluster assessment of facial attractiveness using fuzzy neural network classifier based on 3D Moiré features

Facial attractiveness has long been argued upon varied emphases by philosophers, artists, psychologists and biologists. A number of studies empirically investigated how facial attractiveness was influenced by 2D facial characteristics, such as symmetry, averageness and golden ratio. However, few implementations of facial beauty assessment were based on 3D facial features. The purpose of this paper is to propose a novel cluster assessment system for facial attractiveness that is characterized by the incorporation of 3D geometric Moiré features with an adjusted fuzzy neural network (FNN). We first extract 3D facial features from images acquired by a 3dMD scanner. Seven Moiré features are employed to represent a 3D facial image. The FNN classifier, taking the Moiré features as the parameters, is then trained and validated against independently conducted attractiveness ratings. A number of diverse referees were invited and offered their attractiveness ratings over a five-item Likert scale for 100 female facial images. The proposed assessment presents a high accuracy rate of 90%, and the area under curve (AUC) computed from the receiver operating characteristic (ROC) curve is 0.95. The results show that the perceptions of facial attractiveness are essentially consensus among raters, and can be mathematically modeled through supervised learning techniques. The high accuracy achieved proves that the proposed FNN classifier can serve as a general, automated and human-like judgment tool for objective classification of female facial attractiveness, and thus has potential applications to the entertainment industry, cosmetic industry, virtual media, and plastic surgery.     

Analogical proportions

Analogy-making is at the core of human and artificial intelligence and creativity with applications to such diverse tasks as proving mathematical theorems and building mathematical theories, common sense reasoning, learning, language acquisition, and story telling. This paper introduces from first principles an abstract algebraic framework of analogical proportions of the form ‘a is to b what c is to d’ in the general setting of universal algebra. This enables us to compare mathematical objects possibly across different domains in a uniform way which is crucial for AI-systems. It turns out that our notion of analogical proportions has appealing mathematical properties. As we construct our model from first principles using only elementary concepts of universal algebra, and since our model questions some basic properties of analogical proportions presupposed in the literature, to convince the reader of the plausibility of our model we show that it can be naturally embedded into first-order logic via model-theoretic types and prove from that perspective that analogical proportions are compatible with structure-preserving mappings. This provides conceptual evidence for its applicability. In a broader sense, this paper is a first step towards a theory of analogical reasoning and learning systems with potential applications to fundamental AI-problems like common sense reasoning and computational learning and creativity.

     

Feature-based detection of facial landmarks from neutral and expressive facial images

Feature-based method for detecting landmarks from facial images was designed. The method was based on extracting oriented edges and constructing edge maps at two resolution levels. Edge regions with characteristic edge pattern formed landmark candidates. The method ensured invariance to expressions while detecting eyes. Nose and mouth detection was deteriorated by happiness and disgust.     

Prototypes construction from partial rankings to characterize the attractiveness of companies in Belgium

What are the most relevant factors to be considered by employees when searching for an employer? The answer to this question poses valuable knowledge from the Business Intelligence viewpoint since it allows companies to retain personnel and attract competent employees. It leads to an increase in sales of their products or services, therefore remaining competitive across similar companies in the market. In this paper we assess the attractiveness of companies in Belgium by using a new two-stage methodology based on Artificial Intelligence techniques. The proposed method allows constructing high-quality prototypes from partial rankings indicating experts’ preferences. Being more explicit, in the first step we propose a fuzzy clustering algorithm for partial rankings called fuzzy c-aggregation. This algorithm is based on the well-known fuzzy c-means procedure and uses the Hausdorff distance as dissimilarity functional and a counting strategy for updating the center of each cluster. However, we cannot ensure the optimality of such prototypes, and therefore more accurate prototypes must be derived. That is why the second step is focused on solving the extended Kemeny ranking problem for each discovered cluster taking into account the estimated membership matrix. To accomplish that, we adopt an optimization method based on Swarm Intelligence that exploits a colony of artificial ants. Several simulations show the effectiveness of the proposal for the real-world problem under investigation.     

Automatic stress analysis from facial videos based on deep facial action units recognition

Pattern Analysis and Applications - Stress conditions are manifested in different human body’s physiological processes and the human face. Facial expressions are modelled consistently through...     

Real-time estimation of emotional experiences from facial expressions

The present aim was to develop methods that estimate emotional experiences in real time from the electromyographic activity of two facial muscles: zygomaticus major (activated when smiling) and corrugator supercilii (activated when frowning). Ten subjects were stimulated with a series of emotionally arousing pictures and videos. After each stimulus the subjects rated the valence of their emotional experience on a nine-point bipolar dimensional scale. At the same time the computer estimated the subjects' ratings on the basis of their electrical facial activity during each stimulation with 70 computational models. The models estimated the subjects' ratings either categorically or dimensionally with regression models. The best categorical models were able to estimate negative and positive ratings with an average accuracy of over 70 and 80% for pictures and videos, respectively. The best correlations between the human ratings and machine estimations formed with the regression models were high (r>0.9). These findings indicate that models estimating psycho-emotional experiences on the basis of facial activity can be created successfully in several ways.     

Gender discriminating models from facial surface normals

In this paper, we show how to use facial shape information to construct discriminating models for gender classification. We represent facial shapes using 2.5D fields of facial surface normals, and investigate three different methods to improve the gender discriminating capacity of the model constructed using the standard eigenspace method. The three methods are novel variants of principal geodesic analysis (PGA) namely (a) weighted PGA, (b) supervised weighted PGA, and (c) supervised PGA. Our starting point is to define a weight map over the facial surface that indicates the importance of different locations in discriminating gender. We show how to compute the relevant weights and how to incorporate the weights into the 2.5D model construction. We evaluate the performance of the alternative methods using facial surface normals extracted from 3D range images or recovered from brightness images. Experimental results demonstrate the effectiveness of our methods. Moreover, the classification accuracy, which is as high as 97%, demonstrates the effectiveness of using facial shape information for gender classification.     

On visual BMI analysis from facial images

Automatically assessing body mass index (BMI) from facial images is an interesting and challenging problem in computer vision. Facial feature extraction is an important step for visual BMI estimation. This work studies the visual BMI estimation problem based on the characteristics and performance of different facial representations, which has not been well studied yet. Various facial representations, including geometry based representations and deep learning based, are comprehensively evaluated and analyzed from three perspectives: the overall performance on visual BMI prediction, the redundancy in facial representations and the sensitivity to head pose changes. The experiments are conducted on two databases: a new dataset we collected, called the FIW-BMI and an existing large dataset Morph II. Our studies provide some deep insights into the facial representations for visual BMI analysis: 1) The deep model based methods perform better than geometry based methods. Among them, the VGG-Face and Arcface show more robustness than others in most cases; 2) Removing the redundancy in VGG-Face representation can increase the accuracy and efficiency in BMI estimation; 3) Large head poses lead to low performance for BMI estimation. The Arcface, VGG-Face and PIGF are more robust than the others to head pose variations.     

Red-colored products enhance the attractiveness of women

This research investigated whether carrying red-colored products enhances female sexual attractiveness. In the first experiment, male participants were instructed to observe women carrying laptops in different colors (black, silver, red, or blue). The results indicated that the women who carried red laptops were perceived to possess a significantly higher level of attractiveness and sex appeal than those who carried laptops in other colors; however, the red laptop did not affect men’s perceptions of the assertiveness and health level of the women. In the second experiment, the initial experiment was repeated but female participants observed the women; laptop color did not influence how the participants perceived the women’s attractiveness, sex appeal, assertiveness, and level of health. In other words, women carrying products in red only affected how men, but not women, perceived them; thus, women using red products are more attractive and sexually appealing to men.     

Mixtures of regressions with predictor-dependent mixing proportions

We extend the standard mixture of linear regressions model by allowing the mixing proportions to be modeled nonparametrically as a function of the predictors. This framework allows for more flexibility in the modeling of the mixing proportions than the fully parametric mixture of experts model, which we also discuss. We present an EM-like algorithm for estimation of the new model. We also provide simulations demonstrating that our nonparametric approach can provide a better fit than the parametric approach in some instances and can serve to validate and thus reinforce the parametric approach in others. We also analyze and interpret two real data sets using the new method.     

3D facial shape reconstruction using macro- and micro-level features from high resolution facial images

Three-dimensional (3D) facial modeling and stereo matching-based methods are widely used for 3D facial reconstruction from 2D single-view and multiple-view images. However, these methods cannot realistically reconstruct 3D faces because they use insufficient numbers of macro-level Facial Feature Points (FFPs). This paper proposes an accurate and person-specific 3D facial reconstruction method that uses ample numbers of macro- and micro-level FFPs to enable coverage of all facial regions of high resolution facial images. Comparisons of 3D facial images reconstructed using the proposed method for ground-truth 3D facial images from the Bosphorus 3D database show that the method is superior to a conventional Active Appearance Model-Structure from Motion (AAM + SfM)-based method in terms of average 3D root mean square error between the reconstructed and ground-truth 3D faces. Further, the proposed method achieved outstanding accuracy in local facial regions such as the cheek—areas where extraction of FFPs is difficult for existing methods.     

基于不确定比例标签信息的多视角学习

比例标签数据作为弱标签数据中的一种,近年来受到了广泛关注。针对现实应用中所获取的比例标签数据存在噪声污染而标注困难的局限性,提出将多视角学习应用到不确定比例标签学习中以提高分类器的准确率和稳定性。首先,所提出的方法利用核方法映射多视角信息到特征空间以及引入超实例标签表示比例标签信息,在将多视角信息与比例标签信息结合的同时将不确定比例标签数据的局限性考虑在内,以此构建基于不确定比例标签信息的多视角学习模型;而后利用拉格朗日方法将目标模型转换为对偶形式求解,并引入一个迭代框架解决目标模型以获取多视角分类器。最后,将所提出的方法应用于文本分类的数据集,实验结果表明提出的方法比已有的单一视角比例标签学习方法更具优越性,具体表现在所提方法更高的分类准确率和更不易受数据噪声影响等方面。     

Information extraction from image sequences of real-world facial expressions

Information extraction of facial expressions deals with facial-feature detection, feature tracking, and capture of the spatiotemporal relationships among features. It is a fundamental task in facial expression analysis and will ultimately determine the performance of expression recognition. For a real-world facial expression sequence, there are three challenges: (1) detection failure of some or all facial features due to changes in illumination and rapid head movement; (2) nonrigid object tracking resulting from facial expression change; and (3) feature occlusion due to out-of-plane head rotation. In this paper, a new approach is proposed to tackle these challenges. First, we use an active infrared (IR) illumination to reliably detect pupils under variable lighting conditions and head orientations. The pupil positions are then used to guide the entire information-extraction process. The simultaneous use of a global head motion constraint and Kalman filtering can robustly track individual facial features even in condition of rapid head motion and significant expression change. To handle feature occlusion, we propose a warping-based reliability propagation method. The reliable neighbor features and the spatial semantics among these features are used to detect and infer occluded features through an interframe warping transformation. Experimental results show that accurate information extraction can be achieved for video sequences with real-world facial expressions.Received: 16 August 2003, Accepted: 20 September 2004, Published online: 20 December 2004 Correspondence to: Qiang Ji     

A normed measures of variability among proportions

A measure of variability among a set of proportions is developed. There are no distributional assumptions, so the measure, H, is applicable in a wide variety of situations. H is scaled so that its range is zero (all proportions are equal) to one (maximum variability among the proportions, given the weighted average). The measure can be interpreted as a distance: the value of H indicates the position of the proportions relative to the possible extremes of no variability or maximum variability. Any set of constant weights can be applied to the proportions: the weights are used to compute the weighted average proportion and are also used to determine the extent to which each proportion affects the variability measure. Comparisons are made to other measures of variability and a numerical example is given.     

心理学视角下的自动表情识别

自动表情识别是心理学与计算机科学等深度交叉的前沿领域。情绪心理学、模式识别、情感计算等领域的研究者发展表情识别相关的理论、数据库和算法,极大地推动了自动表情识别技术的进步。文章基于心理学视角,结合我们前期开展的相关工作,首先梳理自动表情识别的心理学基础、情绪的面部表达方式、表情数据的演化、表情样本的标注等方面的理论观点与实践进展,然后分析指出自动表情识别面临的主要问题,最后基于预测加工理论的建构观点,提出注重交互过程中的表情“理解”,有望进一步提高自动表情识别的有效性,并预期这可能是自动表情识别研究的未来发展方向。     

Facial attractiveness: beauty and the machine

This work presents a novel study of the notion of facial attractiveness in a machine learning context. To this end, we collected human beauty ratings for data sets of facial images and used various techniques for learning the attractiveness of a face. The trained predictor achieves a significant correlation of 0.65 with the average human ratings. The results clearly show that facial beauty is a universal concept that a machine can learn. Analysis of the accuracy of the beauty prediction machine as a function of the size of the training data indicates that a machine producing human-like attractiveness rating could be obtained given a moderately larger data set.