Automated Video-Based Capture of Crustacean Fisheries Data Using Low-Power Hardware.

This work investigates the application of Computer Vision to the problem of the automated counting and measuring of crabs and lobsters onboard fishing boats. The aim is to provide catch count and measurement data for these key commercial crustacean species. This can provide vital input data for stock assessment models, to enable the sustainable management of these species. The hardware system is required to be low-cost, have low-power usage, be waterproof, available (given current chip shortages), and able to avoid over-heating. The selected hardware is based on a Raspberry Pi 3A+ contained in a custom waterproof housing. This hardware places challenging limitations on the options for processing the incoming video, with many popular deep learning frameworks (even light-weight versions) unable to load or run given the limited computational resources. The problem can be broken into several steps: (1) Identifying the portions of the video that contain each individual animal; (2) Selecting a set of representative frames for each animal, e.g, lobsters must be viewed from the top and underside; (3) Detecting the animal within the frame so that the image can be cropped to the region of interest; (4) Detecting keypoints on each animal; and (5) Inferring measurements from the keypoint data. In this work, we develop a pipeline that addresses these steps, including a key novel solution to frame selection in video streams that uses classification, temporal segmentation, smoothing techniques and frame quality estimation. The developed pipeline is able to operate on the target low-power hardware and the experiments show that, given sufficient training data, reasonable performance is achieved.

Contact-Free Pulse Signal Extraction from Human Face Videos: A Review and New Optimized Filtering Approach.

In this chapter, we review methods for video-based heart monitoring, from classical signal processing approaches to modern deep learning methods. In addition, we propose a new method for learning an optimal filter that can overcome many of the problems that can affect classical approaches, such as light reflection and subject's movements, at a fraction of the training cost of deep learning approaches. Following the usual procedures for region of interest extraction and tracking, robust skin color estimation and signal pre-processing, we introduce a least-squares error optimal filter, learnt using an established training dataset to estimate the photoplethysmographic (PPG) signal more accurately from the measured color changes over time. This method not only improves the accuracy of heart rate measurement but also resulted in the extraction of a cleaner pulse signal, which could be integrated into many other useful applications such as human biometric recognition or recognition of emotional state. The method was tested on the DEAP dataset and showed improved performance over the best previous classical method on that dataset. The results obtained show that our proposed contact-free heart rate measurement method has significantly improved on existing methods.

Deep Segmentation of Point Clouds of Wheat.

The 3D analysis of plants has become increasingly effective in modeling the relative structure of organs and other traits of interest. In this paper, we introduce a novel pattern-based deep neural network, Pattern-Net, for segmentation of point clouds of wheat. This study is the first to segment the point clouds of wheat into defined organs and to analyse their traits directly in 3D space. Point clouds have no regular grid and thus their segmentation is challenging. Pattern-Net creates a dynamic link among neighbors to seek stable patterns from a 3D point set across several levels of abstraction using the K-nearest neighbor algorithm. To this end, different layers are connected to each other to create complex patterns from the simple ones, strengthen dynamic link propagation, alleviate the vanishing-gradient problem, encourage link reuse and substantially reduce the number of parameters. The proposed deep network is capable of analysing and decomposing unstructured complex point clouds into semantically meaningful parts. Experiments on a wheat dataset verify the effectiveness of our approach for segmentation of wheat in 3D space.

FFD: Fast Feature Detector.

Scale-invariance, good localization and robustness to noise and distortions are the main properties that a local feature detector should possess. Most existing local feature detectors find excessive unstable feature points that increase the number of keypoints to be matched and the computational time of the matching step. In this paper, we show that robust and accurate keypoints exist in the specific scale-space domain. To this end, we first formulate the superimposition problem into a mathematical model and then derive a closed-form solution for multiscale analysis. The model is formulated via difference-of-Gaussian (DoG) kernels in the continuous scale-space domain, and it is proved that setting the scale-space pyramid's blurring ratio and smoothness to 2 and 0.627, respectively, facilitates the detection of reliable keypoints. For the applicability of the proposed model to discrete images, we discretize it using the undecimated wavelet transform and the cubic spline function. Theoretically, the complexity of our method is less than 5% of that of the popular baseline Scale Invariant Feature Transform (SIFT). Extensive experimental results show the superiority of the proposed feature detector over the existing representative hand-crafted and learning-based techniques in accuracy and computational time. The code and supplementary materials can be found at https://github.com/mogvision/FFD.

3D surface texture analysis of high-resolution normal fields for facial skin condition assessment.

BACKGROUND: This paper investigates the use of a light stage to capture high-resolution, 3D facial surface textures and proposes novel methods to use the data for skin condition assessment. MATERIALS AND METHODS: We introduce new methods for analysing 3D surface texture using high-resolution normal fields and apply these to the detection and assessment of skin conditions in human faces, specifically wrinkles, pores and acne. The use of high-resolution normal maps as input to our texture measures enables us to investigate the 3D nature of texture, while retaining aspects of some well-known 2D texture measures. The main contributions are as follows: the introduction of three novel methods for extracting texture descriptors from high-resolution surface orientation fields; a comparative study of 2D and 3D skin texture analysis techniques; and an extensive data set of high-resolution 3D facial scans presenting various skin conditions, with human ratings as "ground truth." RESULTS: Our results demonstrate an improvement on state-of-the-art methods for the analysis of pores and comparable results to the state of the art for wrinkles and acne using a considerably more compact model. CONCLUSIONS: The use of high-resolution normal maps, captured by a light stage, and the methods described, represent an important new set of tools in the analysis of skin texture.

Colour plasticity in response to social context and parasitic infection in a self-fertilizing fish.

Many animal species rely on changes in body coloration to signal social dominance, mating readiness and health status to conspecifics, which can in turn influence reproductive success, social dynamics and pathogen avoidance in natural populations. Such colour changes are thought to be controlled by genetic and environmental conditions, but their relative importance is difficult to measure in natural populations, where individual genetic variability complicates data interpretation. Here, we studied shifts in melanin-related body coloration in response to social context and parasitic infection in two naturally inbred lines of a self-fertilizing fish to disentangle the relative roles of genetic background and individual variation. We found that social context and parasitic infection had a significant effect on body coloration that varied between genetic lines, suggesting the existence of genotype by environment interactions. In addition, individual variation was also important for some of the colour attributes. We suggest that the genetic background drives colour plasticity and that this can maintain phenotypic variation in inbred lines, an adaptive mechanism that may be particularly important when genetic diversity is low.

Facial Shape Analysis Identifies Valid Cues to Aspects of Physiological Health in Caucasian, Asian, and African Populations.

Facial cues contribute to attractiveness, including shape cues such as symmetry, averageness, and sexual dimorphism. These cues may represent cues to objective aspects of physiological health, thereby conferring an evolutionary advantage to individuals who find them attractive. The link between facial cues and aspects of physiological health is therefore central to evolutionary explanations of attractiveness. Previously, studies linking facial cues to aspects of physiological health have been infrequent, have had mixed results, and have tended to focus on individual facial cues in isolation. Geometric morphometric methodology (GMM) allows a bottom-up approach to identifying shape correlates of aspects of physiological health. Here, we apply GMM to facial shape data, producing models that successfully predict aspects of physiological health in 272 Asian, African, and Caucasian faces - percentage body fat (21.0% of variance explained), body mass index (BMI; 31.9%) and blood pressure (BP; 21.3%). Models successfully predict percentage body fat and blood pressure even when controlling for BMI, suggesting that they are not simply measuring body size. Predicted values of BMI and BP, but not percentage body fat, correlate with health ratings. When asked to manipulate the shape of faces along the physiological health variable axes (as determined by the models), participants reduced predicted BMI, body fat and (marginally) BP, suggesting that facial shape provides a valid cue to aspects of physiological health.

Social Preference in Preschoolers: Effects of Morphological Self-Similarity and Familiarity.

Adults prefer to interact with others that are similar to themselves. Even slight facial self-resemblance can elicit trust towards strangers. Here we investigate if preschoolers at the age of 5 years already use facial self-resemblance when they make social judgments about others. We found that, in the absence of any additional knowledge about prospective peers, children preferred those who look subtly like themselves over complete strangers. Thus, subtle morphological similarities trigger social preferences well before adulthood.

3D comparison of average faces in subjects with oral clefts.

This prospective cross-sectional, case-controlled morphometric study assessed three dimensional (3D) facial morphological differences between average faces of 103 children aged 8-12 years; 40 with unilateral cleft lip and palate (UCLP), 23 with unilateral cleft lip and alveolus (UCLA), 19 with bilateral cleft lip and palate (BCLP), 21 with isolated cleft palate (ICP), and 80 gender and age-matched controls. 3D stereophotogrammetric facial scans were recorded for each participant at rest. Thirty-nine landmarks were digitized for each scan, and x-, y-, z-coordinates for each landmark were extracted. A 3D photorealistic average face was constructed for each participating group and subjective and objective comparisons were carried out between each cleft and control average faces. Marked differences were observed between all groups. The most severely affected were groups where the lip and palate were affected and repaired (UCLP and UCLA). The group with midsagittal palatal deformity and repair (ICP) was the most similar to the control group. The results revealed that 3D shape analysis allows morphometric discrimination between subjects with craniofacial anomalies and the control group, and underlines the potential value of statistical shape analysis in assessing the outcomes of cleft lip and palate surgery, and orthodontic treatment.

Men's facial masculinity: when (body) size matters.

Recent studies suggest that judgments of facial masculinity reflect more than sexually dimorphic shape. Here, we investigated whether the perception of masculinity is influenced by facial cues to body height and weight. We used the average differences in three-dimensional face shape of forty men and forty women to compute a morphological masculinity score, and derived analogous measures for facial correlates of height and weight based on the average face shape of short and tall, and light and heavy men. We found that facial cues to body height and weight had substantial and independent effects on the perception of masculinity. Our findings suggest that men are perceived as more masculine if they appear taller and heavier, independent of how much their face shape differs from women's. We describe a simple method to quantify how body traits are reflected in the face and to define the physical basis of psychological attributions.

Looking like a leader-facial shape predicts perceived height and leadership ability.

Judgments of leadership ability from face images predict the outcomes of actual political elections and are correlated with leadership success in the corporate world. The specific facial cues that people use to judge leadership remain unclear, however. Physical height is also associated with political and organizational success, raising the possibility that facial cues of height contribute to leadership perceptions. Consequently, we assessed whether cues to height exist in the face and, if so, whether they are associated with perception of leadership ability. We found that facial cues to perceived height had a strong relationship with perceived leadership ability. Furthermore, when allowed to manually manipulate faces, participants increased facial cues associated with perceived height in order to maximize leadership perception. A morphometric analysis of face shape revealed that structural facial masculinity was not responsible for the relationship between perceived height and perceived leadership ability. Given the prominence of facial appearance in making social judgments, facial cues to perceived height may have a significant influence on leadership selection.

Three-dimensional gender differences in facial form of children in the North East of England.

The aim of the prospective cross-sectional morphometric study was to explore three dimensional (3D) facial shape and form (shape plus size) variation within and between 8- and 12-year-old Caucasian children; 39 males age-matched with 41 females. The 3D images were captured using a stereophotogrammeteric system, and facial form was recorded by digitizing 39 anthropometric landmarks for each scan. The x, y, z coordinates of each landmark were extracted and used to calculate linear and angular measurements. 3D landmark asymmetry was quantified using Generalized Procrustes Analysis (GPA) and an average face was constructed for each gender. The average faces were superimposed and differences were visualized and quantified. Shape variations were explored using GPA and PrincipalComponent Analysis. Analysis of covariance and Pearson correlation coefficients were used to explore gender differences and to determine any correlation between facial measurements and height or weight. Multivariate analysis was used to ascertain differences in facial measurements or 3D landmark asymmetry. There were no differences in height or weight between genders. There was a significant positive correlation between facial measurements and height and weight and statistically significant differences in linear facial width measurements between genders. These differences were related to the larger size of males rather than differences in shape. There were no age- or gender-linked significant differences in 3D landmark asymmetry. Shape analysis confirmed similarities between both males and females for facial shape and form in 8- to 12-year-old children. Any differences found were related to differences in facial size rather than shape.

Judging the health and attractiveness of female faces: is the most attractive level of facial adiposity also considered the healthiest?

Perceived facial adiposity plays an important role in perceptions of both facial attractiveness and health, but people might differentiate between the level of adiposity they find most attractive and healthy. The aim of this study was therefore to test whether or not similar levels of adiposity in faces were preferred for judgments of health and attractiveness. Fifty-three Caucasian university students were asked to make three-dimensional female faces appear as healthy and attractive as possible by changing faces along a continuum that portrays the facial adiposity change associated with a change in body mass index. Results showed that women preferred a significantly lower level of facial adiposity when judging attractiveness than when judging health, while men did not differentiate between the 'most attractive' and 'most healthy' looking level of facial adiposity. These findings are discussed in terms of the sociocultural portrayal of female body ideals and the preference for healthy individuals.

Facial cues of dominance modulate the short-term gaze-cuing effect in human observers.

Responding appropriately to gaze cues is essential for fluent social interaction, playing a crucial role in social learning, collaboration, threat assessment and understanding others' intentions. Previous research has shown that responses to gaze cues can be studied by investigating the gaze-cuing effect (i.e. the tendency for observers to respond more quickly to targets in locations that were cued by others' gaze than to uncued targets). A recent study demonstrating that macaques demonstrate larger gaze-cuing effects when viewing dominant conspecifics than when viewing subordinate conspecifics suggests that cues of dominance modulate the gaze-cuing effect in at least one primate species. Here, we show a similar effect of facial cues associated with dominance on gaze cuing in human observers: at short viewing times, observers demonstrated a greater cuing effect for gaze cues from masculinized (i.e. dominant) faces than from feminized (i.e. subordinate) faces. Moreover, this effect of facial masculinity on gaze cuing decreased as viewing time was increased, suggesting that the effect is driven by involuntary responses. Our findings suggest that the mechanisms that underpin reflexive gaze cuing evolved to be sensitive to facial cues of others' dominance, potentially because such differential gaze cuing promoted desirable outcomes from encounters with dominant individuals.

Emotional expression modulates perceived gaze direction.

Gaze perception is an important social skill, as it portrays information about what another person is attending to. Gaze direction has been shown to affect interpretation of emotional expression. Here the authors investigate whether the emotional facial expression has a reciprocal influence on interpretation of gaze direction. In a forced-choice yes-no task, participants were asked to judge whether three faces expressing different emotions (anger, fear, happiness, and neutral) in different viewing angles were looking at them or not. Happy faces were more likely to be judged as looking at the observer than were angry, fearful, or neutral faces. Angry faces were more often judged as looking at the observer than were fearful and neutral expressions. These findings are discussed on the background of approach and avoidance orientation of emotions and of the self-referential positivity bias.

Symmetry is related to sexual dimorphism in faces: data across culture and species.

BACKGROUND: Many animals both display and assess multiple signals. Two prominently studied traits are symmetry and sexual dimorphism, which, for many animals, are proposed cues to heritable fitness benefits. These traits are associated with other potential benefits, such as fertility. In humans, the face has been extensively studied in terms of attractiveness. Faces have the potential to be advertisements of mate quality and both symmetry and sexual dimorphism have been linked to the attractiveness of human face shape. METHODOLOGY/PRINCIPAL FINDINGS: Here we show that measurements of symmetry and sexual dimorphism from faces are related in humans, both in Europeans and African hunter-gatherers, and in a non-human primate. Using human judges, symmetry measurements were also related to perceived sexual dimorphism. In all samples, symmetric males had more masculine facial proportions and symmetric females had more feminine facial proportions. CONCLUSIONS/SIGNIFICANCE: Our findings support the claim that sexual dimorphism and symmetry in faces are signals advertising quality by providing evidence that there must be a biological mechanism linking the two traits during development. Such data also suggests that the signalling properties of faces are universal across human populations and are potentially phylogenetically old in primates.

Q-cgi: new techniques to assess variation in perception applied to facial attractiveness.

We present novel methods for assessing variation in the perception of subjective cues based on a fusion of Q-methodology with computer graphics techniques. Participants first Q-sort face stimuli based upon a subjective quality; a randomization-based statistic is then calculated to test whether groups of participants differ in their perception. Computer graphics are then used to extract and illustrate the differences in the manner which participants sorted so that the differences can be quantified. As a demonstration, the technique is applied to investigate the effects of prospective relationship duration and of sexual restrictiveness on the characteristics which participants find attractive in photographs of opposite-sex faces. Results show that in a naturally varying set of faces, female participants prefer facial cues related to masculinity for short-term relationships, whereas characteristics related to positive personality attributes are preferred for long-term relationships. For short-term relationships, male participants appear to prefer more feminine, youthful faces. Preferences of individuals with less restricted sexual strategy paralleled short-term preferences in that more feminine female faces and more masculine male faces were preferred.

Reproductive strategy, sexual development and attraction to facial characteristics.

Sexual reproduction strategies vary both between and within species in the level of investment in offspring. Life-history theories suggest that the rate of sexual maturation is critically linked to reproductive strategy, with high investment being associated with few offspring and delayed maturation. For humans, age of puberty and age of first sex are two developmental milestones that have been associated with reproductive strategies. Stress during early development can retard or accelerate sexual maturation and reproduction. Early age of menarche is associated with absence of younger siblings, absence of a father figure during early life and increased weight. Father absence during early life is also associated with early marriage, pregnancy and divorce. Choice of partner characteristics is critical to successful implementation of sexual strategies. It has been suggested that sexually dimorphic traits (including those evident in the face) signal high-quality immune function and reproductive status. Masculinity in males has also been associated with low investment in mate and offspring. Thus, women's reproductive strategy should be matched to the probability of male investment, hence to male masculinity. Our review leads us to predict associations between the rate of sexual maturation and adult preferences for facial characteristics (enhanced sexual dimorphism and attractiveness). We find for men, engaging in sex at an early age is related to an increased preference for feminized female faces. Similarly, for women, the earlier the age of first sex the greater the preference for masculinity in opposite-sex faces. When we controlled sexual dimorphism in male faces, the speed of sexual development in women was not associated with differences in preference for male facial attractiveness. These developmental influences on partner choice were not mediated by self-rated attractiveness or parental relationships. We conclude that individuals assort in preferences based on the rapidity of their sexual development. Fast developing individuals prefer opposite-sex partners with an increased level of sexually dimorphic facial characteristics.

Correlated preferences for facial masculinity and ideal or actual partner's masculinity.

Studies of women's preferences for male faces have variously reported preferences for masculine faces, preferences for feminine faces and no effect of masculinity-femininity on male facial attractiveness. It has been suggested that these apparently inconsistent findings are, at least partly, due to differences in the methods used to manipulate the masculinity of face images or individual differences in attraction to facial cues associated with youth. Here, however, we show that women's preferences for masculinity manipulated in male faces using techniques similar to the three most widely used methods are positively inter-related. We also show that women's preferences for masculine male faces are positively related to ratings of the masculinity of their actual partner and their ideal partner. Correlations with partner masculinity were independent of real and ideal partner age, which were not associated with facial masculinity preference. Collectively, these findings suggest that variability among studies in their findings for women's masculinity preferences reflects individual differences in attraction to masculinity rather than differences in the methods used to manufacture stimuli, and are important for the interpretation of previous and future studies of facial masculinity.

Facial attractiveness judgements reflect learning of parental age characteristics.

Mate preferences are shaped by infant experience of parental characteristics in a wide variety of species. Similar processes in humans may lead to physical similarity between parents and mates, yet this possibility has received little attention. The age of parents is one salient physical characteristic that offspring may attend to. The current study used computer-graphic faces to examine how preferences for age in faces were influenced by parental age. We found that women born to 'old' parents (over 30) were less impressed by youth, and more attracted to age cues in male faces than women with 'young' parents (under 30). For men, preferences for female faces were influenced by their mother's age and not their father's age, but only for long-term relationships. These data indicate that judgements of facial attractiveness in humans reflect the learning of parental characteristics.