Robust facial expression analysis for affect-based interaction

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Interpretation of infant facial expression in the context of maternal postnatal depression

Postnatal maternal depression is associated with difficulties in maternal responsiveness. As most signals arising from the infant come from facial expressions one possible explanation for these difficulties is that mothers with postnatal depression are differentially affected by particular infant facial expressions. Thus, this study investigates the effects of postnatal depression on mothers’ perceptions of infant facial expressions. Participants (15 controls, 15 depressed and 15 anxious mothers) were asked to rate a number of infant facial expressions, ranging from very positive to very negative. Each face was shown twice, for a short and for a longer period of time in random order. Results revealed that mothers used more extreme ratings when shown the infant faces (i.e. more negative or more positive) for a longer period of time. Mothers suffering from postnatal depression were more likely to rate negative infant faces shown for a longer period more negatively than controls. The differences were specific to depression rather than an effect of general postnatal psychopathology—as no differences were observed between anxious mothers and controls. There were no other significant differences in maternal ratings of infant faces showed for short periods or for positive or neutral valence faces of either length. The findings that mothers with postnatal depression rate negative infant faces more negatively indicate that appraisal bias might underlie some of the difficulties that these mothers have in responding to their own infants signals.

Beta event-related desynchronization as an index of individual differences in processing human facial expression: further investigations of autistic traits in typically developing adults

The human mirror neuron system (hMNS) has been associated with various forms of social cognition and affective processing including vicarious experience. It has also been proposed that a faulty hMNS may underlie some of the deficits seen in the autism spectrum disorders (ASDs). In the present study we set out to investigate whether emotional facial expressions could modulate a putative EEG index of hMNS activation (mu suppression) and if so, would this differ according to the individual level of autistic traits [high versus low Autism Spectrum Quotient (AQ) score]. Participants were presented with 3 s films of actors opening and closing their hands (classic hMNS mu-suppression protocol) while simultaneously wearing happy, angry, or neutral expressions. Mu-suppression was measured in the alpha and low beta bands. The low AQ group displayed greater low beta event-related desynchronization (ERD) to both angry and neutral expressions. The high AQ group displayed greater low beta ERD to angry than to happy expressions. There was also significantly more low beta ERD to happy faces for the low than for the high AQ group. In conclusion, an interesting interaction between AQ group and emotional expression revealed that hMNS activation can be modulated by emotional facial expressions and that this is differentiated according to individual differences in the level of autistic traits. The EEG index of hMNS activation (mu suppression) seems to be a sensitive measure of the variability in facial processing in typically developing individuals with high and low self-reported traits of autism.

An optimized ERP brain–computer interface based on facial expression changes

Objective. Interferences from spatially adjacent non-target stimuli are known to evoke event-related potentials (ERPs) during non-target flashes and, therefore, lead to false positives. This phenomenon was commonly seen in visual attention-based brain–computer interfaces (BCIs) using conspicuous stimuli and is known to adversely affect the performance of BCI systems. Although users try to focus on the target stimulus, they cannot help but be affected by conspicuous changes of the stimuli (such as flashes or presenting images) which were adjacent to the target stimulus. Furthermore, subjects have reported that conspicuous stimuli made them tired and annoyed. In view of this, the aim of this study was to reduce adjacent interference, annoyance and fatigue using a new stimulus presentation pattern based upon facial expression changes. Our goal was not to design a new pattern which could evoke larger ERPs than the face pattern, but to design a new pattern which could reduce adjacent interference, annoyance and fatigue, and evoke ERPs as good as those observed during the face pattern. Approach. Positive facial expressions could be changed to negative facial expressions by minor changes to the original facial image. Although the changes are minor, the contrast is big enough to evoke strong ERPs. In this paper, a facial expression change pattern between positive and negative facial expressions was used to attempt to minimize interference effects. This was compared against two different conditions, a shuffled pattern containing the same shapes and colours as the facial expression change pattern, but without the semantic content associated with a change in expression, and a face versus no face pattern. Comparisons were made in terms of classification accuracy and information transfer rate as well as user supplied subjective measures. Main results. The results showed that interferences from adjacent stimuli, annoyance and the fatigue experienced by the subjects could be reduced significantly (p < 0.05) by using the facial expression change patterns in comparison with the face pattern. The offline results show that the classification accuracy of the facial expression change pattern was significantly better than that of the shuffled pattern (p < 0.05) and the face pattern (p < 0.05). Significance. The facial expression change pattern presented in this paper reduced interference from adjacent stimuli and decreased the fatigue and annoyance experienced by BCI users significantly (p < 0.05) compared to the face pattern.

Decreasing the interference of visual-based P300 BCI using facial expression changes

Interferences from the spatially adjacent non-target stimuli evoke ERPs during non-target sub-trials and lead to false positives. This phenomenon is commonly seen in visual attention based BCIs and affects the performance of BCI system. Although, users or subjects tried to focus on the target stimulus, they still could not help being affected by conspicuous changes of the stimuli (flashes or presenting images) which were adjacent to the target stimulus. In view of this case, the aim of this study is to reduce the adjacent interference using new stimulus presentation pattern based on facial expression changes. Positive facial expressions can be changed to negative facial expressions by minor changes to the original facial image. Although the changes are minor, the contrast will be big enough to evoke strong ERPs. In this paper, two different conditions (Pattern_1, Pattern_2) were used to compare across objective measures such as classification accuracy and information transfer rate as well as subjective measures. Pattern_1 was a “flash-only” pattern and Pattern_2 was a facial expression change of a dummy face. In the facial expression change patterns, the background is a positive facial expression and the stimulus is a negative facial expression. The results showed that the interferences from adjacent stimuli could be reduced significantly (P<;0.05) by using the facial expression change patterns. The online performance of the BCI system using the facial expression change patterns was significantly better than that using the “flash-only” patterns in terms of classification accuracy (p<;0.01), bit rate (p<;0.01), and practical bit rate (p<;0.01). Subjects reported that the annoyance and fatigue could be significantly decreased (p<;0.05) using the new stimulus presentation pattern presented in this paper.

An optimized ERP Brain-computer interface based on facial expression changes

OBJECTIVE: Interferences from spatially adjacent non-target stimuli are known to evoke event-related potentials (ERPs) during non-target flashes and, therefore, lead to false positives. This phenomenon was commonly seen in visual attention-based brain-computer interfaces (BCIs) using conspicuous stimuli and is known to adversely affect the performance of BCI systems. Although users try to focus on the target stimulus, they cannot help but be affected by conspicuous changes of the stimuli (such as flashes or presenting images) which were adjacent to the target stimulus. Furthermore, subjects have reported that conspicuous stimuli made them tired and annoyed. In view of this, the aim of this study was to reduce adjacent interference, annoyance and fatigue using a new stimulus presentation pattern based upon facial expression changes. Our goal was not to design a new pattern which could evoke larger ERPs than the face pattern, but to design a new pattern which could reduce adjacent interference, annoyance and fatigue, and evoke ERPs as good as those observed during the face pattern. APPROACH: Positive facial expressions could be changed to negative facial expressions by minor changes to the original facial image. Although the changes are minor, the contrast is big enough to evoke strong ERPs. In this paper, a facial expression change pattern between positive and negative facial expressions was used to attempt to minimize interference effects. This was compared against two different conditions, a shuffled pattern containing the same shapes and colours as the facial expression change pattern, but without the semantic content associated with a change in expression, and a face versus no face pattern. Comparisons were made in terms of classification accuracy and information transfer rate as well as user supplied subjective measures. MAIN RESULTS: The results showed that interferences from adjacent stimuli, annoyance and the fatigue experienced by the subjects could be reduced significantly (p < 0.05) by using the facial expression change patterns in comparison with the face pattern. The offline results show that the classification accuracy of the facial expression change pattern was significantly better than that of the shuffled pattern (p < 0.05) and the face pattern (p < 0.05). SIGNIFICANCE: The facial expression change pattern presented in this paper reduced interference from adjacent stimuli and decreased the fatigue and annoyance experienced by BCI users significantly (p < 0.05) compared to the face pattern.

Exploring combinations of different color and facial expression stimuli for gaze-independent BCIs

Background: Some studies have proven that a conventional visual brain computer interface (BCI) based on overt attention cannot be used effectively when eye movement control is not possible. To solve this problem, a novel visual-based BCI system based on covert attention and feature attention has been proposed and was called the gaze-independent BCI. Color and shape difference between stimuli and backgrounds have generally been used in examples of gaze-independent BCIs. Recently, a new paradigm based on facial expression changes has been presented, and obtained high performance. However, some facial expressions were so similar that users couldn't tell them apart, especially when they were presented at the same position in a rapid serial visual presentation (RSVP) paradigm. Consequently, the performance of the BCI is reduced. New Method: In this paper, we combined facial expressions and colors to optimize the stimuli presentation in the gaze-independent BCI. This optimized paradigm was called the colored dummy face pattern. It is suggested that different colors and facial expressions could help users to locate the target and evoke larger event-related potentials (ERPs). In order to evaluate the performance of this new paradigm, two other paradigms were presented, called the gray dummy face pattern and the colored ball pattern. Comparison with Existing Method(s): The key point that determined the value of the colored dummy faces stimuli in BCI systems was whether the dummy face stimuli could obtain higher performance than gray faces or colored balls stimuli. Ten healthy participants (seven male, aged 21–26 years, mean 24.5 ± 1.25) participated in our experiment. Online and offline results of four different paradigms were obtained and comparatively analyzed. Results: The results showed that the colored dummy face pattern could evoke higher P300 and N400 ERP amplitudes, compared with the gray dummy face pattern and the colored ball pattern. Online results showed that the colored dummy face pattern had a significant advantage in terms of classification accuracy (p < 0.05) and information transfer rate (p < 0.05) compared to the other two patterns. Conclusions: The stimuli used in the colored dummy face paradigm combined color and facial expressions. This had a significant advantage in terms of the evoked P300 and N400 amplitudes and resulted in high classification accuracies and information transfer rates. It was compared with colored ball and gray dummy face stimuli.

TR-2015001: A Survey and Critique of Facial Expression Synthesis in Sign Language Animation

Sign language animations can lead to better accessibility of information and services for people who are deaf and have low literacy skills in spoken/written languages. Due to the distinct word-order, syntax, and lexicon of the sign language from the spoken/written language, many deaf people find it difficult to comprehend the text on a computer screen or captions on a television. Animated characters performing sign language in a comprehensible way could make this information accessible. Facial expressions and other non-manual components play an important role in the naturalness and understandability of these animations. Their coordination to the manual signs is crucial for the interpretation of the signed message. Software to advance the support of facial expressions in generation of sign language animation could make this technology more acceptable for deaf people. In this survey, we discuss the challenges in facial expression synthesis and we compare and critique the state of the art projects on generating facial expressions in sign language animations. Beginning with an overview of facial expressions linguistics, sign language animation technologies, and some background on animating facial expressions, a discussion of the search strategy and criteria used to select the five projects that are the primary focus of this survey follows. This survey continues on to introduce the work from the five projects under consideration. Their contributions are compared in terms of support for specific sign language, categories of facial expressions investigated, focus range in the animation generation, use of annotated corpora, input data or hypothesis for their approach, and other factors. Strengths and drawbacks of individual projects are identified in the perspectives above. This survey concludes with our current research focus in this area and future prospects.

Cortical control of facial expression.

The present topical review deals with the motor control of facial expressions in humans. Facial expressions are a central part of human communication. Emotional face expressions have a crucial role in human non-verbal behavior, allowing a rapid transfer of information between individuals. Facial expressions can be both voluntarily or emotionally controlled. Recent studies in non-human primates and humans revealed that the motor control of facial expressions has a distributed neural representation. At least 5 cortical regions on the medial and lateral aspects of each hemisphere are involved: the primary motor cortex, the ventral lateral premotor cortex, the supplementary motor area on the medial wall, and, finally, the rostral and caudal cingulate cortex. The results of studies in humans and non-human primates suggest that the innervation of the face is bilaterally controlled for the upper part, and mainly contralaterally controlled for the lower part. Furthermore, the primary motor cortex, the ventral lateral premotor cortex, and the supplementary motor area are essential for the voluntary control of facial expressions. In contrast, the cingulate cortical areas are important for emotional expression, since they receive input from different structures of the limbic system. This article is protected by copyright. All rights reserved.

A facial expression for anxiety

Anxiety and fear are often confounded in discussions of human emotions. However, studies of rodent defensive reactions under naturalistic conditions suggest anxiety is functionally distinct from fear. Unambiguous threats, such as predators, elicit flight from rodents (if an escape-route is available), whereas ambiguous threats (e.g., the odor of a predator) elicit risk assessment behavior, which is associated with anxiety as it is preferentially modulated by anti-anxiety drugs. However, without human evidence, it would be premature to assume that rodent-based psychological models are valid for humans. We tested the human validity of the risk assessment explanation for anxiety by presenting 8 volunteers with emotive scenarios and asking them to pose facial expressions. Photographs and videos of these expressions were shown to 40 participants who matched them to the scenarios and labeled each expression. Scenarios describing ambiguous threats were preferentially matched to the facial expression posed in response to the same scenario type. This expression consisted of two plausible environmental-scanning behaviors (eye darts and head swivels) and was labeled as anxiety, not fear. The facial expression elicited by unambiguous threat scenarios was labeled as fear. The emotion labels generated were then presented to another 18 participants who matched them back to photographs of the facial expressions. This back-matching of labels to faces also linked anxiety to the environmental-scanning face rather than fear face. Results therefore suggest that anxiety produces a distinct facial expression and that it has adaptive value in situations that are ambiguously threatening, supporting a functional, risk-assessing explanation for human anxiety.

Seeing emotions in others: Improving cognitive and neuronal mechanisms of facial expression processing

In the conceptual framework of affective neuroscience, this thesis intends to advance the understanding of the plasticity mechanisms of other’s emotional facial expression representations. Chapter 1 outlines a description of the neurophysiological bases of Hebbian plasticity, reviews influential studies that adopted paired associative stimulation procedures, and introduces new lines of research where the impact of cortico-cortical paired associative stimulation protocols on higher order cognitive functions is investigated. The experiments in Chapter 2 aimed to test the modulatory influence of a perceptual-motor training, based on the execution of emotional expressions, on the subsequent emotion intensity judgements of others’ high (i.e., full visible) and low-intensity (i.e., masked) emotional expressions. As a result of the training-induced learning, participants showed a significant congruence effect, as indicated by relatively higher expression intensity ratings for the same emotion as the one that was previously trained. Interestingly, although judged as overall less emotionally intense, surgical facemasks did not prevent the emotion-specific effects of the training to occur, suggesting that covering the lower part of other’s face do not interact with the training-induced congruence effect. In Chapter 3 it was implemented a transcranial magnetic stimulation study targeting neural pathways involving re-entrant input from higher order brain regions into lower levels of the visual processing hierarchy. We focused on cortical visual networks within the temporo-occipital stream underpinning the processing of emotional faces and susceptible to plastic adaptations. Importantly, we tested the plasticity-induced effects in a state dependent manner, by administering ccPAS while presenting different facial expressions yet afferent to a specific emotion. Results indicated that the discrimination accuracy of emotion-specific expressions is enhanced following the ccPAS treatment, suggesting that a multi-coil TMS intervention might represent a suitable tool to drive brain remodeling at a neural network level, and consequently influence a specific behavior.

Electrophysiological and behavioural correlates of facial identity and expression perception deficits following a closed head injury /

A large variety of social signals, such as facial expression and body language, are conveyed in everyday interactions and an accurate perception and interpretation of these social cues is necessary in order for reciprocal social interactions to take place successfully and efficiently. The present study was conducted to determine whether impairments in social functioning that are commonly observed following a closed head injury, could at least be partially attributable to disruption in the ability to appreciate social cues. More specifically, an attempt was made to determine whether face processing deficits following a closed head injury (CHI) coincide with changes in electrophysiological responsivity to the presentation of facial stimuli. A number of event-related potentials (ERPs) that have been linked specifically to various aspects of visual processing were examined. These included the N170, an index of structural encoding ability, the N400, an index of the ability to detect differences in serially presented stimuli, and the Late Positivity (LP), an index of the sensitivity to affective content in visually-presented stimuli. Electrophysiological responses were recorded while participants with and without a closed head injury were presented with pairs of faces delivered in a rapid sequence and asked to compare them on the basis of whether they matched with respect to identity or emotion. Other behavioural measures of identity and emotion recognition were also employed, along with a small battery of standard neuropsychological tests used to determine general levels of cognitive impairment. Participants in the CHI group were impaired in a number of cognitive domains that are commonly affected following a brain injury. These impairments included reduced efficiency in various aspects of encoding verbal information into memory, general slower rate of information processing, decreased sensitivity to smell, and greater difficulty in the regulation of emotion and a limited awareness of this impairment. Impairments in face and emotion processing were clearly evident in the CHI group. However, despite these impairments in face processing, there were no significant differences between groups in the electrophysiological components examined. The only exception was a trend indicating delayed N170 peak latencies in the CHI group (p = .09), which may reflect inefficient structural encoding processes. In addition, group differences were noted in the region of the N100, thought to reflect very early selective attention. It is possible, then, that facial expression and identity processing deficits following CHI are secondary to (or exacerbated by) an underlying disruption of very early attentional processes. Alternately the difficulty may arise in the later cognitive stages involved in the interpretation of the relevant visual information. However, the present data do not allow these alternatives to be distinguished. Nonetheless, it was clearly evident that individuals with CHI are more likely than controls to make face processing errors, particularly for the more difficult to discriminate negative emotions. Those working with individuals who have sustained a head injury should be alerted to this potential source of social monitoring difficulties which is often observed as part of the sequelae following a CHI.

Sensitivity to differences between posed and genuine facial expressions : are children easily fooled? /

Adults and children can discriminate various emotional expressions, although there is limited research on sensitivity to the differences between posed and genuine expressions. Adults have shown implicit sensitivity to the difference between posed and genuine happy smiles in that they evaluate T-shirts paired with genuine smiles more favorably than T-shirts paired with posed smiles or neutral expressions (Peace, Miles, & Johnston, 2006). Adults also have shown some explicit sensitivity to posed versus genuine expressions; they are more likely to say that a model i?,feeling happy if the expression is genuine than posed. Nonetheless they are duped by posed expressions about 50% of the time (Miles, & Johnston, in press). There has been no published study to date in which researchers report whether children's evaluation of items varies with expression and there is little research investigating children's sensitivity to the veracity of facial expressions. In the present study the same face stimuli were used as in two previous studies (Miles & Johnston, in press; Peace et al., 2006). The first question to be addressed was whether adults and 7-year-olds have a cognitive understanding of the differences between posed and genuine happiness {scenario task). They evaluated the feelings of children who expressed gratitude for a present that they did or did not want. Results indicated that all participants had a fundamental understanding of the difference between real and posed happiness. The second question involved adults' and children's implicit sensitivity to the veracity of posed and genuine smiles. Participants rated and ranked beach balls paired with faces showing posed smiles, genuine smiles, and neutral expressions. Adults ranked.but did not rate beach balls paired with genuine smiles more favorably than beach balls paired with posed smiles. Children did not demonstrate implicit sensitivity as their ratings and rankings of beach balls did not vary with expressions; they did not even rank beach balls paired with genuine expressions higher than beach balls paired with neutral expressions. In the explicit (show/feel) task, faces were presented without the beach balls and participants were first asked whether each face was showing happy and then whether each face wasfeeling happy. There were also two matching trials that presented two faces at once; participants had to indicate which person was actuallyfeeling happy. In the show condition both adults and 7-year-olds were very accurate on genuine and neutral expressions but made some errors on posed smiles. Adults were fooled about 50% of the time by posed smiles in thefeel condition (i.e., they were likely to say that a model posing happy was really feeling happy) and children were even less accurate, although they showed weak sensitivity to posed versus genuine expressions. Future research should test an older age group of children to determine when explicit sensitivity to posed versus genuine facial expressions becomes adult-like and modify the ranking task to explore the influence of facial expressions on object evaluations.