Topic
Facial expression
About: Facial expression is a research topic. Over the lifetime, 17085 publications have been published within this topic receiving 639905 citations. The topic is also known as: expression.
Papers published on a yearly basis
Papers
More filters
Posted Content•
TL;DR: In this paper, the authors proposed the use of Continual Learning (CL) in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems while guarding against biases arising from skewed data distributions.
Abstract: As Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of aiming at higher individual accuracy scores. Ranging from surveillance systems to diagnosing mental and emotional health conditions of individuals, these systems need to balance the accuracy vs fairness trade-off to make decisions that do not unjustly discriminate against specific under-represented demographic groups. Identifying bias as a critical problem in facial analysis systems, different methods have been proposed that aim to mitigate bias both at data and algorithmic levels. In this work, we propose the novel usage of Continual Learning (CL), in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of FER systems while guarding against biases arising from skewed data distributions. We compare different non-CL-based and CL-based methods for their classification accuracy and fairness scores on expression recognition and Action Unit (AU) detection tasks using two popular benchmarks, the RAF-DB and BP4D datasets, respectively. Our experimental results show that CL-based methods, on average, outperform other popular bias mitigation techniques on both accuracy and fairness metrics.
7 citations
01 Jan 2003
TL;DR: It is shown that, somewhat counter-intuitively, robustness to facial expressions can be increased by applying random perturbations to the positions of feature points in the database of face templates.
Abstract: Face recognition systems based on elastic graph matching work by comparing the positions and image neighborhoods of a number of detected feature points on faces in input images with those in a database of preregistered face templates. Such systems can absorb a degree of deformation of input faces due for example to facial expression, but may generate recognition errors if the deformation becomes significantly large. We show that, somewhat counter-intuitively, robustness to facial expressions can be increased by applying random perturbations to the positions of feature points in the database of face templates. We present experimental results on video sequences of people smiling and talking, and discuss the probable origin of the observed effect.
7 citations
Patent•
19 Dec 2017
TL;DR: In this article, a method for neonatal pain identification based on facial expression analysis was proposed, which can identify whether a newborn is painful or not, by extracting facial dynamic geometric features and facial dynamic texture features that represent dynamic changes in pain facial expressions.
Abstract: The present invention provides a neonatal pain identification method based on facial expression analysis, which can identify whether a newborn is painful or not. The method comprises: obtaining a video sequence containing facial information of a human face; extracting facial dynamic geometric features and facial dynamic texture features that represent dynamic changes in pain facial expressions from the obtained video sequence; carrying out feature fusion on the extracted facial dynamic geometric features and the facial dynamic texture feature, and carrying out dimension reduction on a facial feature vector obtained after the fusion; and according to the facial feature vector obtained after the dimension reduction, training a classifier. The present invention relates to the technical field of pattern identification and biomedicine.
7 citations
01 Jan 2005
TL;DR: In this paper, the impact of sociodemographic variables on emotional processes was analyzed using the recently developed emotion recognition (VERT 160) and memory for emotional faces tasks (VIEMER).
Abstract: Recognising emotions in facial expressions is a congenital and cross-cultural ability with immen- se social relevance. Compared to emotion recognition, little is known about the memory for emotional faces. To survey possible influencing factors, such as gender or age, 278 persons participated in an investi- gation using the recently developed emotion recognition (VERT 160) and memory for emotional faces tasks (VIEMER). The analysis of the data shows no significant gender effects. There is, however, a significant influence of age, to the extent that younger people show better performance. Happiness is the best recog- nised emotion and posers showing happy faces are also best remembered. In summary, the presented results support the necessity to analysing the impact of sociodemographic variables on emotional processes.
7 citations
01 Sep 2008
TL;DR: Experimental results suggested that the generation method of a subjectspecific emotional feature space using the Self-Organizing Map and the Counter Propagation Network was useful to estimate strength and mixture level of six basic emotions.
Abstract: This paper proposes a generation method of a subjectspecific emotional feature space using the Self-Organizing Map and the Counter Propagation Network. The feature space expresses the correspondence relationship between the change of facial expression pattern and the strength of emotion on the two-dimensional space centering on ldquopleasantnessrdquo and ldquoarousalrdquo. Experimental results suggested that our method was useful to estimate strength and mixture level of six basic emotions.
7 citations