Dataset Information

Towards Machine Recognition of Facial Expressions of Pain in Horses.

ABSTRACT: Automated recognition of human facial expressions of pain and emotions is to a certain degree a solved problem, using approaches based on computer vision and machine learning. However, the application of such methods to horses has proven difficult. Major barriers are the lack of sufficiently large, annotated databases for horses and difficulties in obtaining correct classifications of pain because horses are non-verbal. This review describes our work to overcome these barriers, using two different approaches. One involves the use of a manual, but relatively objective, classification system for facial activity (Facial Action Coding System), where data are analyzed for pain expressions after coding using machine learning principles. We have devised tools that can aid manual labeling by identifying the faces and facial keypoints of horses. This approach provides promising results in the automated recognition of facial action units from images. The second approach, recurrent neural network end-to-end learning, requires less extraction of features and representations from the video but instead depends on large volumes of video data with ground truth. Our preliminary results suggest clearly that dynamics are important for pain recognition and show that combinations of recurrent neural networks can classify experimental pain in a small number of horses better than human raters.

SUBMITTER: Andersen PH

PROVIDER: S-EPMC8229776 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Towards Machine Recognition of Facial Expressions of Pain in Horses.

Andersen Pia Haubro PH Broomé Sofia S Rashid Maheen M Lundblad Johan J Ask Katrina K Li Zhenghong Z Hernlund Elin E Rhodin Marie M Kjellström Hedvig H

Animals : an open access journal from MDPI 20210601 6

Automated recognition of human facial expressions of pain and emotions is to a certain degree a solved problem, using approaches based on computer vision and machine learning. However, the application of such methods to horses has proven difficult. Major barriers are the lack of sufficiently large, annotated databases for horses and difficulties in obtaining correct classifications of pain because horses are non-verbal. This review describes our work to overcome these barriers, using two differe ...[more]

PMID: 34206077

Similar Datasets

Project description:Facial mimicry is commonly defined as the tendency to imitate-at a sub-threshold level-facial expressions of other individuals. Numerous studies support a role of facial mimicry in recognizing others' emotions. However, the underlying functional mechanism is unclear. A prominent hypothesis considers facial mimicry as based on an action-perception loop, leading to the prediction that facial mimicry should be observed only when processing others' facial expressions. Nevertheless, previous studies have also detected facial mimicry during observation of emotional bodily expressions. An emergent alternative hypothesis is that facial mimicry overtly reflects the simulation of an "emotion", rather than the reproduction of a specific observed motor pattern. In the present study, we tested whether blocking mimicry ("Bite") on the lower face disrupted recognition of happy expressions conveyed by either facial or body expressions. In Experiment 1, we tested participants' ability to identify happy, fearful and neutral expressions in the Bite condition and in two control conditions. In Experiment 2, to ensure that such a manipulation selectively affects emotion recognition, we tested participants' ability to recognize emotional expressions, as well as the actors' gender, under the Bite condition and a control condition. Finally, we investigated the relationship between dispositional empathy and emotion recognition under the condition of blocked mimicry. Our findings demonstrated that blocking mimicry on the lower face hindered recognition of happy facial and body expressions, while the recognition of neutral and fearful expressions was not affected by the mimicry manipulation. The mimicry manipulation did not affect the gender discrimination task. Furthermore, the impairment of happy expression recognition correlated with empathic traits. These results support the role of facial mimicry in emotion recognition and suggest that facial mimicry reflects a global sensorimotor simulation of others' emotions rather than a muscle-specific reproduction of an observed motor expression.

Project description:Horses have the ability to generate a remarkable repertoire of facial expressions, some of which have been linked to the affective component of pain. This study describes the facial expressions in healthy horses free of pain before and during transportation and social isolation, which are putatively stressful but ordinary management procedures. Transportation was performed in 28 horses by subjecting them to short-term road transport in a horse trailer. A subgroup (n = 10) of these horses was also subjected to short-term social isolation. During all procedures, a body-mounted, remote-controlled heart rate monitor provided continuous heart rate measurements. The horses' heads were video-recorded during the interventions. An exhaustive dataset was generated from the selected video clips of all possible facial action units and action descriptors, time of emergency, duration, and frequency according to the Equine Facial Action Coding System (EquiFACS). Heart rate increased during both interventions (p<0.01), confirming that they caused disruption in sympato-vagal balance. Using the current method for ascribing certain action units (AUs) to specific emotional states in humans and a novel data-driven co-occurrence method, the following facial traits were observed during both interventions: eye white increase (p<0.001), nostril dilator (p<0.001), upper eyelid raiser (p<0.001), inner brow raiser (p = 0.042), tongue show (p<0.001). Increases in 'ear flicker' (p<0.001) and blink frequency (p<0.001) were also seen. These facial actions were used to train a machine-learning classifier to discriminate between the high-arousal interventions and calm horses, which achieved at most 79% accuracy. Most facial features identified correspond well with previous findings on behaviors of stressed horses, for example flared nostrils, repetitive mouth behaviors, increased eye white, tongue show, and ear movements. Several features identified in this study of pain-free horses, such as dilated nostrils, eye white increase, and inner brow raiser, are used as indicators of pain in some face-based pain assessment tools. In order to increase performance parameters in pain assessment tools, the relations between facial expressions of stress and pain should be studied further.

Dataset Information

Towards Machine Recognition of Facial Expressions of Pain in Horses.

Publications

Towards Machine Recognition of Facial Expressions of Pain in Horses.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets