A fear detection method based on palpebral fissure Rawinan Praditsangthong, Bhattarasiri Slakkham, Pattarasinee Bhattarakosol ⇑ Department of Mathematics and Computer Science, Chulalongkorn University, Thailand article info Article history: Received 15 December 2018 Revised 30 April 2019 Accepted 1 June 2019 Available online xxxx Keywords: Interpalpebral fissure Palpebral fissure region Eye Emotion Decision tree Classification abstract Human emotions, such as smiling or laughing, can be expressed in various forms through the face when- ever there are stimuli. These changing faces can reflect the emotional states that are used to identify a normal or an abnormal behaviour. This research aims to study the patterns in human faces and identify the areas of interest (AOI), which is called Facial Landmark Detection (FLD). The investigation of the external elements of eyes is performed, and it consists of the interpalpebral fissure (IPF), the palpebral fissure length (PFL), and the palpebral fissure region (PFR). These elements are applied to classify the emotional differences between neutral and fearful emotions. A method for emotional classification was designed according to the changing values of the IPF, PFL, and PFR. An ID3 algorithm was used to classify the emotions. Three hundred sixty images were derived from horror-thriller-murder movies based on IMDb. This data set was utilized to generate the proposed pattern. This pattern was used to classify the emotions using a decision tree technique that led to the development of an emotional classification model. The accuracy of the emotional classification model between neutral and fearful emotions was 92.50%, thus proving that the proposed model is efficient. Ó 2019 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 1. Introduction The expression of human emotion consists of positive emotions and negative emotions, such as happiness, sadness, pride, anger, and fear. Moreover, most psychologists (Manssuer et al., 2016; Eva et al., 2016; Trojano et al., 2012; Corey and Komogortsev, 2011) believe that human actions are defined by the rudimentary emotions. Generally, a person can express emotions through their eyes and various actions, such as gazes, fixations, saccades, pupil locations, pupil dilations, or blinking. These actions can be used to classify human emotions. Various approaches, such as the Haar cascade, convolutional neural network (CNN), corneal reflection, projection function, or edge analysis (EA) (Soleymani et al., 2016; Khan et al., 2016; Almudhahka et al., 2016), can be applied to detect and classify human emotions. In addition, some studies use a low cost high-performance camera to detect the eye move- ments (Fuhl et al., 2016; Polatsek and ‘‘Eye, 2013; Papernot et al., 2016; Devahasdin Na Ayudhya and Srinark, 2009; Lopez- Basterretxea et al., 2015). Nevertheless, there are some limitations. For example, when the front camera of tablet is used to detect the pupil dilation or pupil size, the distance from the tablet is only 30 cm (Polatsek and ‘‘Eye, 2013; Huabiao et al., 2013; Patnik et al., 2017). One interesting region of the eyes is the palpebral fissure (PF), which is the elliptical space between the eye lids (Lu et al., 2016). Emotional changes can affect to the distance between the top edge and the bottom edge of the eye lids, which is called the interpalpebral fissure (IPF). These changes can be used to detect human emotions. Fig. 1 shows the emotional flow where the causes of each emotion are important subjects since there is no emotion, without the cause. Additionally, positive stimuli result in positive emotions, but negative stimuli result in negative emotions. This research focus on an emotional detection using the palpe- bral fissure. The objective of the study was to investigate the inter- palpebral fissure and the palpebral fissure regions in order to analyse and classify neutral and fearful emotions. 2. Related work Human emotions refer to the immediate expression of feelings in a situation with stimulus (Izard, 2013). Human emotions can be https://doi.org/10.1016/j.jksuci.2019.06.001 1319-1578/Ó 2019 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). ⇑ Corresponding author. E-mail addresses: rawinan.p@student.chula.ac.th (R. Praditsangthong), 6072620623@student.chula.ac.th (B. Slakkham), pattarasinee.b@chula.ac.th (P. Bhattarakosol). Peer review under responsibility of King Saud University. Production and hosting by Elsevier Journal of King Saud University – Computer and Information Sciences xxx (xxxx) xxx Contents lists available at ScienceDirect Journal of King Saud University – Computer and Information Sciences journal homepage: www.sciencedirect.com Please cite this article as: R. Praditsangthong, B. Slakkham and P. Bhattarakosol, A fear detection method based on palpebral fissure, Journal of King Saud University – Computer and Information Sciences, https://doi.org/10.1016/j.jksuci.2019.06.001