M. Kurosu (Ed.): Human-Computer Interaction, Part II, HCII 2014, LNCS 8511, pp. 739–749, 2014. © Springer International Publishing Switzerland 2014 Emotracking Digital Art Isabelle Hupont 1 , Eva Cerezo 2 , Sandra Baldassarri 2 , and Rafael Del-Hoyo 1 1 Multimedia Technologies Division, Aragon Institute of Technology, Zaragoza, Spain {ihupont,rdelhoyo,dabadia}@ita.es 2 GIGA AffectiveLab, University of Zaragoza, Zaragoza, Spain {ecerezo,sandra}@unizar.es Abstract. Art and emotions are intimately related. This work proposes the ap- plication to arts of Emotracker, a novel tool that mixes eye tracking technology and facial emotions detection to track user behaviour. This combination offers intuitive and highly visual possibilities of relating eye gaze, emotions and artis- tic contents. The results obtained after carrying out “5-second emotracking tests” over art illustrations and the use of the gathered information to create real-time artistic effects are presented. Keywords: affect analysis, gaze, face analysis, digital arts. 1 Introduction Affective Computing aims at developing intelligent systems able to provide a com- puter with the ability of recognizing, interpreting and processing human emotions [1]. Since the introduction of the term Affective Computing in the late 1990s, an increas- ing number of efforts towards automatic human affect extraction have been reported in the literature. Systems able to recognize human emotions from facial expressions, physiological signals, voice, text, etc. have been developed with high accuracy [2]. Independently of the channel -or channels- chosen to detect affect, most works still focus efforts on increasing the success rates in the emotion recognition task. Howev- er, other important issues have scarcely been studied, namely how to efficiently vi- sualize the extracted affective information, how to process it to improve the user’s experience in different applications or what is the best combination of channels de- pending on the information sought. In particular, the combination of user eye gaze and facial emotional information has been proved to have a great potential in measur- ing user perception, impact and/or engagement with digital contents [3]. One of the most subjective perceptual experiences is given by arts. Emotions and art are intimately related [4] and it is, perhaps, the unique and highly variable personal emotional perceptions elicited what makes art so attractive. The study of that percep- tions require the interaction between art and science, two fields that, with few notable exceptions have grown in parallel with only counted interactions. In spite of the im- pact that the scientific study of art could have, it is somehow understandable that such enterprise is only starting to take off [5, 6, 7]. On the one hand, art perception is too subjective and challenging for rigorous scientific exploration. On the other hand,