Measuring Facial Emotional Expressions Using Genetic Programming

Loizides, A.; Slater, Mel; Langdon, William B.

doi:10.1007/978-1-4471-0123-9_46

Cited by 8 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the real images, we used landmark points manually selected from the same data as in [1], with five expressions (Neutral, Angry, Happy, Sad & Surprised) sampled at 13 different poses (∼ 5 • intervals from ∼ −30 • to ∼ +30 • where 0 • corresponds to the frontal view) giving 65 sets of points in total. For the synthetic data, we utilized the 3D head model of Loizides et al [12] to generate images of a face. A subset of the 3D model points was manually selected as landmarks.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Enforcing a Shape Correspondence between Two Views of a 3D Non-rigid Object

Dias

Buxton

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We have developed an algorithm capable of enforcing a shape correspondence between two views of the same object in different shapestates. This algorithm, together with several other significant updates, has helped improve the performance of the Integrated Shape and Pose Model (ISPM) described in [1] by a factor of 10. The ISPM utilizes two flexible basis views to integrate the linear combination of views technique with a coupled-view Flexible Shape Model (FSM) [2]. As a proof-ofprinciple we have evaluated the performance of the improved ISPM in comparison to that of its predecessor [1] and of the conventional FSM [3], via two different databases. The results show that, unlike the FSM, the current ISPM is view-invariant and that, on average, it out-performs the FSM. It also out-performs the initial ISPM described in [1].

show abstract

Section: Discussionmentioning

confidence: 99%

“…Acknowledgements. We thank Andreas Loizides for providing the 3D model used in [12]. We also thank Matthew Trotter for his helpful comments and suggestions on evaluating our model.…”

mentioning

confidence: 99%

Enforcing a Shape Correspondence between Two Views of a 3D Non-rigid Object

Dias

Buxton

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…They act as a communication channel about individual intentions and actions (Desmet, 2018). Facial Action Coding System (Ekman & Friesen, 2003), Genetic Programming (Loizides, Slater & Langdon, 2002), Maximally Discriminative Facial Moving Coding System (Izard, 1979), and the AMUSE tool (Chateau & Mersiol, 2005) are some of the well-established quantitative approaches of data collection in usability testing studies. These studies quantify emotions using scale techniques proposed by Ekman (2007) on recognised key expressions such as happiness, sadness, anger, neutral, fear, surprise and disgust.…”

Section: Thought-action Tendenciesmentioning

confidence: 99%

A UX Pedagogy on Multimodal Aspects of Emotions

Moradi¹,

Sosa²,

Hunting³

2019

Insider Knowledge - Proceedings of the Design Research Society Learn X Design Conference, 2019

View full text Add to dashboard Cite

Everyday products are becoming increasingly complex, at a time when the population is progressively ageing. These trends highlight the importance of teaching future designers to create inclusive and meaningful experiences for ageing users interacting with digital technologies and smart products. This paper presents a pedagogical approach to evaluate and analyse the affective interaction with smart products. Through the development of active problem-solving scenarios, students learn to understand the multidimensional aspects of emotions and cultivate the skills and dispositions needed to empathise with users. The training requires students to capture users' emotions through mixed methods and visually analyse the data in ways that are adapted from the initial stages of a PhD research project and grounded in the literature. Visualisations seek to enhance students' knowledge of how these methods can provide complementary information and how to analyse and interpret the collected data. The proposed model seeks to inform design education on effective ways to design with new technologies for more meaningful and positive emotional experiences.

show abstract

“…The second data set was then used to verify the equations formed, and high positive correlations (all above ¼ ) were found between the results from the equation produced and the subjective evaluations. We use these estimated regression equations [15] to measure the emotional expressions for the method we describe here. Note that this data analysis on generated faces only had to be done once, and the results can be used in any number of different visualisations.…”

Section: Measuring Emotional Expressionsmentioning

confidence: 99%

The empathic visualisation algorithm (EVA) - an automatic mapping from abstract data to naturalistic visual structure

Loizides

Slater

Proceedings Sixth International Conference on Information Visualisation

Self Cite

View full text Add to dashboard Cite

This paper demonstrates a technique for visualising multidimensional data sets holistically. The EVA algorithm provides an automatic mapping from semantically important features of the data to emotionally or perceptually significant features of the corresponding visual structure (such as a face). In other words a single glance at the visual structure informs the observer of the global state of the data, since the visual structure has an emotional impact on the observer. The visualisation is designed to correspond to the impact that would have been generated had the observer been able to access the relevant semantics of the underlying data.

show abstract

Measuring Facial Emotional Expressions Using Genetic Programming

Cited by 8 publications

References 2 publications

Enforcing a Shape Correspondence between Two Views of a 3D Non-rigid Object

Enforcing a Shape Correspondence between Two Views of a 3D Non-rigid Object

A UX Pedagogy on Multimodal Aspects of Emotions

The empathic visualisation algorithm (EVA) - an automatic mapping from abstract data to naturalistic visual structure

Contact Info

Product

Resources

About