Facial expression classification: An approach based on the fusion of facial deformations using the transferable belief model

Hammal, Zakia; Couvreur, Laurent; Caplier, Alice; Rombaut, Michèle

doi:10.1016/j.ijar.2007.02.003

Cited by 70 publications

(61 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It includes several models of reasoning under uncertainty such as the Smets' Transferable Belief Model (TBM) [21]. It has been applied to several disciplines such as people tracking [22], fraud detection [23], classification [24], risk analysis [25], clustering [26,27], image processing [28,29,30,31], autonomous robot mapping [32], human-computer interaction [33], land mine detection [34] and driver assistance [35], amongst others.…”

Section: Keypoint Fusionmentioning

confidence: 99%

Keypoint descriptor fusion with Dempster–Shafer theory

Mondéjar-Guerra

Muñoz-Salinas

Marín-Jiménez

et al. 2015

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

Keypoint matching is the task of accurately finding the location of a scene point in two images. Many keypoint descriptors have been proposed in the literature aiming at providing robustness against scale, translation and rotation transformations, each having advantages and disadvantages. This paper proposes a novel approach to fuse the information from multiple keypoint descriptors using Dempster-Shafer Theory of evidence [1], which has proven particularly efficient in combining sources of information providing incomplete, imprecise, biased, and conflictive knowledge. The matching results of each descriptor are transformed into an evidence distribution on which a confidence factor is computed making use of its entropy. Then, the evidence distributions are fused using Dempster-Shafer Theory (DST), considering its confidence. As result of the fusion, a new evidence distribution that improves the result of the best descriptor is obtained. Our method has been tested with SIFT, SURF, ORB, BRISK and FREAK descriptors using all possible combinations of them. Results on the Oxford keypoint dataset [2] shows that the proposed approach obtains an improvement of up to 10% compared to the best one (FREAK).

show abstract

Section: Keypoint Fusionmentioning

confidence: 99%

Keypoint descriptor fusion with Dempster–Shafer theory

Mondéjar-Guerra

Muñoz-Salinas

Marín-Jiménez

et al. 2015

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

show abstract

“…When a categorical approach is used, the great majority of studies usually show a histogram or pie chart representing the distribution -percentages or confidence values-of the studied emotional labels at each time instant [13,14] as can be seen in Fig. 1a and 1b, respectively.…”

Section: B Affect Visualizationmentioning

confidence: 99%

The Emotracker: Visualizing Contents, Gaze and Emotions at a Glance

Hupont

Baldassarri

Cerezo

et al. 2013

2013 Humaine Association Conference on Affective Computing and Intelligent Interaction

View full text Add to dashboard Cite

In the last years, Affective Computing investigations have focused the efforts in the automatic extraction of human emotions and in increasing the success rates in the emotion recognition task. However, there is a lack of automatic tools that intuitively visualize the users' emotional information. In this work, we propose Emotracker, a novel tool based on the combination of eye tracking and facial emotional recognition technologies that allows the visualization of contents, user emotions and gaze at a glance, and offers a wide range of visualization options, including emotional saccade maps and emotional heat maps. The simultaneous consideration of gaze and emotion opens the door to the evaluation of user engagement, which is of great importance for content creators, but has also other promising fields of application in psychology research and, more specifically, in autism.

show abstract

“…In (Hammal et al, 2007) authors have modeled permanent features information by using the five specific distances defined in (Figure 2). In their work they proposed a description for each facial expression deduced from MPEG-4 description besides their own observations.…”

Section: Permanent Features Information Modelingmentioning

confidence: 99%