An effective methodology for dynamic 3D facial expression retrieval. (April 2016)

• Record Type: Journal Article
• Authors: Danelakis, Antonios; Theoharis, Theoharis; Pratikakis, Ioannis; Perakis, Panagiotis
• Is Part Of: Pattern recognition. Volume 52(2016:Apr.)
• Page Start: 174
• Page End: 185
• Publication Date: 2016-04
• Subjects: Dynamic 3D mesh sequence -- 3D object retrieval -- 4D facial expression retrieval -- 4D facial expression recognition; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.10.012
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: The problem of facial expression recognition in dynamic sequences of 3 D face scans has received a significant amount of attention in the recent past whereas the problem of retrieval in this type of data has not. A novel retrieval methodology for such data is introduced in this paper. The proposed methodology automatically detects specific facial landmarks and uses them to create a descriptor. This descriptor is the concatenation of three sub-descriptors which capture topological as well as geometric information of the 3 D face scans. The motivation behind the proposed hybrid facial expression descriptor is the fact that some facial expressions, like happiness and surprise, are characterized by obvious changes in the mouth topology while others, like anger, fear and sadness, produce geometric but no significant topological changes. The proposed retrieval scheme exploits the Dynamic Time Warping technique in order to compare descriptors corresponding to different 3 D facial sequences. A detailed evaluation of the introduced retrieval scheme is presented showing that it outperforms previous state-of-the-art retrieval schemes. Experiments have been conducted using the six prototypical expressions of the standard dataset BU -4 DFE and the eight prototypical expressions of the recently available dataset BP 4 D-Spontaneous . Finally, a majority voting scheme based on the retrieval results is used to achieve unsupervised dynamic 3 D facial expression recognition. The achieved classification accuracy is comparable to the state-of-the-art supervised dynamic 3 D facial expression recognition techniques. Abstract : Highlights: We illustrate a novel retrieval methodology for dynamic sequences of 3 D face scans. We present a detailed evaluation of the introduced retrieval scheme. BU-4DFE and BP4D-Spontaneous data sets were used for experiments. Retrieval results are used to achieve unsupervised facial expression recognition. The presented results outperform state-of-the-art retrieval schemes.