Cascaded Multi-level Transformed Dirichlet Process for Multi-pose Facial Expression Recognition. (12th March 2018)

• Record Type: Journal Article
• Authors: Mao, Qirong; Zhang, Feifei; Wang, Liangjun; Luo, Sidian; Dong, Ming
• Editors: Kokuer, Munevver
• Is Part Of: Computer journal. Volume 61:Number 11(2018)
• Page Start: 1605
• Page End: 1619
• Publication Date: 2018-03-12
• Subjects: facial expression recognition -- multi-level Transformed Dirichlet Process -- appearance features -- geometric constraints -- spatially coherent features; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxy016
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: As an essential way of human emotional behavior understanding, facial expression recognition (FER) has been studied extensively in recent years. However, the existing methods of FER are typically based on near-frontal face data. High-recognition accuracy for multi-pose FER continues to be a challenge. In this paper, we present a novel cascaded multi-level Transformed Dirichlet Process (cml-TDP) model for multi-pose FER. The top-level structure of the cml-TDP model has been carefully designed to make coarse-to-fine prediction, and the outputs of the model are fused for robust and accurate estimation at each level. There are three primary merits to cml-TDP. First, pose is explicitly introduced into cml-TDP so that separate training and parameter tuning for each pose is not required. Second, cml-TDP describes an image by its detected positions and appearance features to implicitly construct geometric constraints. Third, cml-TDP can learn an intermediate facial expression representation subject to geometric constraints. By sharing the pool of spatially coherent features over expressions and poses, we provide a scalable solution for multi-pose FER. The proposed model has been evaluated on two benchmark databases, BU-3DFE and RAFD, and achieved 79.33% and 75.00% FER accuracy on these two datasets, respectively, which has outperformed current state-of-the-art FER methods.