Journal
IET COMPUTER VISION
Volume 11, Issue 8, Pages 675-682Publisher
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-cvi.2016.0505
Keywords
face recognition; feature extraction; learning (artificial intelligence); image representation; human computer interaction; matrix algebra; image classification; facial expression recognition; discriminative feature learning-based pixel difference representation; human-computer interaction; FER; discriminative feature descriptor; expression representation power improvement; discriminative feature matrix based pixel difference representation; DFM-based pixel difference representation; training samples; discriminative feature dictionary; DFD; vertical two-dimensional linear discriminant analysis; V-2DLDA; matrix representation; nearest neighbour classifier; NN classifier; query sample label; optimal projection matrix; facial expression database; CK plus database; KDEF database; CMU multiPIE database; LOSO scenario; discriminative feature protection
Funding
- National Natural Science Foundation of China [61071199]
- Natural Science Foundation of Hebei Province [F2016203422]
- Postgraduate Innovation Project of Hebei Province [CXZZBS2017051]
Ask authors/readers for more resources
Recently, researchers have proposed different feature descriptors to achieve robust performance for facial expression recognition (FER). However, finding a discriminative feature descriptor remains one of the critical tasks. In this paper, we propose a discriminative feature learning scheme to improve the representation power of expressions. First, we obtain a discriminative feature matrix (DFM) based pixel difference representation. Subsequently, all DFMs corresponding to the training samples are used to construct a discriminative feature dictionary (DFD). Next, DFD is projected on a vertical two-dimensional linear discriminant analysis in direction (V-2DLDA) space to compute between and within-class scatter because V-2DLDA works well with the DFD in matrix representation and achieves good efficiency. Finally, nearest neighbor (NN) classifier is used to determine the labels of the query samples. DFD represents the local feature changes that are robust to the expression, illumination et al. Besides, we exploit V-2DLDA to find an optimal projection matrix since it not only protects the discriminative features but reduces the dimensions. The proposed method achieves satisfying recognition results, reaching accuracy rates as high as 91.87% on CK+ database, 82.24% on KDEF database, and 78.94% on CMU Multi-PIE database in the LOSO scenario, which perform better than other comparison methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available