Loading...
Dictionary Representation of Deep Features for Occlusion-Robust Face Recognition
Cen, Feng Wang, Guanghui
Cen, Feng
Wang, Guanghui
Citations
Altmetric:
Abstract
Deep learning has achieved exciting results in face recognition; however, the accuracy is still unsatisfying for occluded faces. To improve the robustness for occluded faces, this paper proposes a novel deep dictionary representation-based classification scheme, where a convolutional neural network is employed as the feature extractor and followed by a dictionary to linearly code the extracted deep features. The dictionary is composed by a gallery part consisting of the deep features of the training samples and an auxiliary part consisting of the mapping vectors acquired from the subjects either inside or outside the training set and associated with the occlusion patterns of the testing face samples. A squared Euclidean norm is used to regularize the coding coefficients. The proposed scheme is computationally efficient and is robust to large contiguous occlusion. In addition, the proposed scheme is generic for both the occluded and non-occluded face images and works with a single training sample per subject. The extensive experimental evaluations demonstrate the superior performance of the proposed approach over other state-of-the-art algorithms.
Description
Date
2019-02-25
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers
Files
Loading...
Cen_2019.pdf
Adobe PDF, 22.36 MB
Research Projects
Organizational Units
Journal Issue
Keywords
Face recognition, Convolutional neural network, Occlusion-robust, Deep learning, Dictionary representation
Citation
F. Cen and G. Wang, "Dictionary Representation of Deep Features for Occlusion-Robust Face Recognition," in IEEE Access, vol. 7, pp. 26595-26605, 2019. doi: 10.1109/ACCESS.2019.2901376