Name
Title | ||
|---|---|---|
Deformable Quaternion Gabor Convolutional Neural Network For Color Facial Expression Recognition |
Abstract | ||
|---|---|---|
In facial expression recognition (FER), convolutional neural networks (CNNs) have been shown great capability of learning features. In this paper, we propose a new CNN framework for FER in color images, which incorporates deformable Gabor filters into a quaternion CNN. Deformable Gabor filters reinforce the network's ability of extracting different orientations of facial wrinkles information. Quaternion CNNs have greater advantages over the regular CNNs in handling the coupling between color channels. The proposed deformable quaternion Gabor convolutional neural network (DQG-CNN) not only learns FER feature representation excellently, but also processes spectral correlation between color channels naturally. Moreover, it can also effectively reduce training complexity compared to other reference models. Experimental results on three benchmark color datasets Oulu-CASIA, MMI, and SFEW, demonstrate that the proposed DGQ-CNN outperforms other state-of-the-art methods clearly. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICIP40778.2020.9191349 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Facial expression recognition, Gabor filter, quaternion, convolutional neural network, color image processing | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lianghai Jin | 1 | 185 | 15.07 |
| Zhou Xiao | 2 | 84 | 19.21 |
| Hong Liu | 3 | 96 | 18.53 |
| Enmin Song | 4 | 176 | 24.53 |