Alperen Kantarcı, Hazim Kemal Ekenel
Visible face recognition systems achieve nearly perfect recognition accuracies using deep learning. However, in lack of light, these systems perform poorly. A way to deal with this problem is thermal to visible cross-domain face matching. This is a desired technology because of its usefulness in night time surveillance. Nevertheless, due to differences between two domains, it is a very challenging face recognition problem. In this paper, we present a deep autoencoder based system to learn the mapping between visible and thermal face images. Also, we assess the impact of alignment in thermal to visible face recognition. For this purpose, we manually annotate the facial landmarks on the Carl and EURECOM datasets. The proposed approach is extensively tested on three publicly available datasets: Carl, UND-X1, and EURECOM. Experimental results show that the proposed approach improves the state-of-the-art significantly. We observe that alignment increases the performance by around 2%. Annotated facial landmark positions in this study can be downloaded from the following link: github.com/Alpkant/Thermal-to-Visible-Face-Recognition-Using-Deep-Autoencoders .
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Facial Recognition and Modelling | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| Facial Recognition and Modelling | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| Facial Recognition and Modelling | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |
| Face Reconstruction | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| Face Reconstruction | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| Face Reconstruction | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |
| Face Recognition | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| Face Recognition | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| Face Recognition | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |
| 3D | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| 3D | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| 3D | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |
| 3D Face Modelling | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| 3D Face Modelling | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| 3D Face Modelling | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |
| 3D Face Reconstruction | UND-X1 | Rank-1 | 87.2 | Model with Up Convolution + DoG Filter |
| 3D Face Reconstruction | Carl | Rank-1 | 85 | Model with Up Convolution + DoG Filter (Aligned) |
| 3D Face Reconstruction | EURECOM | Rank-1 | 88.33 | Model with Up Convolution + DoG Filter |