A Hybrid Face Recognition Approach Using Local Appearance and Deep Models

Arı, Mert; Ekenel, Hazım Kemal

doi:10.1007/978-3-031-16210-7_17

Cited by 1 publication

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [30] proposed using a TV (thermal to visible)-GAN to apply existing face recognition models for visible light images to thermal images by transforming the thermal ones into visible light ones. Arl et al [31] proposed combining local features from block-based discrete cosine transformation and deep features from ResNet50 to enable the use of both thermal and visible light images as input for face recognition. This method is robust to changes in illumination and occlusion.…”

Section: Face Recognition Using Thermal Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Personal Authentication for Periocular Region in Thermal and Visible Light Images by Using CNN

Nakamura,

Kawamura,

Yoshiura

et al. 2024

Journal of Information Processing

View full text Add to dashboard Cite

Personal authentication based on the periocular region can be performed even when the person's mouth and nose are hidden by a face mask. However, using visible light images for periocular recognition is problematic because recognition accuracy is affected by changes in the lighting conditions. We have developed a method for periocular recognition that overcomes this problem by using thermal images, which are less affected by changes in lighting conditions, in addition to visible light images. In this paper, we propose a method using both thermal and visible light images for periocular recognition based on features obtained by CNN. In addition, our method uses deep metric learning to deal with persons who are not included in the training data. To evaluate the accuracy of the proposed method under unstable conditions, we conducted recognition experiments using images of 83 subjects obtained from the USTC-NVIE database, which contains visible light and thermal images taken simultaneously under various lighting conditions and with various facial expressions. The experimental results show that using both visible light and thermal images achieves higher recognition accuracy than using only visible light images.

show abstract

Section: Face Recognition Using Thermal Imagesmentioning

confidence: 99%

“…These previous studies [20], [21], [28], [29], [30], [31] have shown that the use of thermal images for face recognition improves robustness to changes in lighting conditions and improves accuracy. Therefore, the same effect can be expected in periocular authentication.…”

Section: Face Recognition Using Thermal Imagesmentioning

confidence: 99%