Abstract
Conventional nighttime face detection studies mostly use near-infrared (NIR) light cameras or thermal cameras, which are robust to environmental illumination variation and low illumination. However, for the NIR camera, it is difficult to adjust the intensity and angle of the additional NIR illuminator according to its distance from an object. As for the thermal camera, it is expensive to use as a surveillance camera. For these reasons, we propose a nighttime face detection method based on deep learning using a single visible-light camera. In a long-distance night image, it is difficult to detect faces directly from the entire image due to noise and image blur. Therefore, we propose Two-Step Faster region-based convolutional neural network (R-CNN) based on the image preprocessed by histogram equalization (HE). As a two-step scheme, our method sequentially performs the detectors of body and face areas, and locates the face inside a limited body area. By using our two-step method, the processing time by Faster R-CNN can be reduced while maintaining the accuracy of face detection by Faster R-CNN. Using a self-constructed database called Dongguk Nighttime Face Detection database (DNFD-DB1) and an open database of Fudan University, we proved that the proposed method performs better compared to other existing face detectors. In addition, the proposed Two-Step Faster R-CNN outperformed single Faster R-CNN and our method with HE showed higher accuracies than those without our preprocessing in nighttime face detection.
Highlights
Existing studies of face detection are conducted mainly on visible-light images that are captured during daytime
The performance of the Two-Step Faster region-based convolutional neural network (R-convolutional neural network (CNN)) was measured using DNFD-DB1 [36], which was constructed as the first database in this study
By applying histogram equalization (HE) in the preprocessing, the visibility of the face was improved owing to the increased contrast between the face and the background, and the enhanced detection performance was proved through experiments
Summary
Existing studies of face detection are conducted mainly on visible-light images that are captured during daytime. The adaptive boosting (adaboost) [1] algorithm, which is the first developed algorithm in the field of face detection, can perform face detection in real time. This is followed by face detection methods based on hand-crafted features, such as histogram of oriented gradients (HOG) and local binary pattern (LBP) [2,3,4,5]. CNN-based face detection methods have been actively researched. As most face detection methods use a database with images captured using a visible-light camera, it is difficult to detect faces at nighttime when the intensity of illumination is low.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.