Abstract
In this paper, we propose a robust and reliable face recognition model that incorporates depth information such as data from point clouds and depth maps into RGB image data to avoid false facial verification caused by face spoofing attacks while increasing the model’s performance. The proposed model is driven by the spatially adaptive convolution (SAC) block of SqueezeSegv3; this is the attention block that enables the model to weight features according to their importance of spatial location. We also utilize large‐margin loss instead of softmax loss as a supervision signal for the proposed method, to enforce high discriminatory power. In the experiment, the proposed model, which incorporates depth information, had 99.88% accuracy and an F1 score of 93.45%, outperforming the baseline models, which used RGB data alone.
Highlights
LiDAR, short for light detection and ranging, is a remote sensing technology similar to radar
Point cloud data spoofing attacks [1, 2] because pictures of people’s faces can be obtained on social media platforms without their consent, and these can be used by someone with malicious intent to steal a person’s identity. To prevent such face spoofing attacks, we propose a robust face recognition method that uses both RGB images and depth information such as those extracted from point clouds and depth maps produced by a LiDAR scanner
This paper has proposed a face recognition approach that considers depth information using point cloud data
Summary
LiDAR, short for light detection and ranging, is a remote sensing technology similar to radar. The difference is that radar uses radio waves to detect its surroundings, whereas LiDAR uses laser energy. When a LiDAR sensor directs a laser beam at an object, it can calculate the distance to the object by measuring the delay before the light is reflected back to it, making it possible to extract depth information for an object and display it in the form of a point cloud or depth map. Can LiDAR sensors estimate an object’s range and they can measure its shape with high accuracy and spatial resolution.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
