Wang Zhihai, Wang Shuai, Yu Weixing, Gao Bo, Li Chenxi, Wang Tianxin
Key Laboratory of Spectral Imaging Technology, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, China.
Center of Mechanics Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 101408, China.
Sensors (Basel). 2025 Feb 5;25(3):952. doi: 10.3390/s25030952.
Traditional facial recognition is realized by facial recognition algorithms based on 2D or 3D digital images and has been well developed and has found wide applications in areas related to identification verification. In this work, we propose a novel live face detection (LFD) method by utilizing snapshot spectral imaging technology, which takes advantage of the distinctive reflected spectra from human faces. By employing a computational spectral reconstruction algorithm based on Tikhonov regularization, a rapid and precise spectral reconstruction with a fidelity of over 99% for the color checkers and various types of "face" samples has been achieved. The flat face areas were extracted exactly from the "face" images with Dlib face detection and Euclidean distance selection algorithms. A large quantity of spectra were rapidly reconstructed from the selected areas and compiled into an extensive database. The convolutional neural network model trained on this database demonstrates an excellent capability for predicting different types of "faces" with an accuracy exceeding 98%, and, according to a series of evaluations, the system's detection time consistently remained under one second, much faster than other spectral imaging LFD methods. Moreover, a pixel-level liveness detection test system is developed and a LFD experiment shows good agreement with theoretical results, which demonstrates the potential of our method to be applied in other recognition fields. The superior performance and compatibility of our method provide an alternative solution for accurate, highly integrated video LFD applications.
传统的面部识别是通过基于二维或三维数字图像的面部识别算法实现的，并且已经得到了很好的发展，并在身份验证相关领域得到了广泛应用。在这项工作中，我们提出了一种利用快照光谱成像技术的新型活体面部检测（LFD）方法，该技术利用了人脸独特的反射光谱。通过采用基于蒂霍诺夫正则化的计算光谱重建算法，对于颜色校验块和各种类型的“人脸”样本，实现了保真度超过99%的快速精确光谱重建。使用Dlib人脸检测和欧几里得距离选择算法从“人脸”图像中准确提取出平坦的面部区域。从选定区域快速重建大量光谱并汇编成一个广泛的数据库。在此数据库上训练的卷积神经网络模型具有出色的能力，能够预测不同类型的“人脸”，准确率超过98%，并且根据一系列评估，该系统的检测时间始终保持在一秒以内，比其他光谱成像LFD方法快得多。此外，还开发了一个像素级活体检测测试系统，LFD实验结果与理论结果吻合良好，这表明我们的方法在其他识别领域具有应用潜力。我们方法的卓越性能和兼容性为准确、高度集成的视频LFD应用提供了一种替代解决方案。
