Face Recognition 使用的是 C++ 开源库 dlib 通过深度学习模型构建的先进人脸识别系统,可通过 Python 接口或命令行工具对图片中的人脸进行识别。在 Labeled Faces in the Wild 人脸数据集中进行测试,准确率高达99.38%。
Benchmarks Timings at 240p: - Face locations: 0.0819s - Face landmarks: 0.0029s - Encode face : 0.4879s - End-to-end: 0.5978s Timings at 480p: - Face locations: 0.3257s - Face landmarks: 0.0028s - Encode face : 0.4959s - End-to-end: 0.8203s Timings at 720p: - Face locations: 0.7046s - Face landmarks: 0.0028s - Encode face : 0.4993s - End-to-end: 1.1888s Timings at 1080p: - Face locations: 1.5179s - Face landmarks: 0.0030s - Encode face : 0.4838s - End-to-end: 1.9404s。
Levi G, Hassner T. Age and gender classification using convolutional neural networks//Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2015: 34-42. ↩︎。
1 说明=====1.1 准备篇《Dlib库教程(1):介绍、linux下的安装与避坑》。1.2 本次讲解Dlib库的强大的联合python的人脸检测、标记和识别功能。1.3 熟悉Dlib库的python的API功能函数。1.