Abstract

Face detection and recognition is one of the research hotspots in the field of computer vision, which is widely used in video surveillance and identity matching. The traditional algorithms of face detection include AdaBoost, Haar-like, DPM, etc. These algorithms use face geometric features and template matching for face detection, which is difficult to consider both detection speed and accuracy. In order to solve this problem, this paper proposes an improved FaceNet network. The multi-task cascaded convolutional neural networks (MTCNN) is used to achieve rapid face detection and face alignment, and then the FaceNet with improved loss function is used to realize face verification and recognition with high accuracy. We compare the face detection and recognition performance of our network framework with the traditional algorithms and some deep learning algorithms. The experimental results verify that the improved FaceNet can meet the requirements of real-time recognition, and the recognition accuracy reaches 99.85%, which meets the actual demand. It can be effectively applied to face detection and recognition in the Access Control System.

中文翻译：

---

基于MTCNN和FACENET的人脸检测与识别访问控制系统

摘要

人脸检测与识别是计算机视觉领域的研究热点之一，广泛应用于视频监控和身份匹配。传统的人脸检测算法包括AdaBoost，类似Haar的DPM等。这些算法使用人脸几何特征和模板匹配进行人脸检测，这很难同时考虑检测速度和准确性。为了解决这个问题，本文提出了一种改进的FaceNet网络。利用多任务级联卷积神经网络（MTCNN）实现快速的人脸检测和人脸对齐，然后使用具有改进损失功能的FaceNet实现高精度的人脸验证和识别。我们将网络框架的人脸检测和识别性能与传统算法和一些深度学习算法进行了比较。实验结果表明，改进后的FaceNet能够满足实时识别的要求，识别精度达到99.85％，可以满足实际需求。它可以有效地应用于访问控制系统中的人脸检测和识别。