激光与光电子学进展, 2019, 56 (21): 211501, 网络出版: 2019-11-02
基于卷积神经网络的教室人脸检测算法 下载: 545次
Classroom Face Detection Algorithm Based on Convolutional Neural Network
机器视觉 人脸检测 教室考勤 卷积神经网络 深度学习 machine vision face detection classroom attendance convolutional neural networks deep learning
摘要
针对教室场景下后排学生人脸微小难以检测的情况,提出一种基于卷积神经网络的教室人脸检测算法。采用两阶段检测形式,运用残差神经网络的结构对教室人脸进行特征提取,同时构建特征金字塔,并将Softmax损失函数与中心特征损失函数结合,运用合适的激活函数进行训练。此算法在教室场景下获得95.2%的准确率,且在通用数据集Wider Face的三个等级验证集上分别获得93.0%,87.3%,58.3%的平均精度均值。
Abstract
This study proposes a face detection algorithm based on a convolutional neural network considering the scenario of a classroom, where the faces of students sitting in the back rows might not be visible. First, the algorithm extracts face features in two stages using a residual neural network. Then, it builds a feature pyramid and combines the Softmax loss function with center loss function to train a face recognition model based on a proper activation function. Upon applying the algorithm to the Wider Face dataset, it achieves an accuracy of 95.2% and mean average precision values of 93.0%, 87.3%, and 58.3% for three levels of validation sets, respectively.
王萌, 苏寒松, 刘高华, 李燊. 基于卷积神经网络的教室人脸检测算法[J]. 激光与光电子学进展, 2019, 56(21): 211501. Meng Wang, Hansong Su, Gaohua Liu, Shen Li. Classroom Face Detection Algorithm Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(21): 211501.