针对在现有人脸静态识别过程中被识别人需等待配合的问题,文中提出了一种动态人脸识别系统。该系统采用了基于RetinaFace与FaceNet算法的动态人脸检测和识别方法,并进行了优化,以达到高识别精度和实时性的目标。其中,RetinaFace检测采用...针对在现有人脸静态识别过程中被识别人需等待配合的问题,文中提出了一种动态人脸识别系统。该系统采用了基于RetinaFace与FaceNet算法的动态人脸检测和识别方法,并进行了优化,以达到高识别精度和实时性的目标。其中,RetinaFace检测采用GhostNet作为骨干网络,使用Adaptive-NMS(Non Max Suppression)非极大值抑制用于人脸框的回归,FaceNet识别采用MobileNetV1作为骨干网络,使用Triplet损失与交叉熵损失结合的联合损失函数用以人脸分类。优化后的算法在检测与识别上具有良好表现,改进RetinaFace算法在WiderFace数据集下检测精度为93.35%、90.84%和80.43%,FPS(Frames Per Second)可达53 frame·s^(-1)。动态人脸检测平均检测精度为96%,FPS为21 frame·s^(-1)。当FaceNet阈值设为1.15时,识别率最高达到98.23%。动态识别系统平均识别精度98%,FPS可达20 frame·s^(-1)。实验结果表明,该系统解决了人脸静态识别中需等待配合的问题,具有较高的识别精度与实时性。展开更多
Face recognition is a kind of biometric technology that recognizes identities through human faces. At first, the speed of machine recognition of human faces was slow and the accuracy was lower than manual recognition....Face recognition is a kind of biometric technology that recognizes identities through human faces. At first, the speed of machine recognition of human faces was slow and the accuracy was lower than manual recognition. With the rapid development of deep learning and the application of Convolutional Neural Network (CNN) in the field of face recognition, the accuracy of face recognition has greatly improved. FaceNet is a deep learning framework commo</span><span><span style="font-family:Verdana;">nly used in face recognition in recent years. FaceNet uses the deep learning model GoogLeNet, which has </span><span style="font-family:Verdana;">a high</span><span style="font-family:Verdana;"> accuracy in face recognition. However, its network structure is too large, which causes the </span><span style="font-family:Verdana;">FaceNet</span><span style="font-family:Verdana;"> to run at a low speed. Therefore, to improve the running speed without affecting the recognition accuracy of FaceNet, this paper proposes a lightweight FaceNet model based on MobileNet. This article mainly does the following works:</span></span></span><span style="font-family:""> </span><span style="font-family:Verdana;">Based on the analysis of the low running speed of FaceNet and the principle of MobileNet, a lightweight FaceNet model based on MobileNet is proposed. The model would reduce the overall calculation of the network by using deep separable convolutio</span><span style="font-family:""><span style="font-family:Verdana;">ns. In this paper, the model is trained on the CASIA-WebFace and VGGFace2 </span><span style="font-family:Verdana;">datasets,</span><span style="font-family:Verdana;"> and tested on the LFW dataset. Experimental results show that the model reduces the network parameters to a large extent while ensuring </span><span style="font-family:Verdana;">the accuracy</span><span style="font-family:Verdana;"> and hence an increase in system computing speed. The model can also perform face recognition on a specific person in the video.展开更多
文摘针对在现有人脸静态识别过程中被识别人需等待配合的问题,文中提出了一种动态人脸识别系统。该系统采用了基于RetinaFace与FaceNet算法的动态人脸检测和识别方法,并进行了优化,以达到高识别精度和实时性的目标。其中,RetinaFace检测采用GhostNet作为骨干网络,使用Adaptive-NMS(Non Max Suppression)非极大值抑制用于人脸框的回归,FaceNet识别采用MobileNetV1作为骨干网络,使用Triplet损失与交叉熵损失结合的联合损失函数用以人脸分类。优化后的算法在检测与识别上具有良好表现,改进RetinaFace算法在WiderFace数据集下检测精度为93.35%、90.84%和80.43%,FPS(Frames Per Second)可达53 frame·s^(-1)。动态人脸检测平均检测精度为96%,FPS为21 frame·s^(-1)。当FaceNet阈值设为1.15时,识别率最高达到98.23%。动态识别系统平均识别精度98%,FPS可达20 frame·s^(-1)。实验结果表明,该系统解决了人脸静态识别中需等待配合的问题,具有较高的识别精度与实时性。
文摘Face recognition is a kind of biometric technology that recognizes identities through human faces. At first, the speed of machine recognition of human faces was slow and the accuracy was lower than manual recognition. With the rapid development of deep learning and the application of Convolutional Neural Network (CNN) in the field of face recognition, the accuracy of face recognition has greatly improved. FaceNet is a deep learning framework commo</span><span><span style="font-family:Verdana;">nly used in face recognition in recent years. FaceNet uses the deep learning model GoogLeNet, which has </span><span style="font-family:Verdana;">a high</span><span style="font-family:Verdana;"> accuracy in face recognition. However, its network structure is too large, which causes the </span><span style="font-family:Verdana;">FaceNet</span><span style="font-family:Verdana;"> to run at a low speed. Therefore, to improve the running speed without affecting the recognition accuracy of FaceNet, this paper proposes a lightweight FaceNet model based on MobileNet. This article mainly does the following works:</span></span></span><span style="font-family:""> </span><span style="font-family:Verdana;">Based on the analysis of the low running speed of FaceNet and the principle of MobileNet, a lightweight FaceNet model based on MobileNet is proposed. The model would reduce the overall calculation of the network by using deep separable convolutio</span><span style="font-family:""><span style="font-family:Verdana;">ns. In this paper, the model is trained on the CASIA-WebFace and VGGFace2 </span><span style="font-family:Verdana;">datasets,</span><span style="font-family:Verdana;"> and tested on the LFW dataset. Experimental results show that the model reduces the network parameters to a large extent while ensuring </span><span style="font-family:Verdana;">the accuracy</span><span style="font-family:Verdana;"> and hence an increase in system computing speed. The model can also perform face recognition on a specific person in the video.
