基于MTCNN和Facenet的人脸识别

人脸识别技术在智能城市建设中广泛应用,传统人脸识别算法依赖人工设定的特征,通常会带来不可期望的人为因素和误差。随着计算机算力的提升,基于神经网络的人脸识别方法由于其准确高效深受工业界偏爱。提出了基于多任务卷积神经网络(MTCNN——Multi-task Cascaded Convolutional Networks)和Facenet的人脸识别方法,并实现了从图像处理到识别结果输出的整个人脸识别系统。

Face Recognition Based on MTCNN and Facenet

Face recognition technology is widely used in the smart city construction.Traditional face recognition algorithms rely on artificial features,which usually bring unexpected human factors and errors.With the improvement of computer computing power,the face recognition method based on neural networks are favored by the industry because of its accuracy and efficiency.A face recognition method based on MTCNN(Multi-task Cascaded Convolutional Networks)and facenet is proposed,and the whole face recognition system from image processing to recognition result output is realized.