基于循环推理网络的人脸关键点检测算法  

Face Landmark Detection Algorithm Based on Recurrent Inference Network

作　　者：王兴 WANG Xing(Beijing China-Power Information Technology Co.,Ltd.,Beijing 102208,China)

机构地区：[1]北京中电普华信息技术有限公司,北京102208

出　　处：《现代信息科技》2023年第4期91-94,共4页Modern Information Technology

摘　　要：人脸关键点检测是计算机视觉任务中研究的一个重要话题。但目前的人脸关键点检测算法只能有效地提取人脸的表观信息,未能充分挖掘人脸的结构信息。为了解决上述问题,提出了循环推理网络用于人脸关键点的检测,通过分批次循环递归地学习人脸结构信息和人脸表观信息,使得神经网络能有效地提取人脸的结构信息。通过在AFLW2000-3D数据集的实验表明,文章的算法优于其他经典的人脸关键点检测算法。Face landmark detection is an important topic in computer vision tasks. However, the current face landmark detection algorithm can only effectively extract the face apparent information, but not fully explore the structural information of the face. In order to solve the above problems, a recurrent inference network is proposed to detect the landmark of the face. The neural network can effectively extract the structural information of the face by learning the structural information and the apparent information of the face recursively in batches. Experiments on AFLW2000-3D datasets show that the proposed algorithm outperforms other classical face landmark detection algorithms in this paper.

关 键 词：人脸关键点检测 人脸表观信息 人脸结构信息 神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]