基于结构光视觉传感器的多视角人脸表情识别方法研究  

Research on Multi-Perspective Face Expression Recognition Method Based on Structured Light Vision Sensor

作　　者：孙英 杨海苑 SUN Ying;YANG Haiyuan(Jincheng College of Nanjing University of Aeronautics and Astronautics School of Information Engineering,Nanjing 210000,China;Jincheng College of Nanjing University of Aeronautics and Astronautics College of Aeronautical Transportation and Engineering,Nanjing 210000,China)

机构地区：[1]南京航空航天大学金城学院信息工程学院,江苏南京210000 [2]南京航空航天大学金城学院航空运输与工程学院,江苏南京210000

出　　处：《传感器世界》2024年第10期19-26,共8页Sensor World

摘　　要：传统人脸识别多采用普通摄像头或红外摄像头,经常因图像质量不足导致识别失败或混淆。因此,文章提出一种基于结构光视觉传感器的多视角人脸表情识别方法。该方法利用结构光视觉传感器采集高分辨率精细图像,提高人脸图像的清晰度和细节捕捉能力,通过先进的图像处理技术提取丰富的表情特征,并融合不同视角的特征实现识别目标。实验结果表明,该方法在所有视角下的识别正确次数最高达295次,表现更优,具有更强的鲁棒性,为人脸表情识别提供可靠解决方案。Traditional facial recognition often uses ordinary or infrared cameras,but insufficient image quality leads to recognition failure or confusion.Therefore,the article proposes a multi view facial expression recognition method based on structured light visual sensors.The method utilizes structured light visual sensors to capture high-resolution and fine images,improving the clarity and detail capture ability of facial images.Extracting rich facial expression features through advanced image processing techniques and integrating features from different perspectives to achieve target recognition.The experimental results show that the method achieves a maximum recognition accuracy of 295 times in all perspectives,showing better performance and stronger robustness,providing a reliable solution for facial expression recognition.

关 键 词：结构光视觉 传感器 多视角 人脸表情 表情识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]