人像三维特征信息采集系统的设计与实现  被引量:2

Design and Implementation of 3D Portrait Feature Information Collection System

在线阅读下载全文

作  者:聂建华[1,2] 刘小楠[1,2] 刘昌进[1,2] 李林[1,2] 陈向阳 NIE Jian-hua;LIU Xiao-nan;LIU Chang-jin;LI Lin;CHEN Xiang-yang(The 38th Research Institute of China Electronics Technology Group Corporation, Hefei 230088, China;Anhui Key Laboratory of Emergency Information Technology of Public Safety, Hefei 230088, China;The Public Security Bureau of Criminal Investigation Brigadehui, Hubei Macheng 438300, China)

机构地区:[1]中国电子科技集团公司第三十八研究所,合肥230088 [2]安徽省公共安全应急信息技术重点实验室,合肥230088 [3]湖北省麻城市公安局刑侦大队,湖北麻城438300

出  处:《新型工业化》2016年第10期61-65,共5页The Journal of New Industrialization

基  金:安徽省科技攻关计划(1501b042216)

摘  要:三维人像被认为具有光照和姿态不变的特性,学术界开始探索利用人脸的三维信息提高系统识别性能。针对人像三维特征信息获取面临的采集时间长、设备价格昂贵、点云特征提取算法难度大等问题,提出了一种基于OPENNI兼容设备开发的便携式、低成本、高速度人像三维特征信息采集系统。通过使用电动旋转平台及点云自动拼接功能,获得了360°人像三维点云数据。后期处理模块实现对点云数据的裁剪、去除离群点、修补孔洞等功能。数据分析模块通过使用快速点特征直方图与高斯曲率,获得人像的耳鼻特征区域。Three dimensional portrait is considered to have the special characteristics of unchanged with light and pose,hence, the academia began to improve the performance of human face recognition by exploring the use of three-dimensional information. Aim to solve the problems of 3D portrait feature information acquisition, such as long grabbing time, expensive equipment, complex point cloud feature extraction algorithm and so on. This paper proposes a system of 3D portrait feature information collection based on OPENNI compatible device with the advantages of good portability, low cost and high speed.By using the electric rotary table and point cloud automatic stitching function, 360 degree 3D portrait point cloud data was collected. The post processing module was designed to realize the functions of point cloud data cutting, outliers removing, holes repairing and so force. The data analysis module was used to obtain the characteristic region of portraits’ ears and noses through using the Fast Point Feature Histogram and Gauss Curvature.

关 键 词:模式识别与智能系统 三维特征 点特征直方图 点云 人像 

分 类 号:TP391.72[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象