光学技术, 2016, 42 (6): 501, 网络出版: 2016-12-23
一种高效的人脸三维点云超分辨率融合方法
An efficient method of face super-resolution fusion using 3D cloud points
点云融合 超分辨率 人脸检测 人脸识别 点云对准 cloud points fusion super-resolution face detection face recognition point cloud alignment
摘要
三维人脸识别技术是当前研究和应用的热点。提出了一种专门针对人脸的三维点云融合方法, 通过人脸检测、人脸姿态校正、点云对准和三视点投影等步骤实现三维点云超分辨率融合。实验结果表明, 该方法可提高点云的分辨率, 降低噪声的干扰, 消除孔洞, 能较好地重构人脸表面, 能大幅度地降低融合的计算复杂度, 提高融合的效率。
Abstract
A method of 3D point cloud fusion for face recognition is presented, includes face detection, face pose correction, point cloud alignment and three views projection. Experimental results show that, this method can improve point cloud resolution, reduce noise, eliminate holes, and reconstruct better face surface.
谭红春, 耿英保, 杜炜. 一种高效的人脸三维点云超分辨率融合方法[J]. 光学技术, 2016, 42(6): 501. TAN Hongchun, GENG Yingbao, DU Wei. An efficient method of face super-resolution fusion using 3D cloud points[J]. Optical Technique, 2016, 42(6): 501.