[1]宁雪丽,陈兆学.用于面诊的人脸全景图像拼接算法[J].中国医学物理学杂志,2020,37(4):456-462.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.011]
　NING Xueli,CHEN Zhaoxue.Face panoramic image mosaic algorithm for face diagnosis[J].Chinese Journal of Medical Physics,2020,37(4):456-462.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.011]
点击复制

用于面诊的人脸全景图像拼接算法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
37
期数:
2020年第4期
页码:
456-462
栏目:
医学影像物理
出版日期:
2020-04-29

文章信息/Info

Title:
Face panoramic image mosaic algorithm for face diagnosis
文章编号:
1005-202X（2020）04-0456-07
作者:
宁雪丽; 陈兆学
上海理工大学医疗器械与食品学院， 上海 200093
Author(s):
NING Xueli;  CHEN Zhaoxue
School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
关键词:
中医面诊; 人脸全景图像; 柱面投影; 图像配准
Keywords:
Keywords: face diagnosis in traditional Chinese medicine;  panoramic image of face;  cylindrical projection;  image registration
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2020.04.011
文献标志码:
A
摘要:
采用一种基于人脸特征的柱面投影方法，将人的头部近似看做一个圆柱体，有效地解决了在采集过程中因面部角度所引起的视觉不一致性；利用SIFT特征匹配算法提取两幅图像的特征向量，并通过RANSAC匹配优化算法消除错误的匹配，实现图像的配准；接着采用渐入渐出的融合算法，使图像间实现平滑的过渡，消除拼接缝隙。实验结果表明，本研究使用的算法能够快速、有效地生成人脸全景图像，为后续中医面诊奠定了基础。
Abstract:
Abstract: A cylindrical projection method based on facial features is used to approximate the human head as a cylinder, which effectively solves the problem of visual inconsistency caused by different facial angles during image acquisition. SIFT feature matching algorithm is used to extract the feature vectors of two images, and the optimized RANSAC matching algorithm is used to eliminate false matches, thereby realizing image registration. Then fade-in and fade-out fusion algorithm is applied to smooth image transitions and eliminate stitching gaps. The experimental results show that the proposed algorithm can generate the panoramic image of face quickly and effectively, which lays a foundation for the follow-up face diagnosis in traditional Chinese medicine.

相似文献/References:

[1]罗胜男,陈兆学. 用于面诊的嘴巴定位算法研究[J].中国医学物理学杂志,2019,36(4):440.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.014]
　LUO Shengnan,CHEN Zhaoxue. Mouth segmentation algorithm for facial diagnosis in traditional Chinese medicine[J].Chinese Journal of Medical Physics,2019,36(4):440.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.014]

备注/Memo

备注/Memo:
【收稿日期】2019-12-19 【基金项目】上海市教委科研创新项目（13YZ069） 【作者简介】宁雪丽，硕士研究生，主要研究方向：生物医学图像处理， E-mail: ShirleyNXL@163.com 【通信作者】陈兆学，博士，副教授，主要研究方向：生物医学图像处理、信号处理、模式识别，E-mail: chenzhaoxue@163.com
更新日期/Last Update: 2020-04-29