一种基于法曲率极大值和向量内积的脊椎光学模型特征点自动识别方法 -- 西北工业大学学报,2017,35(6):1064-1072
论文:2017,Vol:35,Issue(6):1064-1072
引用本文:
惠宇, 武君胜, 杜静, 鱼滨, 张琛, 聂文斌. 一种基于法曲率极大值和向量内积的脊椎光学模型特征点自动识别方法[J]. 西北工业大学学报
Hui Yu, Wu Junsheng, Du Jing, Yu Bin, Zhang Chen, Nie Wenbin. An Automatic Recognition Algorithm for Feature Points of Spine Optical Model——Based on Maximum Value of the Curvature and Vector Inner Product[J]. Northwestern polytechnical university

一种基于法曲率极大值和向量内积的脊椎光学模型特征点自动识别方法
惠宇1, 武君胜2, 杜静3, 鱼滨4, 张琛4, 聂文斌5
1. 西北工业大学 计算机学院, 陕西 西安 710072;
2. 西北工业大学 软件与微电子学院, 陕西 西安 710072;
3. 西北工业大学 管理学院, 陕西 西安 710072;
4. 西安电子科技大学 计算机学院, 陕西 西安 710071;
5. 西安点云生物科技有限公司, 陕西 西安 710077
摘要:
在脊椎光学模型的定位和配准中,主要难点是模型特征点的定位。针对手动标注特征点精确度不够,易产生较大误差等问题,提出了一种基于法曲率极大值和向量内积的脊椎模型特征点自动识别方法,该方法可以动态调整拾取点曲率,从而最大限度地保证特征点拾取的精准性。方法首先通过高斯曲率和平均曲率流等多曲率特征,得到手动选取点的法曲率极大值,由于曲率越大,三维模型表面在该点处的弯曲程度也就越大,即就是更能表现三维模型的几何轮廓信息;并以手动拾取点为圆心,计算在指定极小半径r范围内的所有模型点的法曲率相对极大值,然后对这些法曲率极大值进行降序排序,筛选出法曲率极大值较大的n个候选点,候选点与手动选取点之间做向量内积,从而得到向量之间的夹角。由于向量内积之间几何夹角角度越小,代表2个点之间欧几里得距离越靠近,故以夹角最小的候选顶点来替换手动拾取的点,从而可以准确反映该点的局部特征变化情况。经过实验的对比分析,新方法对特征点的标记准确性提高了约35%,从而验证了新方法的有效性。
关键词:    三维光学模型    特征点标注    法曲率极大值    向量内积   
An Automatic Recognition Algorithm for Feature Points of Spine Optical Model——Based on Maximum Value of the Curvature and Vector Inner Product
Hui Yu1, Wu Junsheng2, Du Jing3, Yu Bin4, Zhang Chen4, Nie Wenbin5
1. School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China;
2. School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an 710072, China;
3. School of Management, Northwestern Polytechnical University, Xi'an 710072, China;
4. College of Computer Science, Xidian University Xi'an 710071, China;
5. Xi'an Particle Cloud Biotechnology Co., Ltd, Xi'an 710072, China
Abstract:
In the localization and registration of the spine model, the main difficulty is the location of the model feature points. In order to make the 3D model of human vertebrae more accurate, this paper proposes an automatic recognition algorithm for feature points of the spine model based on the Maximum value of the curvature and vector inner product, which can dynamically adjust the curvature of the pick-up point, so as to ensure the accuracy of feature points' pick-up to the greatest degree. Firstly, the curvature maxima of a manually selected point are obtained by using the multi-curvature features such as Gaussian curvature and mean curvature flow, and the relative maxima of normal curvature of all model points within the specified minimum radius r are calculated. The Maximum value of the curvature are sorted in descending order, and n candidate points with larger Maximum value of the curvature are selected. The vector inner product between the candidate points and the manually selected points is chosen to obtain the angle between vectors. The higher the curvature is, the greater the bending degree of the 3D model surface at that point is, that is, it is the better representation of the geometric contour information of the 3D model, and the smaller the geometric angle between the vector inner products is, representing the Euclidean distance between the two points is closer, so the manually picked points are replaced by the candidate vertices with the smallest angle, which can reflect the local characteristics of the point accurately. After comparing and analyzing the experimental results, the new algorithm improves the tagging accuracy of the feature points by about 35%, which verifies the effectiveness of the proposed algorithm.
Key words:    3D model    feature point tagging    Maximum value of the curvature    vector inner product   
收稿日期: 2017-01-28     修回日期:
DOI:
基金项目: 国家自然科学基金(61172147)资助
通讯作者:     Email:
作者简介: 惠宇(1984-),西北工业大学博士研究生,主要从事医学影像处理、软件工程及有限元计算研究。
相关功能
PDF(6139KB) Free
打印本文
把本文推荐给朋友
作者相关文章
惠宇  在本刊中的所有文章
武君胜  在本刊中的所有文章
杜静  在本刊中的所有文章
鱼滨  在本刊中的所有文章
张琛  在本刊中的所有文章
聂文斌  在本刊中的所有文章

参考文献:
[1] 孟勃,韩广良. 基于改进的尺度不变特征变换特征点匹配的电子稳像方法[J]. 计算机应用, 2012,32(10):2817-2820 Meng Bo, Han Guangliang. Electronic Image Stabilization Method Using Improved Scale Invariant Feature Transform[J]. Journal of Computer Applications, 2012,32(10):2817-2820(in Chinese)
[2] 李根,李文辉. 基于思维进化方法的人脸特征点跟踪[J]. 吉林大学学报, 2015, 45:606-612 Li Gen, Li Wenhui. Facial Feature Tracking Based on Mind Evolutionary Algorithm[J]. Journal of Jilin University, 2015, 45:606-612(in Chinese)
[3] 刘志文,刘定生,刘鹏. 应用尺度不变特征变换的多源遥感影像特征点匹配[J]. 光学精密工程,2013,21(8):2146-2153 Liu Zhwen, Liu Dingsheng, Liu Peng. Sift Feature Matching Algorithm of Multi-Source Remote Image[J]. Opt Precision Eng, 2013,21(8):2146-2153(in Chinese)
[4] Ballerinil Calistim, Cordon O. Auto-Matic Feature Extraction from 3D Range Images of Skulls[J]. Compuational Forensics,2011,5158:58-69
[5] 王欣,张明明,于晓,等. 应用改进迭代最近点方法的点云数据配准[J]. 光学精密工程,2012,20(9):2068-2077 Wang Xing, Zhang Mingming, Yu Xiao, et al. Point Cloud Registration Based on Improved Iterative Closest Point Method[J]. Opt Precision Eng, 2012,20(9):2068-2077(in Chinese)
[6] Damas S, Cordon O, Santamaria J, et al. Forensic Identification by Computer-Aided Craninfacial Superimposition:A Survery[M]. Acm Computing Surveys(Csur), 2011:27
[7] 李康,尚鹏. 基于深度图像的人脸模型特征点自动标定[J]. 计算机科学, 2014, 41:287-291 Li Kang, Shang Peng. Automatic Location of Feature Points on Three-Dimensional Facial Model Based on Depth Image[J]. Computer Science, 2014, 41:287-291(in Chinese)
[8] 翟凤文,党建武. 形状特征和置信传播在去除Sift特征点错误匹配中的应用[J]. 计算机辅助设计与图形学学报, 2016, 28:443-449 Qu Fengwen, Dang Jianwu. Application of Shape Context and Belief Propagation in Removing Sift Mismatches[J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28:443-449(in Chinese)
[9] 王澜,孙博. 一种基于共线特征点的线阵相机内参标定方法[J]. 红外与激光工程, 2015(6):134-140 Wang Lan, Sun Bo. A Novel Method for Calibrating Intrinsic Parameters of Linear Array Cameras Based on Collinear Feature Points[J]. Infrared and Laser Engineering, 2015(6):134-140(in Chinese)
[10] 韩霜. 三维脊椎模型特征点标注的研究与实现[D]. 西安:西安电子科技大学,2013 Han Shuang. Research and Implementation of Tagging Three-Dimensional Model of the Spine with Feature Points[D]. Xi'an, Xidian University,2013(in Chinese)
[11] 李瑞祥. 实用人体解剖彩色图谱[M]. 北京:人民卫生出版社,2001
[12] 陈维桓. 微分几何[M]. 北京:北京大学出版社, 2006 Chen Weiheng. Differential Geometry[M]. Beijing, Peking University Press, 2006(in Chinese)