方向感知的网格模型特征识别

doi:10.11772/j.issn.1001-9081.2019050799

计算机应用 ›› 2019, Vol. 39 ›› Issue (12): 3673-3677.DOI: 10.11772/j.issn.1001-9081.2019050799

• 虚拟现实与多媒体计算 • 上一篇下一篇

方向感知的网格模型特征识别

郭艺辉, 黄承慧, 钟雪灵, 陆寄远

广东金融学院互联网金融与信息工程学院, 广州 510020

收稿日期:2019-05-13 修回日期:2019-07-19 发布日期:2019-09-05 出版日期:2019-12-10
作者简介:郭艺辉(1976-),女,山东济南人,讲师,博士,主要研究方向:计算机图形学、数字几何处理;黄承慧(1976-),男,湖南郴州人,副教授,博士,主要研究方向:机器学习;钟雪灵(1980-),男,广东河源人,教授,博士,主要研究方向:金融科技、大数据;陆寄远(1976-),男,广东南海人,教授,博士,主要研究方向:多媒体数据处理。
基金资助:
国家自然科学基金资助项目（71501051）；国家自然科学基金国际（地区）合作与交流项目（61320106008）；广东省自然科学基金资助项目（2017A050501042）；广东省普通高校人文社会科学研究重点项目（2018WZDXM032）。

Direction-perception feature recognition on mesh model

GUO Yihui, HUANG Chenghui, ZHONG Xueling, LU Jiyuan

School of Internet Finance and Information Engineering, Guangdong University of Finance, Guangzhou Guangdong 510020, China

Received:2019-05-13 Revised:2019-07-19 Online:2019-09-05 Published:2019-12-10
Contact: 郭艺辉
Supported by:
This work is partially supported by the National Natural Science Foundation of China (71501051), the National Natural Science Foundation of China International (Regional) Cooperation and Exchange Project (61320106008), the Natural Science Foundation of Guangdong Province (2017A050501042), the Key Project of the Humanities and Social Sciences Research in Universities of Guangdong Province (2018WZDXM032).

摘要/Abstract

摘要： 针对网格模型平滑区域提取特征困难，以及现有特征识别方法无法检测仅沿某一特定方向分布的特征点的问题，提出一种方向感知的网格模型特征识别方法。首先，分别从x、y、z三个方向探测网格顶点邻接面法向量沿不同方向变化的情况。设定合适的阈值，只要检测到在任何一个方向上顶点邻接面法向量的变化超过阈值，该顶点即被识别为特征点。然后，针对现有网格模型特征识别算法无法检测三维医学模型普遍存在的一种仅沿z轴方向分布的梯田型结构的问题，单独探测医学模型网格顶点邻接面法向量沿z轴方向变化的情况，将变化超出阈值的顶点识别为梯田型结构顶点，正确地将非正常梯田型结构从人体模型正常结构特征中分离出来。与二面角法的对比实验的结果显示：在相同阈值设置下，所提方法能更好地识别出网格模型特征，解决了二面角法在没有明显折线的平滑区域上无法有效识别特征点的问题；同时，也解决了现有网格模型特征检测算法因不具备方向探测能力而无法将医学模型非正常梯田型结构与正常人体结构区分开来的问题，为医学模型后续数字几何处理工作提供了条件。

关键词: 网格特征识别, 平滑特征区域, 方向属性, 医学三维重建, 梯田型结构

Abstract: In order to solve the problems of the difficulty to extract features on the smooth regions of mesh models and the impossibility to recognize the feature vertices distributed only along one specific direction by the existing feature detection methods, a direction-perception method of feature recognition on mesh models was proposed. Firstly, the changes of the normal vectors of the mesh vertex adjacent surfaces were detected in x, y and z directions separately. With a suitable threshold set, if the change of a normal vector of the mesh vertex adjacent surfaces exceeded the threshold in any direction, the vertex would be recognized as a feature vertex. Then, concerning the problem that the existing mesh model feature detection algorithms cannot recognize the terraced field structure only distributed along the z-axis of three-dimensional medical model, the algorithm detected the change of normal vectors of the mesh vertex adjacent surfaces just along the z-axis direction, and recognized the vertex as a terraced field structure vertex once the change of the vertex exceeds the threshold. The abnormal terraced field structures were separated from the normal structures of the human body successfully. The experimental results show that, compared with the dihedral angle method, the proposed method can identify the features of the mesh model better under the same conditions. The proposed method solves the problem that the dihedral angle method cannot effectively identify the feature vertices on the smooth regions without obvious broken lines, and also solves the problem that the existing mesh model feature detection algorithms cannot distinguish the abnormal terraced field structures from the normal human body structures due to the lack of the direction detection ability, and establishes a base for the following digital geometry processing of the medical model.

Key words: mesh feature recognition, smooth feature region, directionality property, three-dimensional medical reconstruction, terraced field structure

中图分类号:

TP391.72

郭艺辉, 黄承慧, 钟雪灵, 陆寄远. 方向感知的网格模型特征识别[J]. 计算机应用, 2019, 39(12): 3673-3677.

GUO Yihui, HUANG Chenghui, ZHONG Xueling, LU Jiyuan. Direction-perception feature recognition on mesh model[J]. Journal of Computer Applications, 2019, 39(12): 3673-3677.

参考文献

[1] GUSKOV I, SWELDENS W, SCHRÖDER P. Multiresolution signal processing for meshes[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques. New York:ACM Press, 1999:325-334.
[2] LEE C H, VARSHNEY A, JACOBS D W. Mesh saliency[J]. ACM Transactions on Graphics, 2005, 24(3):659-666.
[3] KIM Y, VARSHNEY A, JACOBS D W, et al. Mesh saliency and human eye fixations[J]. ACM Transactions on Applied Perception, 2010, 7(2):Article No. 12.
[4] SIPIRAN I, BUSTOS B. Harris 3D:a robust extension of the Harris operator for interest point detection on 3D meshes[J]. The Visual Computer, 2011, 27(11):963-976.
[5] LAGA H. Data-driven approach for automatic orientation of 3D shapes[J]. The Visual Computer, 2011, 27(11):977-989.
[6] DUTAGACI H, CHEUNG C P, GOSIL A. Evaluation of 3D interest point detection techniques via human-generated ground truth[J]. The Visual Computer, 2012, 28(9):901-917.
[7] SONG R, LIU Y, MARTIN R R, ROSIN P L. 3D point of interest detection via spectral irregularity diffusion[J]. The Visual Computer, 2013, 29(6/7/8):695-705.
[8] WU J, SHEN X, ZHU W. Mesh saliency with global rarity[J]. Graphical Models, 2013, 75(5):255-264.
[9] 朱帆,杨风雷.基于特征点检测的三维模型最佳视点选择[J].计算机应用,2013,33(11):3172-3175.(ZHU F, YANG F L. Best viewpoints selection based on feature points detection[J]. Journal of Computer Applications, 2013, 33(11):3172-3175.)
[10] 王海玲,王建,印桂生,等.多特征融合的网格模型简化方法[J].计算机应用,2013,33(11):3167-3171.(WANG H L, WANG J, YIN G S, et al. Multi-feature fusion method for mesh simplification[J]. Journal of Computer Applications, 2013, 33(11):3167-3171.)
[11] GUPTA R K, GURUMOORTHY B. Classification, representation, and automatic extraction of deformation features in sheet metal parts[J]. Computer-Aided Design, 2013, 45(11):1469-1484.
[12] 孙挺,张锦华,耿国华.基于局部特征概率密度估计的三维模型特征提取方法[J].计算机科学,2015,42(6):293-295,312.(SUN T, ZHANG J H, GENG G H. New architecture for extraction of 3D model features based on probabilistic density estimation of local surface features[J]. Computer Science, 2015, 42(6):293-295, 312.)
[13] LEVALLOIS J, COEURJOLLY D, LACHAUD J. Scale-space feature extraction on digital surfaces[J]. Computers and Graphics, 2015, 51:177-189.
[14] LIU H, DAI N, ZHONG B, et al. Extract feature curves on noisy triangular meshes[J]. Graphical Models, 2017, 93:1-13.
[15] KONG T, ZHANG Y, FU X B. The model of feature extraction for free-form surface based on topological transformation[J]. Applied Mathematical Modelling, 2018, 64:386-397.
[16] MURALEEDHARAN L P, KANNAN S S, KARVE A, et al. Random cutting plane approach for identifying volumetric features in a CAD mesh model[J]. Computers and Graphics, 2018, 70:51-61.
[17] TORRENTE M, BIASOTTI S, FALCIDIENO B. Recognition of feature curves on 3D shapes using an algebraic approach to Hough transforms[J]. Pattern Recognition, 2018, 73:111-130.
[18] SOLTANPOUR S, BOUFAMA B, WU Q M J. A survey of local feature methods for 3D face recognition[J]. Pattern Recognition, 2017, 72:391-406.
[19] SONG R, LIU Y, MARTIN R R. Local-to-global mesh saliency[J]. The Visual Computer, 2018, 34(3):323-336.
[20] CHEN H, LI M. A novel mesh saliency approximation for polygonal mesh segmentation[J]. Multimedia Tools and Applications, 2018, 77(13):17223-17246.
[21] 刘斌.三角网格曲面上的特征阵列[J].机械工程学报,2019,55(3):120-129.(LIU B. Pattern design of freeform features on triangular meshes[J]. Journal of Mechanical Engineering, 2019, 55(3):120-129.)
[22] 杨贤康,潘茂东,童伟华,等.基于L₀优化的网格曲面特征线提取算法[J].计算机工程,2019,45(7):251-257,263.(YANF X K, PAN M D, TONG W H, et al. Feature lines extraction on meshes using L₀ minimization[J]. Computer Engineering, 2019, 45(7):251-257, 263.)
[23] 胡俊,刘斌,黄常标,等.网格曲面上自由形状特征交互式阵列设计[J].计算机集成制造系统,2019,25(1):61-70.(HU J, LIU B, HUANG C B, et al. Interactive pattern design of freeform features on mesh surface[J]. Computer Integrated Manufacturing Systems, 2019, 25(1):61-70.)
[24] CHEN X, GOLOVINSKIY A, FUNKHOUSER T. A benchmark for 3D mesh segmentation[J]. ACM Transactions on Graphics, 2009, 28(3):Article No. 73.
[25] 严严,陈日伟,王菡子,等.基于深度学习的人脸分析研究进展[J].厦门大学学报(自然科学版),2017,56(1):13-24.(YAN Y, CHEN R W, WANG H Z, et al. Recent advances on deep-learning-based face analysis[J]. Journal of Xianmen University (Natural Science), 2017, 56(1):13-24.)
[26] 刘栋,李素,曹志冬.深度学习及其在图像物体分类与检测中的应用综述[J].计算机科学,2016,43(12):13-23.(LIU D, LI S, CAO Z D. State-of-the-art on deep learning and its application in image object classification and detection[J]. Computer Science, 2016, 43(12):13-23.)
[27] 李鑫,陈雷霆,蔡洪斌.基于结构感知深度神经网络的显著性对象检测算法[J].计算机应用研究,2019,36(7):2195-2199.(LI X, CHEN L T, CAI H B. Salient object detection algorithm based on structure-sensitive deep neural network[J]. Application Research of Computers, 2019, 36(7):2195-2199.)
[28] 杨军,王顺,周鹏.基于深度体素卷积神经网络的三维模型识别分类[J].光学学报,2019,39(4):314-324.(YANG J, WANG S, ZHOU P. Recognition and classification for three-dimensional model based on deep voxel convolution neural network[J]. Acta Optica Sinica, 2019, 39(4):314-324.)
[29] CHARLES R Q, SU H, MO K. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:77-85.
[30] LUCIANO L, HAMZA A B. Deep learning with geodesic moments for 3D shape classification[J]. Pattern Recognition Letters, 2018, 105:182-190.
[31] FEY M, LENSSEN J E, WEICHERT F, et al. SplineCNN:fast geometric deep learning with continuous B-spline kernels[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:869-877.

方向感知的网格模型特征识别

Direction-perception feature recognition on mesh model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	赵京东, 杨凤华, 郭英新. 散乱点云去噪与简化的统一算法[J]. 计算机应用, 2017, 37(10): 2879-2883.
[2]	杨张龙, 陈明. 大规模网格模型间的快速视觉布尔运算[J]. 计算机应用, 2017, 37(7): 2050-2056.
[3]	陈明, 李杰. 稀疏三角网格模型的Gregory曲面光顺插值[J]. 计算机应用, 2016, 36(11): 3183-3187.
[4]	周继来, 周明全, 耿国华, 王小凤. 基于曲度特征的三维模型检索算法[J]. 计算机应用, 2016, 36(7): 1914-1917.
[5]	郭洪帅, 孙殿柱, 李延瑞, 李聪. 支持STL数据源的网格曲面动态空间索引[J]. 计算机应用, 2015, 35(9): 2611-2615.
[6]	方永锋, 陈建军, 邱泽阳. T-Bézier曲线能量法的光顺计算[J]. 计算机应用, 2015, 35(7): 2047-2050.
[7]	张湘玉, 马希青. Catmull-Clark细分网格数据点拾取[J]. 计算机应用, 2015, 35(5): 1454-1458.
[8]	赵京东, 杨凤华, 刘爱晶. 散乱点云近离群点识别算法[J]. 计算机应用, 2015, 35(4): 1089-1092.
[9]	张湘玉, 李明, 马希青. 基于细分的网格模型骨架驱动变形技术[J]. 计算机应用, 2015, 35(3): 811-815.
[10]	纪小刚杨艳薛杰. 任意分辨率小波光顺的光顺精度分析[J]. 计算机应用, 2014, 34(5): 1423-1426.
[11]	张帆康宝生赵建东李娟. 散乱点云数据曲率估计方法[J]. 计算机应用, 2013, 33(06): 1662-1681.
[12]	殷明强李世其. 保持外观的CAD模型轻量化技术[J]. 计算机应用, 2013, 33(06): 1719-1722.
[13]	郑慧杰刘弘郑向伟. 基于改进群搜索优化算法的群体路径规划方法[J]. 计算机应用, 2012, 32(08): 2223-2226.
[14]	花锋. 基于NXOpen的验证规则定制[J]. 计算机应用, 2011, 31(10): 2861-2864.
[15]	吴海龙刘希玉向来生. 基于遗传算法的骨骼结构模型概念创新设计[J]. 计算机应用, 2011, 31(04): 1155-1158.