您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (3): 30-35.doi: 10.6040/j.issn.1672-3961.0.2023.169

• 机器学习与数据挖掘 • 上一篇    

基于点云处理网络的三维颜面正中矢状面预测模型

刘真光1,2,朱玉佳3,4,5,王勇3,4,5,傅湘玲1,2,5,赵一姣3,4,5,陈晋鹏1,2,5*   

  1. 1.北京邮电大学计算机学院(国家示范性软件学院), 北京 100876;2.可信分布式计算与服务教育部重点实验室(北京邮电大学), 北京 100876;3.北京大学口腔医学院·口腔医院, 北京 100081;4.国家口腔医学中心, 北京100081;5.口腔生物材料和数字诊疗装备国家工程研究中心, 北京 100081
  • 发布日期:2024-06-28
  • 作者简介:刘真光(1997— ),男,河南信阳人,硕士研究生,主要研究方向为数据挖掘与智能计算. E-mail:1023736798@qq.com. *通信作者简介:陈晋鹏(1985— ),男,山西晋城人,副教授,博士生导师,博士,主要研究方向为数据挖掘与智能计算. E-mail:jpchen@bupt.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(82071171,82271039);北京大学口腔医院实验室开放课题资助项目(PKUSS20220301);北京邮电大学研究生创新创业资助项目(2023-YC-T030)

3D facial midsagittal plane prediction model with point cloud processing network

LIU Zhenguang1,2, ZHU Yujia3,4,5, WANG Yong3,4,5, FU Xiangling1,2,5, ZHAO Yijiao3,4,5, CHEN Jinpeng1,2,5*   

  1. 1. School of Computer Science(National Pilot Software Engineering School), BUPT, Beijing 100876, China;
    2. Key Laboratory of Trustworthy Distributed Computing and Service(BUPT), Ministry of Education, Beijing 100876, China;
    3. Peking University School and Hospital of Stomatology, Beijing 100081, China;
    4. National Center for Stomatology, Beijing 100081, China;
    5. National Engineering Research Center of Oral Biomaterials and Digital Medical Devices, Beijing 100081, China
  • Published:2024-06-28

PDF (PC)

184

摘要： 设计一种基于点云处理网络的三维颜面正中矢状面预测模型(facial midsagittal plane prediction network, FSPNet),实现三维颜面正中矢状面端到端自动化预测。FSPNet模型以三维颜面点云数据为输入,利用点云处理网络提高数据处理效率。它包含3个模块:全局特征编码模块从点云整体结构提取全局特征;局部特征编码模块从点云局部空间结构提取局部特征;正中矢状面预测模块聚合全局特征和局部特征,输出正中矢状面平面参数。借助点云编码模块,模型能够从不同角度充分挖掘颜面点云数据空间信息,实现点云特征全面提取。在真实颜面数据集上的试验结果表明,FSPNet模型具有优秀的性能,点云编码模块能够准确提取颜面点云特征,模型预测效果明显优于临床广泛使用的迭代最近点关联法,充分验证了FSPNet模型的有效性。

关键词: 颜面正中矢状面, 点云处理网络, 平面预测, 端到端框架, 三维颜面数据

中图分类号: 

  • TP18
[1] 赵一姣, 高林, 王勇. 颅颌面点云数据解剖标志点及对称参考平面的构建算法浅析[J]. 中华口腔医学杂志, 2023, 58(6):519-526. ZHAO Yijiao, GAO Lin, WANG Yong. Advances in algorithms for three-dimensional craniomaxillofacial features construction based on point clouds[J]. Chinese Journal of Stomatology, 2023, 58(6):519-526.
[2] XIONG Y X, ZHAO Y J, YANG H F, et al. Accuracy assessment of Procrustes analysis for computing mid-sagittal plane of three-dimensional facial data[C] //International Conference on Optical and Photonic Engineering(icOPEN). Bellingham, USA: SPIE, 2015, 9524: 123-131.
[3] NUR R B, ÇAKAN D G, ARUN T. Evaluation of facial hard and soft tissue asymmetry using cone-beam computed tomography[J]. American Journal of Orthodontics and Dentofacial Orthopedics, 2016, 149(2): 225-237.
[4] 刘筱菁, 李倩倩, 王晓霞, 等. 基于本体-镜像关联的三维头颅正中矢状面自动构建法[J]. 中华口腔正畸学杂志, 2014, 21(3): 148-150. LIU Xiaojing, LI Qianqian, WANG Xiaoxia, et al. Automatic constructed MSP of 3D skull based on original-mirror alignment[J]. Chinese Journal of Orthodontics, 2014, 21(3): 148-150.
[5] XIONG Y X, ZHAO Y J, YANG H F, et al. Comparison between interactive closest point and Procrustes analysis for determining the median sagittal plane of three-dimensional facial data[J]. Journal of Craniofacial Surgery, 2016, 27(2): 441-444.
[6] ZHU Y J, ZHENG S W, YANG G S, et al. A novel method for 3D face symmetry reference plane based on weighted Procrustes analysis algorithm[J]. BMC Oral Health, 2020, 20(1): 1-11.
[7] ZHU Y J, ZHAO Y J, ZHENG S W, et al. A method for constructing three-dimensional face symmetry reference plane based on weighted shape analysis algorithm[J]. Journal of Peking University(Health Sciences), 2020, 53(1): 220-226.
[8] HARTMANN J, MEYER-MARCOTTY P, BENZ M, et al. Reliability of amethod for computing facial symmetry plane and degree of asymmetry based on 3D-data[J]. Journal of Orofacial Orthopedics, 2007, 68(6): 477-490.
[9] 张顺利, 徐艳芝, 周明全, 等. 基于自适应邻域匹配的点云配准方法[J]. 计算机学报, 2019, 42(9): 2114-2126. ZHANG Shunli, XU Yanzhi, ZHOU Mingquan, et al.Registration of point clouds based on matching of general adaptive neighborhood[J]. Chinese Journal of Computers, 2019, 42(9): 2114-2126.
[10] CHEN J P, CAO Y, ZHANG F, et al. Sequential intention-aware recommender based on user interaction graph[C] //Proceedings of the 2022 International Conference on Multimedia Retrieval(ICMR). New York, USA: ACM, 2022: 118-126.
[11] XU Y, HU J, GAO Z Q, et al. UCL-AST: active self-training with uncertainty-aware clouded logits for few-shot text classification[C] //IEEE 34th International Conference on Tools with Artificial Intelligence(ICTAL). Piscataway, USA: IEEE, 2022: 1390-1395.
[12] CAO Y, GAO Z Q, HU J, et al. Nearest neighbor classifier with margin penalty for active learning[C] //International Conference on Neural Information Processing. Berlin, German: Springer, 2022: 379-392.
[13] 李宗霖, 张盛平, 刘杨, 等. 基于多级残差映射器的文本驱动人脸图像生成和编辑[J]. 软件学报, 2023, 34(5): 2101-2115. LI Zonglin, ZHANG Shengping, LIU Yang, et al. Text-driven face image generation and manipulation via multi-level residual mapper[J]. Journal of Software, 2023, 34(5): 2101-2115.
[14] KIM M, JAIN A K, LIU X M. Adaface: quality adaptive margin for face recognition[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, USA: IEEE, 2022: 18750-18759.
[15] ZHU Y J, XU Q, ZHAO Y J, et al. Deep learning-assisted construction of three-dimensional facial midsa-gittal plane[J]. Journal of Peking University(Health Sciences), 2022, 54(1): 134-139.
[16] QI C R, SU H, MO K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, USA: IEEE, 2017: 652-660.
[17] QI C R, YI L, SU H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[J]. Advances in Neural Information Processing Systems, 2017, 30: 5099-5108.
[18] WANG Y, SUN Y B, LIU Z W, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 2019, 38(5): 1-12.
[19] WU W X, QI Z G, LI F X. PointConv: deep convolutional networks on 3d point clouds[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, USA: IEEE, 2019: 9621-9630.
[20] ZHAO H S, LI J, JIA J Y, et al. Point transformer[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV). Piscataway, USA: IEEE, 2021: 16259-16268.
[21] GUO M H, CAI J X, LIU Z N, et al. PCT: point cloud transformer[J]. Computational Visual Media, 2021, 7: 187-199.
[1] 徐芊芊,许倩,徐华畅,赵钰琳,徐凯,朱红. 基于CnViT的胶质瘤IDH1突变状态智能预测方法[J]. 山东大学学报 (工学版), 2023, 53(2): 127-134.
[2] 刘子一,崔超然,孟凡安,林培光. 基于批归一化统计量的无源多领域自适应方法[J]. 山东大学学报 (工学版), 2023, 53(2): 102-108.
[3] 曹春红,段鸿轩,曹玲,张乐乐,胡凯,肖芬. 基于多级特征级联的遥感图像实时语义分割[J]. 山东大学学报 (工学版), 2021, 51(2): 19-25.
[4] 彭岩,冯婷婷,王洁. 基于集成学习的O3的质量浓度预测模型[J]. 山东大学学报 (工学版), 2020, 50(4): 1-7.
[5] 李怡霏,郭尊华. 一种Chirplet神经网络自动目标识别算法[J]. 山东大学学报 (工学版), 2020, 50(3): 8-14.
[6] 王一宾,李田力,程玉胜,钱坤. 基于核极限学习机自编码器的标记分布学习[J]. 山东大学学报 (工学版), 2020, 50(3): 58-65.
[7] 李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[8] 高铭壑,张莹,张蓉蓉,黄子豪,黄琳焱,李繁菀,张昕,王彦浩. 基于预测数据特征的空气质量预测方法[J]. 山东大学学报 (工学版), 2020, 50(2): 91-99.
[9] 李英达,谢宗霞. 基于核相似性删减策略的支持向量回归算法[J]. 山东大学学报 (工学版), 2019, 49(3): 8-14.
[10] 张成彬,赵慧,曹宗钰. 基于深度学习的车身网络KWP2000协议漏洞挖掘[J]. 山东大学学报 (工学版), 2019, 49(2): 17-22.
[11] 庞阔,陈思琪,宋笑迎,邹丽. 基于粒计算的语言概念决策形式背景分析[J]. 山东大学学报 (工学版), 2018, 48(6): 74-81.
[12] 陈红,杨小飞,万青,马盈仓. 基于相关熵和流形学习的多标签特征选择算法[J]. 山东大学学报 (工学版), 2018, 48(6): 27-36.
[13] 梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.
[14] 何正义,曾宪华,郭姜. 一种集成卷积神经网络和深信网的步态识别与模拟方法[J]. 山东大学学报(工学版), 2018, 48(3): 88-95.
[15] 王婷婷,翟俊海,张明阳,郝璞. 基于HBase和SimHash的大数据K-近邻算法[J]. 山东大学学报(工学版), 2018, 48(3): 54-59.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发