Matching method of cultural relics fragments based on multi-feature parameters fusion

ZHAO Fuqun; ZHOU Mingquan

doi:10.37188/OPE.20233110.1522

您当前的位置：

首页 >

文章列表页 >

Matching method of cultural relics fragments based on multi-feature parameters fusion

Information Sciences | 更新时间：2026-09-12

- Matching method of cultural relics fragments based on multi-feature parameters fusion
- Optics and Precision Engineering Vol. 31, Issue 10, Pages: 1522-1531(2023)
- 作者机构：
  
  1.西安财经大学信息学院，陕西西安 710100
  2.西北大学信息科学与技术学院，陕西西安 710127
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233110.1522
  CLC： TP391
- Received：08 July 2022，
  
  Revised：2022-09-30，
  
  Published：25 May 2023
- 稿件说明：
移动端阅览
赵夫群,周明全.基于多特征参数融合的文物碎片自动匹配方法[J].光学精密工程,2023,31(10):1522-1531.

ZHAO Fuqun,ZHOU Mingquan.Matching method of cultural relics fragments based on multi-feature parameters fusion[J].Optics and Precision Engineering,2023,31(10):1522-1531.
赵夫群,周明全.基于多特征参数融合的文物碎片自动匹配方法[J].光学精密工程,2023,31(10):1522-1531. DOI： 10.37188/OPE.20233110.1522.

ZHAO Fuqun,ZHOU Mingquan.Matching method of cultural relics fragments based on multi-feature parameters fusion[J].Optics and Precision Engineering,2023,31(10):1522-1531. DOI： 10.37188/OPE.20233110.1522.

摘要

针对基于单一几何特征的文物碎片匹配方法的精度不高的问题，提出一种基于多特征参数融合的文物碎片自动匹配方法。首先，采用分割算法提取文物碎片的断裂面，并计算断裂面上点的四个特征参数：点到邻域点的平均距离、点到邻域重心的距离、曲率以及邻域法向夹角平均值；然后，融合四个特征参数得到特征判别参数，并通过判断特征判别参数值提取出特征点集；最后，采用基于尺度因子的迭代最近点（Iterative Closest Point， ICP）算法对特征点集进行匹配，从而实现文物碎片的断裂面匹配。实验采用兵马俑碎片的点云数据模型来验证该基于多特征参数融合的文物碎片匹配方法，结果表明该匹配方法可以克服基于单一几何特征匹配方法的精度不够高的问题，比已有算法的匹配精度提高15%以上，时间效率提高20%以上。因此说，该基于多特征参数融合的匹配方法是一种有效的文物碎片匹配方法。

Abstract

To address the low accuracy of the single-geometric-feature-based matching method for cultural relic fragments， an alternative multi-feature-parameter-fusion-based automatic matching method is proposed herein. For this， first， a segmentation algorithm is used to extract the fracture surfaces of cultural relic fragments， and the following four characteristic parameters of points on these fracture surfaces are computed： the average distance from a point to its neighborhood points， distance from a point to the gravity center of its neighborhood， curvature， and average value of the normal included angle of the neighborhood. Following this， the four feature parameters are fused to obtain feature discrimination parameters， and a feature point set is extracted by judging the value of these feature discrimination parameters. Finally， the iterative closest point algorithm based on the scale factor is used to match the feature point set， and consequently， accurate fracture surface matching of cultural relic fragments is achieved. In the experiment， a point cloud data model of Terracotta Warriors fragments is used to verify the performance of the multi-feature-parameter-fusion-based matching method for cultural relic fragments. The results reveal that the proposed matching method can overcome the low accuracy of the single-geometric-feature-based matching method. Compared with the matching accuracy of the existing algorithm， that of the proposed algorithm is improved by more than 15%， while its time efficiency is improved by more than 20%. Therefore， the multi-feature-parameter-fusion-based matching method is effective for cultural relic fragment matching.

关键词

Keywords

references

李娇娇，孙红岩，董雨，等 . 基于深度学习的3维点云处理综述［J］. 计算机研究与发展， 2022 ， 59 （ 5 ）： 1160 - 1179 . doi: 10.7544/issn1000-1239.20210131 http://dx.doi.org/10.7544/issn1000-1239.20210131

LI J J ， SUN H Y ， DONG Y ， et al . Survey of 3-dimensional point cloud processing based on deep learning ［J］. Journal of Computer Research and Development ， 2022 ， 59 （ 5 ）： 1160 - 1179 . （in Chinese） . doi: 10.7544/issn1000-1239.20210131 http://dx.doi.org/10.7544/issn1000-1239.20210131

GAO H J ， GENG G H ， ZENG S . Approach for 3D cultural relic classification based on a low-dimensional descriptor and unsupervised learning ［J］. Entropy ， 2020 ， 22 （ 11 ）： 1290 . doi: 10.3390/e22111290 http://dx.doi.org/10.3390/e22111290

WEN Y ， ZHOU M Q ， ZHANG P F ， et al . Matching method of cultural relic fragments constrained by thickness and contour feature ［J］. IEEE Access ， 2020 ， 8 ： 25892 - 25904 . doi: 10.1109/access.2020.2969995 http://dx.doi.org/10.1109/access.2020.2969995

耿国华，张鹏飞，刘雨萌，等 . 基于断裂面邻域特征的文物碎片拼接［J］. 光学精密工程， 2021 ， 29 （ 5 ）： 1169 - 1179 . doi: 10.37188/OPE.20212905.1169 http://dx.doi.org/10.37188/OPE.20212905.1169

GENG G H ， ZHANG P F ， LIU Y M ， et al . Reassembly method of cultural relic fragments based on the neighborhood characteristics of fracture surface ［J］. Opt. Precision Eng. ， 2021 ， 29 （ 5 ）： 1169 - 1179 . （in Chinese） . doi: 10.37188/OPE.20212905.1169 http://dx.doi.org/10.37188/OPE.20212905.1169

胡佳贝，周蓬勃，耿国华，等 . 基于生成树代价和和几何约束的文物碎片自动重组方法［J］. 自动化学报， 2020 ， 46 （ 5 ）： 946 - 956 .

HU J B ， ZHOU P B ， GENG G H ， et al . Reassembly of fractured fragments based on spanning tree cost and geometric constraints ［J］. Acta Automatica Sinica ， 2020 ， 46 （ 5 ）： 946 - 956 . （in Chinese）

高宏娟，耿国华，王飘 . 基于关键点特征描述子的三维文物碎片重组［J］. 计算机辅助设计与图形学学报， 2019 ， 31（ 3 ） 393 - 399

GAO H J ， GENG G H ， WANG P . 3D archaeological fragment reassembly based on feature descriptors of key points ［J］. Journal of Computer-Aided Design & Computer Graphics ， 2019 ， 31 （ 3 ）： 393 - 399 . （in Chinese）

LI Y J ， ZHANG J W ， ZHONG Y Z ， et al . An efficient stereo matching based on fragment matching ［J］. The Visual Computer ， 2019 ， 35 （ 2 ）： 257 - 269 . doi: 10.1007/s00371-018-1491-0 http://dx.doi.org/10.1007/s00371-018-1491-0

YU S Y ， SUN S ， YAN W ， et al . A method based on curvature and hierarchical strategy for dynamic point cloud compression in augmented and virtual reality system ［J］. Sensors ， 2022 ， 22 （ 3 ）： 1262 . doi: 10.3390/s22031262 http://dx.doi.org/10.3390/s22031262

ZHANG C J ， XU S H ， JIANG T ， et al . Integrating normal vector features into an atrous convolution residual network for LiDAR point cloud classification ［J］. Remote Sensing ， 2021 ， 13 （ 17 ）： 3427 . doi: 10.3390/rs13173427 http://dx.doi.org/10.3390/rs13173427

LU Q N ， ZHUOMA S N ， GE B Z ， et al . Turbulent-degraded image restoration via improved principal component analysis method ［J］. Journal of Modern Optics ， 2021 ， 68 （ 17 ）： 906 - 915 . doi: 10.1080/09500340.2021.1960445 http://dx.doi.org/10.1080/09500340.2021.1960445

SARITA K ， DEVARAPALLI R ， KUMAR S ， et al . Principal component analysis technique for early fault detection ［J］. Journal of Intelligent & Fuzzy Systems ， 2022 ， 42 （ 2 ）： 861 - 872 . doi: 10.3233/jifs-189755 http://dx.doi.org/10.3233/jifs-189755

BESL P J ， MCKAY N D . A method for registration of 3-D shapes ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 1992 ， 14 （ 2 ）： 239 - 256 . doi: 10.1109/34.121791 http://dx.doi.org/10.1109/34.121791

赵夫群 . 基于多特征的兵马俑断裂面匹配方法研究［D］. 西安：西北大学， 2019 . doi: 10.21629/jsee.2018.01.20 http://dx.doi.org/10.21629/jsee.2018.01.20

ZHAO F Q . Research on Fracture Surface Matching Method for Terracotta Warriors Based on Multi-Feature ［D］ . Xi'an ： Northwest University ， 2019 . （in Chinese） . doi: 10.21629/jsee.2018.01.20 http://dx.doi.org/10.21629/jsee.2018.01.20

SUN Z L ， ZHANG R G ， HU J ， et al . Probability re-weighted 3D point cloud registration for missing correspondences ［J］. Multimedia Tools and Applications ， 2022 ， 81 （ 8 ）： 11107 - 11126 . doi: 10.1007/s11042-022-12134-5 http://dx.doi.org/10.1007/s11042-022-12134-5

LI J L ， LI Y T ， LONG J ， et al . SAP-net： a simple and robust 3D point cloud registration network based on local shape features ［J］. Sensors ， 2021 ， 21 （ 21 ）： 7177 . doi: 10.3390/s21217177 http://dx.doi.org/10.3390/s21217177

HU Q L ， NIU J Y ， WANG Z W ， et al . Improved point cloud registration with scale invariant feature extracted ［J］. Journal of Russian Laser Research ， 2021 ， 42 （ 2 ）： 219 - 225 . doi: 10.1007/s10946-021-09953-6 http://dx.doi.org/10.1007/s10946-021-09953-6

李群辉 . 基于断裂面匹配的破碎刚体复原研究［D］. 西安：西北大学， 2013 . doi: 10.1109/icig.2013.117 http://dx.doi.org/10.1109/icig.2013.117

LI Q H . Research on Restoration of Broken Rigid Body Based on Fracture Surface Matching ［D］. Xi'an ： Northwest University ， 2013 . （in Chinese） . doi: 10.1109/icig.2013.117 http://dx.doi.org/10.1109/icig.2013.117

Views

414

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Rapid registration for neighborhood distribution of 3D point cloud

Point cloud matching algorithm based on adaptive local neighborhood conditions

Hierarchical optimization of skull point cloud registration

Optimization registration of point cloud model of skull

Comparison inspection between ICT images & CAD model based on edge extracting by neural networks

Related Author

LIU Zhongyuan

LIU Hao

DU Liuqing

FANG Rong

YU Yongwei

SUO Hongyan

GUO Songtao

WANG Jin

Related Institution

College of Mechanical Engineering， Chongqing University of Technology

Shanxi Coal Geological Survey and Mapping Institute Co.， Ltd

School of Surveying and Spatial Information， Shandong University of Science and Technology

School of Geospatial Information， University of Information Engineering， Strategic Support Force of the People's Liberation Army of China

College of Information Science and Technology, Northwest University, Xi′an

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰