基于SURF特征描述符和杰卡德距离的文物碎片拼接

刘晓宁; 狄宏璋; 杨稳; 林芃樾; 王世雄

doi:doi:10.3788/ope.20202804.0963

光学精密工程, 2020, 28 (4): 963, 网络出版: 2020-07-02

基于SURF特征描述符和杰卡德距离的文物碎片拼接

Mosaic of cultural relics fragments based on SURF feature extraction descriptor and Jaccard distance

论文大纲

刘晓宁 ^*狄宏璋杨稳林芃樾王世雄

作者单位

西北大学信息科学与技术学院, 陕西西安 710127

碎片拼接特征提取 SURF特征描述子边缘提取刚体变化 fragment splicing feature extraction Speeded Up Robust Features(SURF) descriptor edge extraction rigid body change

摘要

针对文物碎片拼接过程中存在因局部碎片缺失和纹饰几何特征受损导致断裂面特征提取不准确的问题, 本文提出了一种基于SURF特征描述符和杰卡德距离(Jaccard Distance)的文物碎片拼接方法。首先用Canny算子提取碎片边沿轮廓线以及模型表面纹饰线条, 再通过构造多尺度空间来提取断裂面特征点。其次, 针对以往构建特征描述符存在的高冗余和欧氏距离计算存在的高延时问题, 本文提出构造低冗余的SURF特征描述符, 再借助Jaccard距离来进行特征点的相似性比较, 确定碎片最优邻接关系。最后采用ICP方法计算得到刚体变化参数, 实现碎片较准确拼合。实验结果表明: 本文算法运行时间提高了12%~16%,拼接误差不超过0.750 mm。与传统方法相比, 本文方法能有效地减少因碎片模型受损而造成的拼接缝隙过大、渗透等现象, 拼合误差较小, 高效地实现碎片拼接。

Abstract

The feature extraction of a fracture surface is inaccurate due to the lack of local fragments and damage of the geometric features of ornamentation.Thus, in this paper, a method was proposed to solve this problem based on SURF feature descriptor and Jaccard distance. First, Canny operator was used to extract the contour lines of the debris edges and model surface, and a multi-scale space was constructed to extract the feature points of the fault surface. Second, to solve the high redundancy in constructing feature descriptors and high delay in Euclidean distance calculation, SURF feature descriptors with low redundancy was constructed, and then compared the similarity of feature points with Jaccard distance to determine the optimal adjacency relationship of fragments. Finally, the parameters of rigid body were calculated by ICP method, and the fragments were assembled accurately. The experimental results showed that the running time of the algorithm increased by 12%-16%, and the splicing error was at most 0.750 mm. Compared to the traditional method, the proposed method can effectively reduce the considerably large splicing gap and penetration caused by the damage of the fragment model,as well as the splicing error, and achieve fragment splicing efficiently.

参考文献

[1] 刘军, 周明全, 耿国华, 等.基于轮廓与断面匹配的秦俑碎片拼接方法［J］.计算机工程,2014,40(1): 181-185,190.

刘军, 周明全, 耿国华, 等.基于轮廓与断面匹配的秦俑碎片拼接方法［J］.计算机工程,2014,40(1): 181-185,190.

LIU J, ZHOU M Q, GENG G H, et al.. The splicing method of Qin Figurine fragments based on contour and section matching［J］. Computer Engineering, 2014, 40(1): 181-185,190.(in Chinese)

[2] 袁洁, 周明全, 耿国华, 等.基于轮廓线双向距离场的文物碎片拼接算法［J］.计算机工程, 2018,44(6): 207-212,218.

袁洁, 周明全, 耿国华, 等.基于轮廓线双向距离场的文物碎片拼接算法［J］.计算机工程, 2018,44(6): 207-212,218.

YUAN J, ZHOU M Q, GENG G H, et al.. Heritage debris splicing algorithm based on contour line two-way distance field［J］. Computer Engineering, 2018, 44(6): 207-212, 218.(in Chinese)

[3] 赵夫群,周明全,耿国华.基于轮廓曲线和特征区域的秦俑碎块匹配算法［J］.北京理工大学学报,2018,38(3): 293-299.

赵夫群,周明全,耿国华.基于轮廓曲线和特征区域的秦俑碎块匹配算法［J］.北京理工大学学报,2018,38(3): 293-299.

ZHAO F Q, ZHOU M Q, GENG G H. Terracotta warrior blocks matching algorithm based on conto-ur curve and feature region［J］. Journal of Beijing University of Technology, 2018, 38(3): 293-299.(in Chinese)

[4] MIKOLAJCZYK K, SCHMID C. Comparison of Aff-Ine-Invariant Local Detectors and Descriptor-S［C］.12th European Signal Processing Conference(EUSIPCO 2004), 2004: 1729-1732.

MIKOLAJCZYK K, SCHMID C. Comparison of Aff-Ine-Invariant Local Detectors and Descriptor-S［C］.12th European Signal Processing Conference(EUSIPCO 2004), 2004: 1729-1732.

[5] 李姗姗,耿国华,周明全,等.基于表面邻接约束的交互式文物碎片重组［J］.计算机辅助设计与图形学学报,2016,28(6): 924-931.

李姗姗,耿国华,周明全,等.基于表面邻接约束的交互式文物碎片重组［J］.计算机辅助设计与图形学学报,2016,28(6): 924-931.

LI SH SH, GENG G H, ZHOU M Q, et al.. Interactive reassembly of fractured fragments based on surface adjacency constraint［J］.Journal of computer aided design and graphics, 2016, 28(6): 924-931.(in Chinese)

[6] 袁洁, 周明全, 耿国华, 等.基于Morse-Smale拓扑特征的文物碎片拼接算法［J］.自动化学报,2018,44(8): 1486-1498.

袁洁, 周明全, 耿国华, 等.基于Morse-Smale拓扑特征的文物碎片拼接算法［J］.自动化学报,2018,44(8): 1486-1498.

YUAN J, ZHOU M Q, GENG G H, et al.. Automatic reassembly of fractured fragments using Morse topological features［J］. Acta Automatica Sinica, 2018, 44(8): 1486-1495.(in Chinese)

[7] SHENGLAN LIU, MUXIN SUN, XIAODONG HUANG, et al.. Feat-ure fusion using Extended Jaccard Graph and word embedding for robot［J］. Assembly Automation, 2017, 37(3): 278-284.

SHENGLAN LIU, MUXIN SUN, XIAODONG HUANG, et al.. Feat-ure fusion using Extended Jaccard Graph and word embedding for robot［J］. Assembly Automation, 2017, 37(3): 278-284.

[8] AYOUB K, AHMED D E M, MOHAMMED E H. A novel statistical model for content--based stereo image retrieval in the complex wavelet domain［J］. Journal of Visual Communication and Image Representation, 2018, 50: 27-39.

AYOUB K, AHMED D E M, MOHAMMED E H. A novel statistical model for content--based stereo image retrieval in the complex wavelet domain［J］. Journal of Visual Communication and Image Representation, 2018, 50: 27-39.

[9] 李群辉, 周明全, 耿国华.基于积分不变量的断裂面匹配算法［J］.计算机工程, 2012, 38(2): 1000-3428.

李群辉, 周明全, 耿国华.基于积分不变量的断裂面匹配算法［J］.计算机工程, 2012, 38(2): 1000-3428.

LI Q H, ZHOU M Q, GENG G H. Fracture surface mat-ching algorithm based on integral invariant-s［J］. Computer Engineering, 2012, 38(2): 1000-3428.(in Chinese)

[10] ZHAO Y, ZHAI Y, DUBOIS E, et al.. Image match-ing algorithm based on SIFT using color and expo-sure information［J］.Journal of Systems Engineering and Electronics,2016,27(3): 691-699.

ZHAO Y, ZHAI Y, DUBOIS E, et al.. Image match-ing algorithm based on SIFT using color and expo-sure information［J］.Journal of Systems Engineering and Electronics,2016,27(3): 691-699.

[11] MAMMONE N, IERACITANO C, ADELI H, et al.. Permutation jaccard distance-based hierarchical clustering to estimate eeg network density modif-ications in mci subjects［J］. IEEE transactions on neural networks and learning systems, 2018: 5122-5135.

MAMMONE N, IERACITANO C, ADELI H, et al.. Permutation jaccard distance-based hierarchical clustering to estimate eeg network density modif-ications in mci subjects［J］. IEEE transactions on neural networks and learning systems, 2018: 5122-5135.

[12] 王凡.基于sift的图像检索特征改进方法［J］.数字技术与应用, 2016(1): 139-141.

王凡.基于sift的图像检索特征改进方法［J］.数字技术与应用, 2016(1): 139-141.

WANG F. Image retrieval feature improvement meth-od based on SIFT［J］. Numerical Technology & Applications, 2016(1): 139-141.(in Chinese)

[13] BARG M C, MANGUM A J. A phase sepa-ration problem and geodesic disks on Cassinian ov-al surfaces［J］. Applied Mathematics and Computation, 2019, 354: 192-205.

BARG M C, MANGUM A J. A phase sepa-ration problem and geodesic disks on Cassinian ov-al surfaces［J］. Applied Mathematics and Computation, 2019, 354: 192-205.

[14] IWAHORI Y,TAKADA Y,SHIINA T, et al.. Defect classification of electronic board using dense SIFT and CNN［J］. Procedia Computer Science, 2018, 126: 1673-1682.

IWAHORI Y,TAKADA Y,SHIINA T, et al.. Defect classification of electronic board using dense SIFT and CNN［J］. Procedia Computer Science, 2018, 126: 1673-1682.

[15] CHANG X, DU S, LI Y, et al.. A coarse-to-fine geometric scale-invariant feature transform for large size high resolution satellite image registration［J］.Sensors, 2018, 18(5): 1-16.

CHANG X, DU S, LI Y, et al.. A coarse-to-fine geometric scale-invariant feature transform for large size high resolution satellite image registration［J］.Sensors, 2018, 18(5): 1-16.

[16] 樊彦国,柴江龙,许明明,等.基于ORB与RANSAC融合改进的图像配准［J］.光学精密工程,2019, 27(3): 702-717.

樊彦国,柴江龙,许明明,等.基于ORB与RANSAC融合改进的图像配准［J］.光学精密工程,2019, 27(3): 702-717.

PAN Y G, CHAI J L, XU M M, et al.. Image registration based on fusion of orb and RANSAC［J］.Opt. Precision Eng., 2019, 27(3): 702-717.

[17] MENG Y, ZHANG Z, YIN H, et al.. Automatic detection of particle size distribution by image analysis based on local adaptive canny edge detection and modified circular Hough transform［J］. Micron, 2018,106: 34-41.

MENG Y, ZHANG Z, YIN H, et al.. Automatic detection of particle size distribution by image analysis based on local adaptive canny edge detection and modified circular Hough transform［J］. Micron, 2018,106: 34-41.

[18] 周明全,袁洁,耿国华,等.基于轮廓线特征点的交互式文物拼接［J］.光学精密工程,2017,25(6): 1597-1606.

周明全,袁洁,耿国华,等.基于轮廓线特征点的交互式文物拼接［J］.光学精密工程,2017,25(6): 1597-1606.

ZHOU M Q, YUAN J, GENG G H, et al.. Interactive mosaic of cultural relics based on contour feature points［J］. Opt. Precision Eng., 2017, 25(6): 1597-1606.(in Chinese)

[19] LI A, JIANG W, YUAN W, et al.. An improv-ed FAST+SURF fast matching algorithm［J］. Proced-ia Computer Science, 2017, 107: 306-312.

LI A, JIANG W, YUAN W, et al.. An improv-ed FAST+SURF fast matching algorithm［J］. Proced-ia Computer Science, 2017, 107: 306-312.

[20] MENG C, CHEN Z, YANG H, et al.. Effect of strain rate and temperature on fracture and mi-crostructure evolution of AZ91D magnesium alloy processed by laser surface melting［J］. Metallurgic-al and MaterialsTransactions, 2018: 1-13

MENG C, CHEN Z, YANG H, et al.. Effect of strain rate and temperature on fracture and mi-crostructure evolution of AZ91D magnesium alloy processed by laser surface melting［J］. Metallurgic-al and MaterialsTransactions, 2018: 1-13

[21] RAFAEL B T, JOSE M J, JAVIER P F, et al.. Complex Gaussian processes for regression［J］. IEEE transactions on neural networks and learning systems, 2018: 5449-5511.

RAFAEL B T, JOSE M J, JAVIER P F, et al.. Complex Gaussian processes for regression［J］. IEEE transactions on neural networks and learning systems, 2018: 5449-5511.

[22] 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.

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.Reconstruction of 3D cultural relic fragments based on key point featur-e descriptors［J］.Journal of computer aided design a-nd graphics,2019,31(3): 393-399.(in Chinese)

[23] 肖启阳,李健,吴思进,等.基于能量的DSPI相位图正余弦降噪［J］.光学精密工程,2018,26(4): 936-943.

肖启阳,李健,吴思进,等.基于能量的DSPI相位图正余弦降噪［J］.光学精密工程,2018,26(4): 936-943.

XIAO Q Y, LI J, WU S J, et al.. Noise reduction of positive and cosine of DSPI phase diagram based on energy［J］. Opt. Precision Eng., 2018, 26(4): 936-943.(in Chinese)

刘晓宁, 狄宏璋, 杨稳, 林芃樾, 王世雄. 基于SURF特征描述符和杰卡德距离的文物碎片拼接[J]. 光学精密工程, 2020, 28(4): 963. LIU Xiao-ning, DI Hong-zhang, YANG Wen, LIN Peng-yue, WANG Shi-xiong. Mosaic of cultural relics fragments based on SURF feature extraction descriptor and Jaccard distance[J]. Optics and Precision Engineering, 2020, 28(4): 963.

基于SURF特征描述符和杰卡德距离的文物碎片拼接

关于本站 Cookie 的使用提示

全站搜索

基于SURF特征描述符和杰卡德距离的文物碎片拼接

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索