结合表面纹理与断裂轮廓的碎片拼接方法
|
摘要
陶土制文物在自然环境及人为发掘等过程中,碎片易受损缺失,断裂部位难以保证完整性,传统采用几何驱动的拼接方法受到限制。为此,针对断裂部位几何信息缺失的陶制文物碎片,提出一种结合表面几何纹理及断裂轮廓的拼接方法。使用Splatting lines生成方法提取碎片纹理特征线,对三维模型密集点采样,用不同参数溅射渲染2个深度图像,由两图像间差值生成线图。计算纹理形状边角信息,构造破损纹理约束条件,完成初步匹配。对断裂边界轮廓上的离散点集,利用遗传算法计算匹配点对,得到最终结果。实验结果表明,该方法能够实现缺损文物碎片的拼接,匹配度稳定在0. 53以上,且对纹理特征显著及缺损严重的碎片拼接效果较优。
In the process of natural environment and artificial excavation of pottery relics,the fragments are easy to be damaged and missing,and the integrity of the fracture site is difficult to be guaranteed. The traditional geometric driven splicing method is restricted. Aiming at the pottery relic fragments with missing geometric information,a splicing method combined with surface texture and fracture contour is proposed. Splatting lines method is used to extract the fragment texture feature lines,sampling the dense points of the 3 D model,sputter two depth images with different parameters,and generate the graph by the difference between the two images. The edge and angle information of texture shape is calculated,and the constraint condition of damaged texture is constructed,and the initial matching is completed. For the discrete point set on the fracture boundary contour,the matching point pair is calculated by genetic algorithm,and the final result is obtained. Experimental results show that this method can realize the splicing of defective cultural relics fragments,and the matching degree is above 0. 53,and the splicing effect of fragments with obvious texture feature and serious defects is better.
In the process of natural environment and artificial excavation of pottery relics,the fragments are easy to be damaged and missing,and the integrity of the fracture site is difficult to be guaranteed. The traditional geometric driven splicing method is restricted. Aiming at the pottery relic fragments with missing geometric information,a splicing method combined with surface texture and fracture contour is proposed. Splatting lines method is used to extract the fragment texture feature lines,sampling the dense points of the 3 D model,sputter two depth images with different parameters,and generate the graph by the difference between the two images. The edge and angle information of texture shape is calculated,and the constraint condition of damaged texture is constructed,and the initial matching is completed. For the discrete point set on the fracture boundary contour,the matching point pair is calculated by genetic algorithm,and the final result is obtained. Experimental results show that this method can realize the splicing of defective cultural relics fragments,and the matching degree is above 0. 53,and the splicing effect of fragments with obvious texture feature and serious defects is better.
引文
[1]ZHANG K,LI X.A graph-based optimization algorithm for fragmented image reassembly[J].Graphical Models,2014,76(5):484-495.
[2]ROCCO I,ARANDJELOVIC R,SIVIC J.Convolutional neural network architecture for geometric matching[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2017:39-48.
[3]曹戴,陈丽芳.基于杰卡德度量的智能拼图改进算法[J].计算机工程与应用,2018,54(2):188-192,197.
[4]韩盈盈,章毅鹏,沈鸿平,等.基于遗传算法和0-1规划的规则图形碎片拼接[J].电子科技,2015,28(5):136-139.
[5]TSANG P W M,SITU W C.Affine invariant matching of broken boundaries based on simple genetic algorithm and contour reconstruction[J].Pattern Recognition Letters,2010,31(9):771-780.
[6]KHALID S,SABIR B,JABBAR S,et al.Precise shape matching of large shape datasets using hybrid approach[J].Journal of Parallel and Distributed Computing,2017,110:16-30.
[7]SAMMOUD O,SOLNON C,GHEDIRA K.Ant algorithm for the graph matching problem[C]//Proceedings of the 5th European Conference on Evolutionary Computation in Combinatorial Optimization.Berlin,Germany:Springer,2005:213-223.
[8]UCOLUK G,TOROSLU I H.Automatic reconstruction of broken 3-D surface objects[J].Computers and Graphics,1999,23(4):573-582.
[9]ALTANTSETSEG E,MATSUYAMA K,KONNO K.Pairwise matching of 3D fragments using fast fourier transform[J].Visual Computer,2014,30(6-8):929-938.
[10]COHEN F,LIU Z,EZGI T.Virtual reconstruction of archeological vessels using expert priors and intrinsic differential geometry information[J].Computers and Graphics,2013,37(1/2):41-53.
[11]LI Q,ZHOU M,GENG G.Pairwise matching of 3Dfragments[C]//Proceedings of 2012 International Conference on Information Management,Innovation Management and Industrial Engineering.Washington D.C.,USA:IEEE Press,2012:479-482.
[12]BERNARD F,SCHMIDT F R,THUNBERG J,et al.Acombinatorial solution to non-rigid 3D shape-to-image matching[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:1000-1009.
[13]HUANG Q X,FLORY S,GELFAND N,et al.Reassembling fractured objects by geometric matching[J].ACMTransactions on Graphics,2006,25(3):569-578
[14]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.
[15]SUN Q,ZHANG L,HE Y.Splatting lines for 3D mesh illustration[C]//Proceedings of the ACM SIGGRAPHSymposium on Interactive 3D Graphics and Games.New York,USA:ACM Press,2013:193-193.
[16]ZHANG L,SUN Q,HE Y.Splatting lines:an efficient method for illustrating 3D surfaces and volumes[C]//Proceedings of the 18th Meeting of the ACMSIGGRAPH Symposium on Interactive 3D Graphics and Games.New York,USA:ACM Press,2014:135-142.
[17]TSANG P W M.A genetic algorithm for affine invariant object shape recognition[C]//Proceedings of the 1st International Conference on Genetic Algorithms in Engineering Systems:Innovations and Applications.[S.l.]:IET,1995:293-298.
[18]TSANG P W M.A genetic algorithm for affine invariant recognition of object shapes from broken boundaries[J].Pattern Recognition Letters,1997,18(7):631-639.
[19]TSANG P W M,SITU W C.Affine invariant matching of broken boundaries based on simple genetic algorithm and contour reconstruction[J].Pattern Recognition Letters,2010,31(9):771-780.
[20]李群辉,张俊祖,耿国华,等.以轮廓曲线为特征的断裂面匹配[J].西安交通大学学报,2016,50(9):105-110.
[21]赵夫群,耿国华.基于特征点的秦俑断裂面匹配方法[J].激光与光电子学进展,2018,55(4):128-134.
[2]ROCCO I,ARANDJELOVIC R,SIVIC J.Convolutional neural network architecture for geometric matching[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2017:39-48.
[3]曹戴,陈丽芳.基于杰卡德度量的智能拼图改进算法[J].计算机工程与应用,2018,54(2):188-192,197.
[4]韩盈盈,章毅鹏,沈鸿平,等.基于遗传算法和0-1规划的规则图形碎片拼接[J].电子科技,2015,28(5):136-139.
[5]TSANG P W M,SITU W C.Affine invariant matching of broken boundaries based on simple genetic algorithm and contour reconstruction[J].Pattern Recognition Letters,2010,31(9):771-780.
[6]KHALID S,SABIR B,JABBAR S,et al.Precise shape matching of large shape datasets using hybrid approach[J].Journal of Parallel and Distributed Computing,2017,110:16-30.
[7]SAMMOUD O,SOLNON C,GHEDIRA K.Ant algorithm for the graph matching problem[C]//Proceedings of the 5th European Conference on Evolutionary Computation in Combinatorial Optimization.Berlin,Germany:Springer,2005:213-223.
[8]UCOLUK G,TOROSLU I H.Automatic reconstruction of broken 3-D surface objects[J].Computers and Graphics,1999,23(4):573-582.
[9]ALTANTSETSEG E,MATSUYAMA K,KONNO K.Pairwise matching of 3D fragments using fast fourier transform[J].Visual Computer,2014,30(6-8):929-938.
[10]COHEN F,LIU Z,EZGI T.Virtual reconstruction of archeological vessels using expert priors and intrinsic differential geometry information[J].Computers and Graphics,2013,37(1/2):41-53.
[11]LI Q,ZHOU M,GENG G.Pairwise matching of 3Dfragments[C]//Proceedings of 2012 International Conference on Information Management,Innovation Management and Industrial Engineering.Washington D.C.,USA:IEEE Press,2012:479-482.
[12]BERNARD F,SCHMIDT F R,THUNBERG J,et al.Acombinatorial solution to non-rigid 3D shape-to-image matching[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:1000-1009.
[13]HUANG Q X,FLORY S,GELFAND N,et al.Reassembling fractured objects by geometric matching[J].ACMTransactions on Graphics,2006,25(3):569-578
[14]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.
[15]SUN Q,ZHANG L,HE Y.Splatting lines for 3D mesh illustration[C]//Proceedings of the ACM SIGGRAPHSymposium on Interactive 3D Graphics and Games.New York,USA:ACM Press,2013:193-193.
[16]ZHANG L,SUN Q,HE Y.Splatting lines:an efficient method for illustrating 3D surfaces and volumes[C]//Proceedings of the 18th Meeting of the ACMSIGGRAPH Symposium on Interactive 3D Graphics and Games.New York,USA:ACM Press,2014:135-142.
[17]TSANG P W M.A genetic algorithm for affine invariant object shape recognition[C]//Proceedings of the 1st International Conference on Genetic Algorithms in Engineering Systems:Innovations and Applications.[S.l.]:IET,1995:293-298.
[18]TSANG P W M.A genetic algorithm for affine invariant recognition of object shapes from broken boundaries[J].Pattern Recognition Letters,1997,18(7):631-639.
[19]TSANG P W M,SITU W C.Affine invariant matching of broken boundaries based on simple genetic algorithm and contour reconstruction[J].Pattern Recognition Letters,2010,31(9):771-780.
[20]李群辉,张俊祖,耿国华,等.以轮廓曲线为特征的断裂面匹配[J].西安交通大学学报,2016,50(9):105-110.
[21]赵夫群,耿国华.基于特征点的秦俑断裂面匹配方法[J].激光与光电子学进展,2018,55(4):128-134.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |