二维碎片拼接的局部匹配

详细信息    查看全文 | 推荐本文 |

英文篇名：Local matching for 2-D fragments reassembling 作者：房然然 ; 黄发忠 ; 辛化梅 英文作者：FANG Ran-ran;HUANG Fa-zhong;XIN Hua-mei;College of Physics and Electronics,Shandong Normal University; 关键词：碎片拼接 ; 多边形逼近 ; 旋转角度 ; 局部匹配 英文关键词：fragment reassembling;;polygon approximation;;rotation angle;;local matching 中文刊名：XDDJ 英文刊名：Modern Electronics Technique 机构：山东师范大学物理与电子科学学院; 出版日期：2015-05-01 出版单位：现代电子技术 年：2015 期：v.38;No.440 基金：教育部留学回国人员科研启动基金项目(教外司留2009-36);; 山东省优秀中青年科学家科研奖励基金(BS2013DX035);; 国家自然科学基金(61401259) 语种：中文; 页：XDDJ201509014 页数：3 CN：09 ISSN：61-1224/TN 分类号：62-64

摘要

基于轮廓的二维非规则碎片拼接问题,通常分为局部匹配和全局匹配两个步骤,这里提出一种新的局部匹配的方法,首先对轮廓进行多边形逼近得到多边形顶点序列,然后获取多边形顶点的转角序列特征并计算相邻顶点间长度,对该转角序列使用改进过的"坦克算法",应用一定筛选规则,寻找到多边形顶点的若干候选匹配信息。改进的算法可降低时间复杂度,提高匹配效率。
        The 2-D irregular fragments reassembling issue based on contour is usually divided into two steps:local matching and global matching. A new local matching method based on improved Tank algorithm is proposed. Firstly the sequence of polygon vertices is obtained by polygonal approximation to the contour,then the corner sequence signature of the polygon is acquired,the distance between two adjacent vertices is calculated. The improved Tank algorithm is applied in the corner sequence to find some candidate matching information of the polygon vertices by some screening rules. The improved algorithm can reduce time complexity and improve matching efficiency.

引文

[1]WOLFSON H.On curve matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(5):483-489.
    [2]DA GAMA LEITAO H C,STOLFI J.A multiscale method for the reassembly of two-dimensional fragmented objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(9):1239-1251.
    [3]KONG Wei-xin,KIMIA B B.On solving 2D and 3D puzzles using curve matching[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2001,2:583-590.
    [4]AMIGONI F,GAZZANI S,PODICO S.A method for reassembling fragments in image reconstruction[C]//Proceedings of2003 International Conference on Image Processing.[S.l.]:IEEE,2003,2:581-584.
    [5]ZHU Liang-jia,ZHOU Zong-tan,HU De-wen.Globally consistent reconstruction of ripped-up documents[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(1):1-13.
    [6]朱延娟,周来水,张丽艳,等.基于Hausdorff距离的多尺度轮廓匹配算法[J].中国机械工程,2004,15(17):1553-1561.
    [7]周丰,黄晓鸣.基于角序列的二维碎片轮廓匹配算法[J].科学技术与工程,2007,7(15):3757-3760.
    [8]饶芮菱,金雪峰,鲁怀伟.基于链码的二维碎片轮廓匹配算法[J].计算技术与自动化,2007,26(2):34-37.
    [9]JUSTINO E,OLIVEIRA L S,FREITAS C.Reconstructing shredded documents through feature matching[J].Forensic Science International,2006,160(2):140-147.
    [10]ROSIN P L,WEST G A W.Non-parametric segmentation of curves into various representations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(2):1140-1153.