期刊文献+

一种串行/并行两用的区域标记算法 被引量:4

Serial/Parallel Algorithm for Region Labeling
下载PDF
导出
摘要 通过设计一种游程与目标体间接关联的数据结构实现游程标记冲突的实时解决,提出一种基于游程的顺序扫描式区域标记算法,只需一次扫描分析即可获取游程区域表达,复杂度低,编码实现方便,易于扩展应用于并行计算系统中进行并行标记。实验结果表明,该算法与已有算法相比,拥有更高效的串行标记性能,在进行并行标记时具有近似线性的加速比。 By designing a structure of run-length associated indirectly with object to solve the problem of run-length labeling conflict in real time,an efficient run-length based and raster-scanned region labeling algorithm is proposed,which can acquire the run-length region representation by only one scan.The algorithm owns low complexity for easy implementation,and can be easily extended to implement parallel labeling in parallel computing system.Experimental results show that the algorithm is more efficient than other algorithms in serial labeling,and gains approximate linear speedup ratio in parallel labeling.
出处 《计算机工程》 CAS CSCD 北大核心 2010年第9期17-19,22,共4页 Computer Engineering
基金 国家“863”计划基金资助项目(2008AA8041205)
关键词 区域标记 游程 目标体索引 目标体双重索引 并行标记 加速比 region labeling run-length object index object dual index parallel labeling speedup ratio
  • 相关文献

参考文献7

  • 1Shima Y.A High Speed Algorithm for Propagation-type Labeling Based on Block Sorting of Runs in Binary Images[C]//Proc.of the 10th International Conference on Pattern Recognition.[S.l.]:IEEE Press,1990:655-658.
  • 2Chang Fu,Chen Chun-Jen,Lu Chi-Jen.A Linear-time Component-labeling Algorithm Using Contour Tracing Technique[J].Computer Vision and Image Understanding,2004,93(2):206-220.
  • 3Rosenfeld A,Pfaltz J L.Sequential Operations in Digital Picture Processing[J].Journal of ACM,1966,13(4):471-494.
  • 4Stefano L D,Bulgarelli A.A Simple and Efficient Connected Components Labeling Algorithm[C]//Proc.of Int'l Conference on Image Analysis and Processing.[S.l.]:IEEE Press,1999:322-327.
  • 5Suzuki K.Linear-time Connected-component Labeling Based on Sequential Local Operations[J].Computer Vision and Image Understanding,2003,89(1):1-23.
  • 6Dillencourt M B,Samet H,Tamminen M.A General Approach to Connected Component Labeling for Arbitrary Image Repre-sentations[J].Journal of ACM,1992,39(2):253-280.
  • 7徐利华,陈早生.二值图像中的游程编码区域标记[J].光电工程,2004,31(6):63-65. 被引量:31

二级参考文献4

  • 1[1]CASTLMAN K R. Digital Image Processing [M].北京:清华大学出版社,1998.480-481.
  • 2[2]SONKA M, HLAVAC V, BOYLE R. Image Processing Analysis and Machine Vision 2 ed [M].北京:人民邮电出版社,2002. 232 - 236.
  • 3[3]PRATT W K. Digital Image Processing: PIKS Inside, 3 ed.[M]. New York: John Wiley & Sons, Inc, 2001. 581 - 583.
  • 4[4]FREEMAN H. Boundary Encoding and Processing [A]. Picture Processing and Psychopictorics[C], New York: Academic Press, 1970. 241-266.

共引文献30

同被引文献26

  • 1徐利华,陈早生.二值图像中的游程编码区域标记[J].光电工程,2004,31(6):63-65. 被引量:31
  • 2张桂林,陈益新,曹伟,李强.基于跑长码的连通区域标记算法[J].华中理工大学学报,1994,22(5):11-14. 被引量:27
  • 3SUZUKI K, HORIBA I, SUGIE N. Linear-time connected-compo- nent labeling based on sequential local operations [ J]. Computer Vision and Image Understanding, 2003, 89(1): 1 -23.
  • 4AIZAWA K, TANAKA S, MOTOMURA K, et al. Algorithms for connected component labeling based on quadtrees [ J]. International Journal of Imaging Systems and Technology, 2009, 19(2): 158 - 166.
  • 5KESHENG W, EKOW O, ARIES. Optimizing connected compo- nent labeling algorithms [C]// Proceedings of SPIE 5747. San Die- go: SPIE, 2005:1965-1976.
  • 6贾云得.机器视觉[M].北京:科学出版社,2004
  • 7杨妮,王玉田.玻璃厚度检测图像特点及其识别算法的研究[J].半导体光学,2008,29(6):954-959.
  • 8Messom CH, Demidenko S, Subramaniam K. Size poison identification in realtime image processing using run length encoding. Instrumentation and Measurement Technology Conference (IMTC)2002. Anchorage, Reading. 2002. 1055- 1060.
  • 9Gupta GS, Win TA, Messom C, Demidenko S, et al. Defect analysis of gritblasted or spraypainted surface using vision sensing techniques, hnage and Vision Computing, NewZealand. 2003.18-23.
  • 10Dillencourt MB, Samet H, Tarnminen M. A general approach to connected component labeling for arbitrary image representations. Journal of the Association for Computing Machinery(ACM), 1992, 39(2): 253-280.

引证文献4

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部