郭斯羽,胡萍萍,唐 璐,温 和,刘 敏.基于区域重构的树状骨架快速去毛刺方法[J].电子测量与仪器学报,2020,34(4):58-64
基于区域重构的树状骨架快速去毛刺方法
Fast pruning method for tree-structured skeletonsbased on region reconstruction
  
DOI:
中文关键词:  区域骨架  骨架化  骨架去毛刺  重构触发策略  游程森林
英文关键词:region skeleton  skeletonization  skeleton pruning  reconstruction triggering strategy  runforest
基金项目:国家自然科学基金(61471167)、湖南省自然科学基金杰出青年基金(2019JJ20001)资助项目
作者单位
郭斯羽 1.湖南大学 电气与信息工程学院 
胡萍萍 1.湖南大学 电气与信息工程学院 
唐 璐 1.湖南大学 电气与信息工程学院 
温 和 1.湖南大学 电气与信息工程学院 
刘 敏 1.湖南大学 电气与信息工程学院 
AuthorInstitution
Guo Siyu 1.College of Electrical and Information Engineering, Hunan University 
Hu Pingping 1.College of Electrical and Information Engineering, Hunan University 
Tang Lu 1.College of Electrical and Information Engineering, Hunan University 
Wen He 1.College of Electrical and Information Engineering, Hunan University 
Liu Min 1.College of Electrical and Information Engineering, Hunan University 
摘要点击次数: 630
全文下载次数: 486
中文摘要:
      区域骨架去毛刺是骨架提取与应用中的重要问题。 常见的去毛刺途径之一,是用基于区域重构的骨架显著性指标对骨 架进行阈值化处理,但存在算法参数难以直观设置、去毛刺效果不易控制、运行速度较慢等问题。 针对上述问题,提出了一种逐 次剪除骨架分枝的去毛刺方法,以突出部分骨架长度为显著性指标,每次剪除显著性最低的一个分枝,直至剩余分枝达到给定 数量;为提高算法速度,采用了游程森林结构加速区域重构操作,提出了重构触发策略来减少重构次数。 在实际图像集上的实 验结果表明,提出的方法的正确骨架分枝的召回率较对比算法高 13%,准确率高近 3%;采用重构触发策略的算法运行时间平 均为未采用该策略算法的约 56%。 实验结果表明了所提方法的有效性。
英文摘要:
      Skeleton pruning is an important issue in skeleton extraction and application. A common pruning approach utilizes the thresholding of skeletal components by saliency indices based on region reconstruction. However, this approach suffers difficulties in algorithmic parameter setting, pruning outcome control, and the execution time. To deal with these difficulties, a pruning method is proposed that iteratively removes the skeletal components. The punctuating skeleton length saliency index is used, and in each iteration, the least salient skeleton branch is pruned out, until the number of the remaining branches reaches a user defined level. In order to accelerate the algorithm, the RunForest data structure is adopted for region reconstruction operations, and the reconstruction triggering strategy (RTS) is proposed to reduce the number of reconstructions needed. Experimental results on a real-world image base show that the recall of the skeletal branches of the proposed method is higher than the existing algorithm by 13 percentage points, and the precision, by about 3 points. The execution time of the algorithm with RTS is about 56% that of without. The results show that the proposed method is effective.
查看全文  查看/发表评论  下载PDF阅读器