基于向量内积的新型骨架提取方法

胡斯淼; 任洪娥; 于鸣; 姜士辉; 齐红

doi:10.3788/YJYXS20153005.0844

您当前的位置：

首页 >

文章列表页 >

基于向量内积的新型骨架提取方法

成像技术与图像处理 | 更新时间：2020-08-12

- 基于向量内积的新型骨架提取方法
- A new skeleton extraction method based on vector inner production
- 液晶与显示 2015年30卷第5期页码：844-850
- 作者机构：
  
  1. 东北林业大学信息与计算机工程学院, 黑龙江哈尔滨 150040
  2. 黑龙江省林业智能装备工程研究中心, 黑龙江哈尔滨 150040
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目(No.31370566)();黑龙江省自然科学基金重点项目(No.ZD201203)()
- DOI：10.3788/YJYXS20153005.0844
  中图分类号： TP391.41
- 收稿日期：2015-09-24，
  
  修回日期：2015-10-05，
  
  网络出版日期：2014-11-05，
  
  纸质出版日期：2015-10-05
- 稿件说明：
移动端阅览
胡斯淼, 任洪娥, 于鸣, 姜士辉, 齐红. 基于向量内积的新型骨架提取方法[J]. 液晶与显示, 2015,30(5): 844-850

HU Si-miao, REN Hong-e, YU Ming, JIANG Shi-hui, QI Hong. A new skeleton extraction method based on vector inner production[J]. , 2015,30(5): 844-850
胡斯淼, 任洪娥, 于鸣, 姜士辉, 齐红. 基于向量内积的新型骨架提取方法[J]. 液晶与显示, 2015,30(5): 844-850 DOI： 10.3788/YJYXS20153005.0844.

HU Si-miao, REN Hong-e, YU Ming, JIANG Shi-hui, QI Hong. A new skeleton extraction method based on vector inner production[J]. , 2015,30(5): 844-850 DOI： 10.3788/YJYXS20153005.0844.

摘要

为了提高骨架提取的准确性和连通性

提出了一种基于向量内积的新型骨架提取方法。对二值图像进行欧氏距离变换

获得了由内部像素点指向边界点的边界向量

通过比较内部像素点8-邻域范围内对应边界向量内积值符号在4个方向上的变化情况确定了边界向量方向发生重大变化的次数

并据此选取候选骨架点;采用基于回归分析的方法确定延伸方向

并完成连接操作生成完整的骨架线。实验结果表明

该算法能够保证骨架的连通性和完整性

且骨架定位准确

平均正确率达到92.27%

同时可以克服边界扰动

是一种有效的骨架提取算法。

Abstract

A new method for skeleton extraction based on vector inner product was presented in order to improve the accuracy and connectivity. Euclidean distance transform is used to determine the nearest edge element for each pixel in a binary image. A vector from each pixel that stops at the nearest edge element is defined as edge vector. By comparing the inner product of edge vector within 8-neighborhood of the pixel

the number of significant changes in direction can be determined

and the candidate skeleton points can be selected according to it. Finally

a complete skeleton was generated by extending process based on regression analysis. Experimental results show that the algorithm can guarantee connectivity and integrity of the skeleton

and the average accuracy rate of location reached 92.27%. It also has advantages in reflecting the topological structures of objects and overcoming boundary disturbance. So

it is an effective skeleton extraction algorithm.

关键词

Keywords

references

Yoon S M, Kuijper A. Human action recognition based on skeleton splitting[J]. Expert Systems With Applications,2013,40(17):6848-6855.[2] Liu W P, Jiang H B, Bai X, et al. Distance transform-based skeleton extraction and its applications in sensor networks[J]. IEEE Transactions On Parallel And Distributed Systems,2013,24(9):1763-1772.[3] 夏菁菁,高琳,范勇,等.基于骨架特征的人数统计[J].计算机应用,2014,34(2):585-588. Xia J J, G L, F X, et al. Peaple counting based on skeleton feature[J]. Journal of Computer Applications, 2014,34(2):585-588. (in Chinese)[4] 王卫星,田利平,王悦.基于改进的图论最小生成树及骨架距离直方图分割细胞图像[J].光学精密工程,2013,21(9):2464-2472. Wang W X, Tian L P, Wang Y. Segmentation of cell images based on improved graph MST and skeleton distance mapping[J]. Optics and Precision Engineering, 2013,21(9):2464-2472. (in Chinese)[5] 王平,张力,周长其.基于种子点的粘连巨噬细胞图像的分割方法[J].液晶与显示,2012,27(6):808-813. Wang P, Zhang L, Zhou C Q. Segmentation method to adhesion macrophage image based on seeding point[J]. Chinese Journal of Liquid Crystals and Displays,2012,27(6):808-813. (in Chinese)[6] Montero A S, Lang J. Skeleton pruning by contour approximation and the integer medial axis transform[J]. Computers & Graphics,2012,36(5):477-487.[7] Shen W, Bai X, Hu R, et al. Skeleton growing and pruning with bending potential ratio[J]. Pattern Recognition,2011,44(2):196-209.[8] 杨晨晖,刘聪.优化的梯度最短路径骨架提取算法[J].厦门大学学报(自然科学版),2014,53(2):201-205. Yang C H, Liu C. Skeleton extraction algorithm of optimized gradient path[J]. Journal of Xiamen University(Natural Science), 2014,53(2):201-205. (in Chinese)[9] 庄彩云,熊平.基于近似最小距离场的二维图像骨架提取方法[J].计算机工程与应用,2013,49(21):164-167. Zhuang C Y, Xiong P.2D image skeleton generation based on approximate minimum distance filed[J]. Computer Engineering and Applications,2013,49(21):164-167.(in Chinese)[10] 康文雄,邓飞其.利用模板和邻域信息的静脉骨架提取新算法[J].中国图象图形学报,2010,15(3):378-384. Kang W X, Deng F Q. A skeletonization method for vein patterns using template and neighbor information[J]. Journal of Image and Graphics,2010,15(3):378-384. (in Chinese)[11] 崔雪森,伍玉梅,戴阳,等.外部压力法(EPM)的二值图像骨架提取[J].计算机工程与应用,2013,49(13):138-141,227. Cui X S, Wu Y M, Dai Y, et al. Binary image skeleton extraction by External Pressure Method(EPM)[J]. Computer Engineering and Applications,2013,49(13):138-141,227. (in Chinese)[12] 颜廷秦,周昌雄,刘淑芬.一种距离场约束下的普适细化算法[J].南京大学学报(自然科学版),2013,49(2):189-195. Yan T Q, Zhou C X, Liu S F. A universal thinning algorithm restricted by distance[J]. Journal of Nanjing University(Natural Science),2013,49(2):189-195. (in Chinese)[13] 刘怡静,唐莉萍,曾培峰.基于向量内积的骨架提取算法[J].东华大学学报(自然科学版),2010,36(2):158-164. Liu Y J, Tang L P, Zeng P F. Skeleton extraction algorithm based on vector inner-product[J]. Journal of Donghua University(Natural Science),2010,36(2):158-164. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据