基于漫水填充的图像骨架提取方法

doi:10.16182/j.issn1004731x.joss.19-VR0443

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (8): 1455-1464.doi: 10.16182/j.issn1004731x.joss.19-VR0443

基于漫水填充的图像骨架提取方法

蔡兴泉, 杨哲, 蔡润博, 葛亚坤, 杨波

北方工业大学信息学院,北京 100144

收稿日期:2019-08-24 修回日期:2019-11-14 出版日期:2020-08-18 发布日期:2020-08-13
作者简介:蔡兴泉(1980-),男,山东,博士,教授,研究方向为虚拟现实、人机互动。
基金资助:
国家自然科学基金(61503005),北京市社会科学基金(19YTC043),北方工业大学毓优人才培养项目(NCUTYY19XN132)

Image Skeleton Extraction Method Based on Flood-Fill

Cai Xingquan, Yang Zhe, Cai Runbo, Ge Yakun, Yang Bo

School of Information Science and Technology, North China University of Technology, Beijing 100144, China

Received:2019-08-24 Revised:2019-11-14 Online:2020-08-18 Published:2020-08-13

摘要/Abstract

摘要： 针对当前图像骨架提取存在毛刺现象和骨架冗余的问题,提出基于漫水填充的图像骨架提取方法。对目标图像预处理,得到阈值化二值图像,分割出前景和背景;构建掩模图像和轴线图,为后续运算过程提供数据来源和判断依据;通过遍历水平面灰度直方图,模拟漫水过程,收缩掩膜图像的前景轮廓,根据邻域连通分量变化,确定是否为骨架特征点,待轮廓收缩完毕,得到图像骨架。实验验证表明,该方法可以有效地提取图像骨架,毛刺现象和冗余结构明显减少,执行速度快。

关键词: 骨架提取, 漫水填充, 掩膜图像, 轴线图, 水面交汇

Abstract: Aiming at the burr phenomenon and skeleton redundancy in current image skeleton extraction, a method based on flood-fill is proposed. The target image is pre-processed to obtain a threshold binary image and the foreground and background are segmented. A mask image and axis map are constructed to provide data sources and judgment basis for the subsequent calculation process. The diffusing water process is simulated by traversing the horizontal grayscale histogram. The foreground contour of the mask image is shrinked. According to the change of the connected components of the neighborhood, a skeleton feature point is determined . When the contour shrinking is finished, the image skeleton is obtained. The experimental results show that the method can effectively extract the image skeleton, the burr phenomenon and redundant structure are significantly reduced, and the execution speed is fast.

Key words: skeleton extraction, flood-fill, mask image, axes image, water surface confluence

中图分类号:

TP391.9

蔡兴泉, 杨哲, 蔡润博, 葛亚坤, 杨波. 基于漫水填充的图像骨架提取方法[J]. 系统仿真学报, 2020, 32(8): 1455-1464.

Cai Xingquan, Yang Zhe, Cai Runbo, Ge Yakun, Yang Bo. Image Skeleton Extraction Method Based on Flood-Fill[J]. Journal of System Simulation, 2020, 32(8): 1455-1464.

参考文献 25

[1]	韩国强, 田绪红, 李志垣, 等. 三维图像骨架化方法综述[J]. 小型微型计算机系统, 2007, 28(9): 1695-1699.Han Guoqiang, Tian Xuhong, Li Zhiyuan, et al.Survey of 3D Image Skeletonization[J]. Journal of Chinese Computer System, 2007, 28(9): 1695-1699.
[2]	李劝男. 灰度图像骨架的提取及在物体检测中的应用[D]. 武汉: 华中科技大学, 2009.Li Quannan, Skeleton Extraction of Gray-Sacle Images and Its Application in Object Detection[D]. Wuhan: Huazhong University of Science and Technology, 2009.
[3]	Dey T K, Zhao W.Approximating the Medial Axis from the Voronoi Diagram with a Convergence Guarantee[J]. Algorithmica (S0178-4617), 2004, 38(1): 179-200.
[4]	Blum H.Biological Shape and Visual Science (part I)[J]. Journal of Theoretical Biology (S0022-5193), 1973, 38(2): 205-287.
[5]	Sundar H, Silver D, Gagvani N, et al.IEEE Compute. Soc Shape Modeling International 2003-Seoul, South Korea (12-15 May 2003), 2003 Shape Modeling International. Skeleton based shape matching and retrieval[C]//Shape Modeling International. Seoul, South Korea, South Korea, IEEE, 2003: 130-139.
[6]	Cornea N D, Silver D, Yuan X, et al.Computing hierarchical curve-skeletons of 3D objects[J]. The Visual Computer (S0178-2789), 2005, 21(11): 945-955.
[7]	Zheng W, Li L, Zhang Z, et al.Relational Network for Skeleton-Based Action Recognition[C]. 2019 IEEE International Conference on Multimedia and Expo (ICME). Shanghai, China, IEEE, 2019: 826-831.
[8]	赵春江, 施文康, 邓勇. 具有鲁棒性的图像骨架提取方法[J]. 计算机应用, 2005, 25(6): 1305-1306.Zhao Chunjiang, Shi Wenkang, Deng Yong.New robust extraction method of image skeleton[J]. Computer Applications, 2005, 25(6): 1305-1306
[9]	Au O K C, Tai C L, Chu H K, et al. Skeleton extraction by mesh contraction[J]. ACM Transactions on Graphics (S0730-0301), 2008, 27(3): 1-10.
[10]	吕哲, 王福利, 常玉清, 等. 改进的形态学骨架提取算法[J]. 计算机工程, 2009, 35(19): 23-25.Lü Zhe, Wang Fuli, Chang Yuqing, et al.Improved Morphological Skeleton Extraction Algorithm[J]. Computer Engineering, 2009, 35(19): 23-25.
[11]	Coeurjolly D, Montanvert A.Optimal Separable Algorithms to Compute the Reverse Euclidean Distance Transformation and Discrete Medial Axis in Arbitrary Dimension[J]. IEEE Transactions on Pattern Analysis& Machine Intelligence (S0162-8828), 2007, 29(3): 437-448.
[12]	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.Cui Xuesen, Wu Yumei, Dai Yang, et al.Binary image skeleton extraction by External Pressure Method (EPM). Computer Engineering and Applications[J]. 2013, 49(13): 138-141.
[13]	Kazuhisa F.Extract an essential skeleton of a character as a graph from a character image[J]. International Journal of Computer Science (S2333-9721), 2015, 10(5): 35-39.
[14]	Marie R, Labbani-Igbida O, Mouaddib E M.The Delta Medial Axis A fast and robust algorithm for filtered skeleton extraction[J]. Pattern Recognition (S0031-3203), 2016: 5626-5639.
[15]	Cai Y X, Ming C G, Qin Y T.Skeleton extraction based on the topology and Snakes model[J]. Results in Physics (S2211-3797), 2017, 7: 373-378.
[16]	Gao F Y, Wei G S, Xin S Q, et al.2D Skeleton Extraction Based on Heat Equation[J]. Computers & Graphics (S0097-8493), 2018, 74: 99-108.
[17]	Liu X L, Lyu P Y, Bai X, et al.Fusing Image and Segmentation Cues for Skeleton Extraction in the Wild[C]//ICCV 2017 Workshop A Challenge: Detecting Symmetry in the Wild. Venice, Italy IEEE, 2017.
[18]	Shen W, Zhao K, Jiang Y, et al.Object skeleton extraction in natural images by fusing scale-associated deep side outputs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 222-230.
[19]	Gao L M, Zhang D, Li N, et al.Force field driven skeleton extraction method for point cloud trees[J]. Earth Science Informatics (S1865-0481), 2018(1): 161-171.
[20]	He G Z, Yang J, Sevev B.Research on geometric features and point cloud properties for tree skeleton extraction[J]. Personal & Ubiquitous Computing (S1617-4917), 2018, 22(5/6): 903-910.
[21]	刁智华, 吴贝贝, 毋媛媛, 等. 基于图像处理的骨架提取算法的应用研究[J]. 计算机科学, 2016, 43(增1): 232-235.Diao Zhihua, Wu Beibei, Wu Yuanyuan, et al.Application Research of Skeleton Extraction Algorithm Based on Image Processing[J]. Computer Science, 2016, 43(S1): 232-235.
[22]	唐超, 张苗辉, 李伟, 等. 基于深度图像的人体行为识别[J]. 系统仿真学报, 2018, 30(5): 1641-1649.Tang Chao, Zhang Maohui, Li Wei, et al.Human behavior recognition based on depth image[J]. Journal of System Simulation, 2018, 30(5): 1641-1649.
[23]	李乾, 高尚兵, 潘志庚, 等. 基于无标记识别的增强现实方法研究[J]. 系统仿真学报, 2018, 30(7): 2608-2614.Li Qian, Gao Shangbing, Pan Zhigeng, et al.Augmented reality method based on markless recognition[J]. Journal of System Simulation, 2018, 30(7): 2608-2614.
[24]	蔡兴泉, 杨哲, 何鑫, 等. 结合伺服电机的古建筑物增强现实交互展示系统[J/OL]. 系统仿真学报: 1-9 [2020-06-09].http://kns.cnki.net/kcms/detail/11.3092.V.20190111.0919.016.html..Cai Xingquan, Yang Ze, He Xin, et al. Interactive Media System for Ancient Buildings Combined with Servom otor[J/OL]. Journal of System Simulation: 1-9 [2020-06-09].http://kns.cnki.net/kcms/detail/11.3092.V.20190111.0919.016.html.
[25]	宋丽君, 李喆, 付强文, 等. 基于格网框架的极区SINS/GPS组合导航算法研究[J]. 系统仿真学报, 2019, 31(8): 1683-1691.Song Lijun, Li Zhe, Fu Qiangwen, et al.Research on SINS/GPS Integrated Navigation Algorithm Based on Grid Frame in Polar Region[J]. Journal of System Simulation, 2019, 31(8): 1683-1691.

基于漫水填充的图像骨架提取方法

Image Skeleton Extraction Method Based on Flood-Fill

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 25

相关文章 1

编辑推荐

Metrics

本文评价