计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220600114-7.doi: 10.11896/jsjkx.220600114

• 图像处理&多媒体技术 • 上一篇    下一篇

基于球簇聚类的超像素分割迭代算法

刘垚, 官礼和   

  1. 重庆交通大学数学与统计学院 重庆 400074
  • 出版日期:2023-06-10 发布日期:2023-06-12
  • 通讯作者: 官礼和(guanlihe@cqjtu.edu.cn)
  • 作者简介:(474890301@qq.com)
  • 基金资助:
    国家自然科学基金(12271067);重庆市高校创新研究群体项目(CXQT21021);重庆市研究生联合培养基地建设项目(JDLHPYJD2021016)

Superpixel Segmentation Iterative Algorithm Based on Ball-k-means Clustering

LIU Yao, GUAN Lihe   

  1. School of Mathematics and Statistics,Chongqing Jiaotong University,Chongqing 400074,China
  • Online:2023-06-10 Published:2023-06-12
  • About author:LIU Yao,born in 1993,postgraduate.Her main research interests include image processing and so on. GUAN Lihe,born in 1975,Ph.D,asso-ciate professor,postgraduate supervisor.His main research interests include intelligent information processing and machine learning.
  • Supported by:
    National Natural Science Foundation of China(12271067),Chongqing University Innovation Research Group Project(CXQT21021) and Chongqing Postgraduate Joint Training Base Construction Project(JDLHPYJD2021016).

PDF (PC)

284

摘要： 针对超像素分割问题,为了进一步提高超像素边缘贴合度,提出了一种基于球簇聚类的超像素分割迭代算法。首先,将超像素视为五维超球体,对图像进行均匀分割得到初始超像素及其中心和半径;其次,依据邻接超像素中心间的距离及其半径搜索近邻超像素;然后,利用超像素与其近邻超像素中心间的距离,将超像素划分为稳定区和多个环形活跃区;最后,每个环形活跃区内的像素点仅根据其与部分近邻超像素中心的距离将其分入最近的超像素,如此迭代实现超像素分割。为了减少距离计算量以加快收敛速度,给出了近邻超像素关系判定定理,对像素点的超像素类标签设计了一种自适应分区更新策略。在BSD500数据集上与多种典型超像素分割算法进行了实验对比,结果表明该算法对不同类型图像的分割效果均较好,边缘贴合度更高,且受参数影响较小,分割结果更稳定。

关键词: 图像分割, 超像素, 聚类, 球簇

Abstract: Considering the problem of superpixel segmentation,this paper propose an iterative algorithm of superpixel segmentation based on Ball-k-means clustering to further improve the edge fit of superpixels.Firstly,the superpixels are regarded as five-dimensional hyperspheres,and the image is evenly segmented to obtain the initial superpixels.Secondly,the neighbor superpixels are searched according to the radius and distance between the centers of adjacent superpixels.Then,using the distances between the superpixels and their neighbor superpixel centers,the superpixels are divided into a stable region and multiple ring active regions.Finally,the pixels in each annular active area are divided into the nearest neighbor superpixel only according to their distance from the center of some neighbor superpixels,so as to realize the superpixel segmentation iteratively.In order to reduce the distance calculation and speed up the convergence,a judgment theorem of the relation between the nearest neighbor superpixels is given,and an adaptive partition updating strategy is designed for the superpixel class labels of pixels.Experimental comparison and analysis on BSD500 data set show that the proposed algorithm has better segmentation effect on different types of images,with higher edge fitting degree,less influence by parameters,and more stable segmentation results.

Key words: Image segmentation, Superpixel, Clustering, Ball cluster

中图分类号: 

  • TP391
[1]REN X F,MALIK J.Learning a classification model for segmentation[C]//Proceedings of the 9th IEEE International Conference on Computer Vision.Washington,2003:10-17.
[2]YANG F,LU H,YANG M H.Robust Superpixel Tracking[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2014,23(4):1639-1651.
[3]ZHOU X E,WANG Y N,ZHU Q,et al.SSG:superpixel segmentation and GrabCut-based salient object segmentation[J].The Visual Computer,2019,35(3):385-398.
[4]HE S,LAU R,LIU W,et al.SuperCNN:A Superpixel wiseConvolutional Neural Network for Salient Object Detection[J].International Journal of Computer Vision,2015,115(3):330-344.
[5]LI B,YANG Y,LIU Q.RGB-D video saliency detection via superpixel-level conditional radom field[J].Journal of Image and Graphics,2021,26(4):872-882.
[6]ZHANG Y M,SUN H Y,XU Y L.An improved hyperspectral image segmentation method based on superpixel[J].Remote Sensing for Natural Resources,2019,31(1):58-64.
[7]WANG Y,LIU C,TANG J G.Fuzzy-means clustering with aadaptive multiple features reduction for remote sensing image segmentation[J].Application Research of Computer,2022,39(3):906-910.
[8]CHEN B B,FAN J L,LEI B,et al.SLIC superpixel granulation-based rough entropy image segmentation algorithm[J].Transducer and Microsystem Technologies,2022,41(2):105-107.
[9]LUCCHI A,SMITH K,ACHANTA R,et al.Supervoxel-based Segmentation of Mitochondria in EM Image Stacks with Learned Shape Features[J].IEEE Transactions on Medical Imaging,2012,31(2):474-486.
[10]HU C Y,SI M M,CHEN W.Brain MRI Tumor Segmentation Method Based on Superpixel and Mean Shift[J].Journal of Chinese Computer Systems,2022,43(1):91-97.
[11]SHI J B,MALIK J.Normalized cuts and image segmentation[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[12]FELZENSEALB P F,HUTTENLOCHER D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.
[13]LIU M Y,TUZEL O,RAMALINGAM S,et al.Entropy rate superpixel segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.2011:2097-2104.
[14]LEVINSHTEIN A,STERE A,KUTULAKOS K N,et al.Turbopixels:Fast superpixels using geometric flows[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297.
[15]ACHANTA R,SHAJI A,SMITH K,et al.Slic superpixelscompared to state-of-art superpixel methods[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[16]LI Z,CHEN J.Superpixel segmentation using linear spectralclustering[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1356-1363.
[17]ZHANG Z L,LI A H,LI C W.Superpixel Segmentation Based on Clustering by Finding Density Peaks[J].Chinese Journal of Computers,2020,43(1):1-15.
[18]LEI T,LIAN Q,JIA X H.Fast Simple Linear Iterative Clustering for Image Superpixel Algorithm[J].Computer Science,2020,47(2):143-149.
[19]LOKE S C,MACDONALD B A,PARSONS M,et al.Accelerated superpixel image segmentation with a parallelized DBSCAN algorithm[J].Journal of Real-Time Image Processing,2021,18:2361-2376.
[20]WU J,LIU C X.Superpixel segmentation with texture aware-ness[J].Journal of Image and Graphics,2021,26(5):1006-1016.
[21]XIA S,PENG D,MENG D,et al.A Fast Adaptive k-means with No Bounds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,44(1):87-99.
[22]MARTIN D,FOWLKES C,TAL D,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecologicalstatistics[C]//IEEE International Conference on Computer Vision.IEEE,2002:1-8.
[23]STUTZ D,HERMANS A,LEIBE B.Superpixels:An evaluation of the state-of-the-art[J].Computer Vision and Image Understanding,2018,166(1):1-27.
[24]XIE X,XIE G,XU X,et al.Adaptive high-precision superpixel segmentation[J].Multimedia Tools and Applications,2019,78(9):12353-12371.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发