结合CS-LBP纹理特征的快速图割算法

计算机科学 ›› 2013, Vol. 40 ›› Issue (5): 300-302.

结合CS-LBP纹理特征的快速图割算法

刘毅,黄兵,孙怀江,夏德深

南京理工大学计算机科学与技术学院南京210094;南京审计学院信息与科学学院南京210029;南京理工大学计算机科学与技术学院南京210094;南京理工大学计算机科学与技术学院南京210094

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受基金项目中国数字化虚拟人切片图像分割研究(60805003)资助

Fast Image Segmentation Algorithm Combining CS-LBP Texture Features

LIU Yi,HUANG Bing,SUN Huai-jiang and XIA De-shen

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 图割算法是目前最有效的交互式图像分割方法之一。针对当前景和背景颜色相似时容易发生分割错误并产生shrinking bias现象,以及基于像素的计算导致交互效率不高的问题,提出一种结合纹理特征的改进算法。该算法首先利用Mean Shift算法对图像进行预分割,构建区域邻接图,然后用累计直方图、CS-LBP纹理描述子对每个区域进行颜色和纹理特征的提取,通过在能量函数中引入纹理约束项以及局部自适应的正则化参数,有效改善了分割效果和shrinking bias现象。实验结果表明,本算法交互效率得到了提高,分割结果更加精确。

关键词: 图割,GrabCut,均值漂移,累积直方图,中心对称局部二值模式

Abstract: Graph cuts algorithm is one of the most effective interactive image segmentation methods．But it is prone to produce segmentation errors and shrinking bias phenomena when the color of foreground and background is similar and its interaction efficiency is not high due to pixel-based calculation．To improve these problems,an algorithm combining CS-LBP texture features was proposed in this paper．First the mean shift algorithm is applied to pre-segment the original image into regions to construct region adjacency graph．Then cumulative histogram and CS-LBP texture descriptor are used to extract color and texture features form each region．A new term of texture constraint is added to the energy function and local adaptive regularization parameter is used．So the segmentation effect and shrinking bias phenomenon are improved efficiently．The experiments show that interactivity efficiency and segmentation accuracy are improved.

Key words: Graph cuts,GrabCut,Mean shift,Cumulative histogram,CS-LBP

刘毅,黄兵,孙怀江,夏德深. 结合CS-LBP纹理特征的快速图割算法[J]. 计算机科学, 2013, 40(5): 300-302. https://doi.org/

LIU Yi,HUANG Bing,SUN Huai-jiang and XIA De-shen. Fast Image Segmentation Algorithm Combining CS-LBP Texture Features[J]. Computer Science, 2013, 40(5): 300-302. https://doi.org/

参考文献

[1] Boykov Y,Jolly M P．Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]∥Preceedings of Computer Vision．2001(1):105-112
[2] Boykov Y,Funka-Lea G．Graph cuts and efficient N-D imagesegmentation[J]．International Journal of Computer Vision,2006,70(2):109-131
[3] Vicente S,Kolmogorov V,Rother C．Graph cut based image segmentation with connectivity priors [C]∥Preceedings of Computer Vision and Pattern Recognition．2008:1-8
[4] 韩守东,赵勇,陶文兵,等．基于高斯超像素的快速Graph Cuts图像分割方法[J].自动化学报,2011,37(1):11-20
[5] 刘技,康晓东,贾富仓．基于图割与均值漂移算法的脊椎骨自动分割[J].计算机应用,2011,1(3):760-762
[6] Peng Bo,Zhang Lei,Zhang D,et al.Image segmentation by itera-ted region merging with localized graph cuts[J]．Pattern Reco-gnition,2011,44(10/11):2527-2538
[7] 徐秋平,郭敏,王亚荣．基于分水岭变换和图割的彩色图像快速分割[J].计算机工程,2009,5(19):210-212
[8] Veksler O,Boykov Y,Mehrani P．Superpixels and Supervoxels in an Energy Optimization Framework[C]∥Preceedings of European Conference on Computer Vision(ECCV’10)．2010:211-224
[9] Heikki M,Pietikinen M,Schmid C．Description of Interest Re-gions with Center-Symmetric Local Binary Patterns [C]∥Preceedings of ICVGIP．2006:58-69
[10] Comaniciu D,Meer P．Mean Shift:A Robust Approach Toward Feature Space Analysis[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,4(5):603-619
[11] Stricker M A,Orengo M．Similarity of Color Images[C]∥Preceedings of Storage and Retrieval for Image and Video Databases(SPIE)．1995:381-392
[12] Ojala T,Pietikainen M,Harwood D．A comparative study of texture measures with classification based on feature distributions[J]．Pattern Recognition,1996,1(29):51-59
[13] Heikkila M,Pietikainen M．A texture based method for mode-ling the background and detecting moving objects[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):657-662
[14] Candemir S,Akgül Y S.Adaptive Regularization Parameter for Graph Cut Segmentation[C]∥Preceedings of ICIAR．2010(6111):117-126
[15] Rother C,Kolmogorov V,Blake A．Grabcut:Interactive fore-ground extraction using iterated graph cuts[J]．Preceedings of SIGGRAPH,2004,23(3):309-314

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed