[1]薛 萍.基于超像素特征表示的图像前景背景分割算法[J].西安科技大学学报,2017,(05):731-735.[doi:10.13800/j.cnki.xakjdxxb.2017.0520]
 XUE Ping.Foreground and background segmentation based on superpiexel-level feature representation[J].Journal of Xi'an University of Science and Technology,2017,(05):731-735.[doi:10.13800/j.cnki.xakjdxxb.2017.0520]
点击复制

基于超像素特征表示的图像前景背景分割算法(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2017年05期
页码:
731-735
栏目:
出版日期:
2017-09-30

文章信息/Info

Title:
Foreground and background segmentation based on superpiexel-level feature representation
文章编号:
1672-9315(2017)05-0731-05
作者:
薛 萍
作者简介:薛 萍(1963-),女,山东青岛人,高级工程师,E-mail:xuep@xust.edu.cn
Author(s):
XUE Ping
College of Computer Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China
关键词:
图像分割算法 超像素提取 线性分类器 特征表示
Keywords:
Key words:image segmentation superpixel extraction linear classifier feature representation
分类号:
TN 911.73
DOI:
10.13800/j.cnki.xakjdxxb.2017.0520
文献标志码:
A
摘要:
图像前景背景分割是图像处理中的关键技术,文中提出了基于超像素分类的二值分割算法。对于输入图像,首先采用超像素分割算法,将图像分割成多个保留边缘的封闭区域,即超像素; 对每一块超像素,考虑颜色和纹理,构造一种对光照和颜色较为鲁棒的特征,来消除同种物体在光照和颜色差异下的影响; 用所得特征训练分类器,判断每块超像素属于前景或背景; 最后将超像素分类结果作为初值用图分割的方法进行修正,得到最终的二值分割结果。实验结果显示算法能较好的完成前景背景分割的任务。此外,本算法易于和现有的分类算法相结合,具有较强的可移植性。
Abstract:
Abstract:The foreground and background segmentation is an important technique in image processing.In this paper,a binary segmentation method is proposed based on the classification of superpixel.The input image is firstly divided into several superpixel to protect the edge of objects.For each superpixel,the color and texture are considered to extract the feature with robust for illumination and color,which can eliminate the influence of light and color.The feature vectors are further used to train a classification to classify the superpixel into foreground or background.Finally,the graph cut method is used to modify the class label of each pixel with the initialization of superpixel.The experiment result shows that the method can successfully extract the objects from the background.Moreover,this method is easy to be implemented since it can be combined with the classification technique directly.

参考文献/References:

[1] 朱远清,李才伟.一种基于前景与背景划分的区域图像检索方法及实现[J].中国图像图形学报,2007,12(2):234-238. ZHU Yuan-qing,LI Cai-wei.A method and implementation for region-based image retrieval using partition of foreground and background[J].Journal of Image and Graphics,2007,12(2):234-238.
[2] 牛 杰,卜雄洙,钱 堃.基于前景分割的目标实时监测方法[J].计算机应用,2014,34(5):1 463-1 466. NIU Jie,BU Xiong-zhu,QIAN Kun.Real-time object detection method based on foreground segmentation[J].Journal of Computer Application,2014,34(5):1 463-1 466.
[3] 戴雪峰,金连文,熊 波.基于图像前景分割的嵌入式智能监控系统[J].计算机工程,2007,33(20):233-235. DAI Xue-feng,JIN Lian-wen,XIONG Bo.Embedded intelligent surveillance systems based on foreground segmentation technology[J].Computer Engineering,2007,33(20):233-235.
[4] 刘 铭,刘雅楠,李靖宇.基于分割和全背景图像的视频修复算法[J].中国新通信,2015(7):117-118. LIU Ming,LIU Ya-nan,LI Jing-yu.Video completion based cut and background image[J].China New Telecommunications,2015(7):117-118.
[5] Liu G,Sun X,Fu K,et al.Aircraft recognition in high-resolution satellite images using coarse-to-fine shape prior[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):573-577.
[6] 楚 瀛,田 淞,张桂林,等.基于图像边缘特征的前景背景分割方法[J].华中科技大学学报,2008,36(5):20-23. CHU Ying,TIAN Song,ZHANG Gui-lin,et al.Video foreground and background segmentations based edge features[J].Journal of Huazhong University of Science and Technology,2008,36(5):20-23.
[7] 张巧荣,景 丽,肖会敏,等.利用视觉显著性的图像分割方法[J].中国图象图形学报,2011,16(5):767-772. ZHANG Qiao-rong,JING Li,XIAO Hui-min,et al.Image segmentation based on visual saliency[J].Journal of Image and Graphic,2011,16(5):767-772.
[8] 翟 玲,朱 敏,戴李君.基于超像素与特征改进的Grab cut前景分割[J].微型电脑应用,2015,31(11):48-50. ZHAI Ling,ZHU Min,DAI Li-jun.Foreground cut based on superpixel and feature-improved grab cut[J].Microcomputer Applications,2015,31(11):48-50.
[9] 陈鹏翔,杨晟院.区域拟合的背景去除图像分割模型[J].中国图像图形学报,2016,21(6):683-690. CHEN Peng-xiang,YANG Sheng-yuan.Fast image segmentation based on region-scalable fitting background removal model[J].Journal of Image and Graphics,2016,21(6):683-690.
[10]Cordes K,Scheuermann B,Rosenhahn B,et al.Foreground segmentation from occlusions using structure and motion recovery[C]//Computer Vision,Imaging and Computer Graphics.Theory and Application.Springer Berlin Heidelberg,2013:340-353.
[11]Achanta R,Shaji A,Smith K,et al.SLIC Superpixels[R].EPFL:Technical Report,2010.
[12]Ojala T,Pietik inen T,Harwood D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996(29):51-59.
[13]Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273.
[14]Boykov Y,Kolmogorov V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1 124-1 137.

备注/Memo

备注/Memo:
作者简介:薛 萍(1963-),女,山东青岛人,高级工程师,E-mail:xuep@xust.edu.cn
更新日期/Last Update: 2017-11-08