结 论
本文采用超像素作为图像目标识别的基本单元,在目标多样!背景复杂的图像中,通过对图像中每个超像素类别标签的判定,定位所要找的特定类别目标的位置,并将其与背景分割开来,最终得到目标的分割图像\
利用超像素颜色均值图对超像素邻域合并进行修正,从而使边界处的超像素尽可能与同类超像素合并,使识别结果的到较为清晰的目标边缘,最后,本文利用基于超像素的Graphcuts图论模型对目标识别结果进行分割,以超像素分类的置信值结果为数据项,以相邻超像素之间的颜色相似性和公共边界的长度为平滑项,建立GraphCuts能量函数\最小化该能量函数,从而得到本文目标识别结果的分割图,我们在具有较大挑战性的Graz一02数据集上验证了本文的算法,得到了较好的识别,率和边界较为清晰的目标识别结果分割图\通过这些工作,我们发现,在计算机实现全自动化的图像目标识别的过程中.基于局部学习的超像素级图像目标识别特征,如颜色特征,纹理特征等,来增强超像素的表现力和判别力,以提高超像素分类的准确性
超像素级的图像目标识别是一种基于部分的图像内容识别方法,以后的工作中,我们可以引入目标类型的整体模型与我们的方法相结合,使目标的部分模型与整体模型相互促进,增强图像目标识别的效果。
26
致 谢
在我的论文完成之际，首先我要感谢张太发老师，是他为我创造了良好学习的机会和环境，并给了我悉心指导和孜孜不倦的教诲，使我能在工作和学习上克服困难，取得进步。
在此要感谢我生活学习了四年的母校,母校给了我一个宽阔的学习平台,让我不断吸取新知,充实自己。需要特别感谢的是我的父母。父母的养育之恩无以为报,他们是我十多年求学路上的坚强后盾,在我面临人生选择的迷茫之际,为我排忧解难,他们对我无私的爱与照顾是我不断前进的动力。 再次感谢所有关心帮助我的亲人、老师和朋友,祝福你们!
27
参考文献
[1]王猛，李玉良，王庆飞图像处理在矿井瓦斯监控中的应用研究[J].工矿自动化，1671 -251X(2011)07 -0061 -04 .
[2]田丽军.煤矿监控中火灾图像分割方法研究[J].煤炭技术，1008-8725（2011）07-0083-03. [3]李忠杰，胡文涛，胡宁.图像分割技术在煤矿生产中的应用[J].价值工程，1006-4311（2012）11-0151-02.
[4]于淼，戚正伟．NewBluePill 深入理解硬件虚拟机[M]京: 清华 大学出版社，2011:55． [5]王春瑶，陈俊，李炜 超像素分割算法研究综述 计算机应用研究[J] 01-3695(2014) 01-0006-07 .
[6] LiuGC,Lin Z C,Yan S C,etal.Robust Recovery of Subspace Structures by Low-rank Representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013, 35(1):171-184.
[7]ACHANTA R，SHAJI A，SMITH K,t al.LIC superpixels compared to state-of-the-art superpixel methods［J］.IEEE Trans on Pattern Analysis and Machine Intelligence，2012，34 (11) :2274-2282．
[8]LEVINSHTEIN A，SMINCHISESCH C，DICKINSON S.Multiscale symmetric part detection and grouping ［J］.International Journal of Computer Vision，2013,104(2) :117-134． [9]LUCCHI A，SMITH K，ACHANTA R,etal.Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features［J］.IEEE Trans on Medical Imaging，2012，31(2) : 474-486．
[10]WANG Shu，LU Hu-chuan，YANG Fan,et al.Superpixel tracking［C］Proc of IEEE International Conference on Computer Vision.2011:1323-1330．
[11]ZHOU Xue，LI Xi，CHIN T J，etal .uperpixel-driven level set tracking［C］Proc of the 19th IEEE International Conference on Image Processing.2012:409-412．
[12]LIU Li-wei，XING Jun-liang，AI Hai-zhou，etal．Semantic super- pixel based vehicle tracking［C］Proc of the 21st International Conference on Pattern Recognition.Berlin: Springer-Verlag，2012: 2222-2225．
[13]WANG Wei-jun，NEVATIA R.Robust object tracking using constel- lation model with superpixel［C］Proc of the 11th Asian Conference on Computer Vision.erlin: Springer-Verlag， 2012:191-204．
[14]MAJI S，VISHNOI N K，MALIK J.iased normalized cuts［C］Proc of IEEE Conference on
28
Computer Vision and Pattern Recognition，Washington DC: IEEE Computer Society,2011:2057-2064．
[15]GU Guang-hua，LI Fengcai，ZHAO Y，etal．Scene classification based on spatial pyramid representation by superpixel lattices and contextual visual features［J］.Optical Engineering，2012，51(1) :017201-1-017201-8．
[16] X.Yang, G.Zhang, J.Lu, J.Ma. A kernel fuzzy c-means clustering-based fuzzy support vector machine algorithm for classification problems with outliers or noises. 2011, 19(1): 105-115. [17] X.Zhou, D.Chen, S.Yuan. Medical brain MRI images segmentation by improved fuzzy c-means clustering analysis. Journal of Jilin University (Engineering and Technology Edition). 2009, 2(39): 381-385.
[18] I.Despotovic, E.Vansteenkiste, W.Philips. Spatially coherent fuzzy clustering for accurate and noise-robust image segmentation. IEEE Signal Processing Letters. 2013, 20(4): 295-298. [19] A.Joulin, F.Bach, J.Ponce. Discriminative clustering for image co-segmentation. IEEE Conference on Computer Vision and Pattern Recognition. 2010, 1943-1950.
[20] P.Mehrani, O.Veksler. Saliency segmentation based on learning and graph cut renement. British Machine Vision Conference. 2010.
[21]Gan L,Wu Y,Liu M,et al. Triplet Markov fields with edge location for fastunsupervised multiclass segmentation of synthetic aperture radar images [J], IET Image Processing, 6(7): 831-838,2012.
[22] Zhang L, Ji Q. Image Segmentation with a Unified Graphical Model[J], IEEE Transactions on Patten Analysis and Machine Intelligence, 32(8): 1406-1425,2010.
[23] Zhou X,Li X, Chin T J, et al. Superpixel-driven level set tracking[C]. IEEE International Conference on Image Processing, 2012: 409-412, 2012.
[24] Gong X, Liu J. Rock detection via superpixel graph cuts[C]. IEEE International Conf. on Image Processing, 2012: 2149-2152,2012.
[25] Jiang H. Linear Solution to Scale Invariant Global Figure Ground Separation[C].IEEE Conference on Computer Vision and Pattern Recognition, 2012: 678-685,2012.
[26] Li Z, Wu X M, Chang S F. Segmentation Using Superpixels: A Bipartite Graph Partitioning Approach[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2012: 789-796,2012.
[27] Achanta R,Shaji A,Smith K,et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11): 2274-2281,2012.
29
[28] Van den Bergh M,Boix X, Roig Q etal. SEEDS: Superpixels Extracted via Energy-Driven Sampling[M]. In European Conference on Computer Vision, 2012:13-26, 2012.
[29] Liu M Y, Tuzel O, Ramalingam S,et al. Entropy Rate Superpixel Segmentation[C].IEEE Conference on Computer Vision and Pattern Recognition, 2011: 2097-2104,2011.
[30] Zhang Y,Hartley R,Mashford J,et al. Superpixels via Pseudo-Boolean Optimization[C]. IEEE International Conference on Computer Vision, 2011:'1387-1394,2011.
30