融合纹理信息的SLIC算法在医学图像中的研究

侯向丹; 李柏岑; 刘洪普; 杜佳卓; 郑梦敬; 于铁忠

doi:10.16383/j.aas.c180682

融合纹理信息的SLIC算法在医学图像中的研究

doi: 10.16383/j.aas.c180682

侯向丹^1,2,,
李柏岑^1,2,,
刘洪普^1,2,3, ,,
杜佳卓^1,2,,
郑梦敬^1,2,,
于铁忠^1,

1.
河北工业大学人工智能与数据科学学院天津 300401
2.
河北省大数据计算重点实验室天津 300401
3.
河北工业大学电气工程学院天津 300401

基金项目:

天津市自然科学基金 16JCYBJC15600

详细信息

作者简介:
侯向丹  河北工业大学人工智能与数据科学学院副教授.2007年获得河北工业大学电工理论与新技术专业博士学位.主要研究方向为数字图像处理, 智能算法.E-mail:hxd@scse.hebut.edu.cn

李柏岑  河北工业大学人工智能与数据科学学院硕士研究生.2015年获得黑龙江大学信息系统与信息管理专业学士学位.主要研究方向为数字图像处理.E-mail:zeroformove@gmail.com

杜佳卓  河北工业大学人工智能与数据科学学院硕士研究生.2017年获得唐山学院物联网工程专业学士学位.主要研究方向为数字图像处理.E-mail:zezzdjz0601@163.com

郑梦敬  河北工业大学人工智能与数据科学学院硕士研究生.2016年获得河北大学工商学院计算机科学与技术专业学士学位, 主要研究方向为数字图像处理.E-mail:zhengmengjing@cslc.com.cn

于铁忠  河北工业大学人工智能与数据科学学院正高级工程师.1991年获得国防科技大学硕士学位.主要研究方向为智能信息处理.E-mail:yutiezhong139@163.com

通讯作者:
刘洪普河北工业大学人工智能与数据科学学院讲师.2006年获得河北工业大学计算机应用技术专业硕士学位.主要研究方向为数字图像处理, 智能算法, 机器学习.本文通信作者.E-mail:liuii@scse.hebut.edu.cn

计量
- 文章访问数: 2121
- HTML全文浏览量: 413
- PDF下载量: 417
- 被引次数: 0
出版历程
- 收稿日期: 2018-10-19
- 录用日期: 2019-02-13
- 刊出日期: 2019-05-20

SLICT: Computing Texture-Sensitive Superpixels in Medical Images

HOU Xiang-Dan^{1,2
,},
LI Bo-Cen^{1,2
,},
LIU Hong-Pu^{1,2,3
, ,},
DU Jia-Zhuo^{1,2
,},
ZHENG Meng-Jing^{1,2
,},
YU Tie-Zhong^1
,

1.
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401
2.
Hebei Provincial Key Laboratory of Big Data Computing, Tianjin 300401
3.
School of Electrical Engineering, Hebei University of Technology, Tianjin 300401

Funds:

Natural Science Fundation of Tianjin 16JCYBJC15600

More Information

Author Bio:
Associate professor at the School of Artificial Intelligence, Hebei University of Technology. She received her Ph. D. degree in theory and new technology of electrical engineering from Hebei University of Technology in 2007. Her research interest covers digital image processing and intelligent algorithm

Master student at the School of Artificial Intelligence, Hebei University of Technology. He received his bachelor degree in information systems and information management from Heilongjiang University in 2015. His main research interest is digital image processing

Master student at the School of Artificial Intelligence, Hebei University of Technology. He received his bachelor degree in internet of things from Tangshan College in 2017. His main research interest is digital image processing

Master student at the School of Artificial Intelligence, Hebei University of Technology. She received her bachelor degree in computer science and technology from Industrial and Commercial College of Hebei University in 2016. Her main research interest is digital image processing

Professor of Engineering at the School of Artificial Intelligence, Hebei University of Technology. He received his master degree from National University of Defense Technology in 1991. His main research interest is intelligent information processing

Corresponding author: LIU Hong-Pu Lecturer at the School of Artificial Intelligence, Hebei University of Technology. He received his master degree in computer application technology from Hebei University of Technology in 2006. His research interests cover digital image processing, intelligent algorithm, and machine learning. Corresponding author of this paper

摘要

摘要: 随着超像素算法的发展，SLIC（Simple linear iterative clustering）由于时间复杂度低及良好的分割结果而被广泛关注.但是由于传统的SLIC算法并没有考虑到图像的纹理信息，故而对于纹理较复杂的图像分割效果略有不足.LBP（Local binary pattern）对于纹理的识别有着优秀的表现而且时间复杂度低，但是对于噪声的鲁棒性较差，并且会产生纹理偏移.因此，本文首先针对传统的LBP中存在的问题进行改进；然后将改进后的算法与SLIC结合，提出一种融合纹理信息的超像素算法——SLICT（Simple linear iterative clustering based on texture）.为验证分割效果，本文选取纹理较多的医学图像进行实验，采用心脏MRI数据库进行验证并与其他超像素算法进行对比.实验表明，SLICT在边缘召回率、欠分割错误率以及覆盖率上的综合表现优于其他算法.从分割结果上来看，SLICT不但能够更好地贴合图像边缘，而且对于连续区域的分割效果也较好，更适合纹理较复杂的图像.
- 纹理偏移 /
- SLIC /
- LBP /
- 医学图像 /
- 超像素
Abstract: With the development of superpixel algorithm, SLIC (Simple linear iterative clustering) is widely noticed because of its low time-complexity and remarkable results. However, traditional SLIC does not take texture information into consideration, which leads to unsatisfactory results on texture-complex images. LBP (Local binary pattern) algorithm has good performance on texture analysis. But it is not robust enough to texture noise, and it may also lead to texture deviation. So, we propose simple linear iterative clustering based on texture (SLICT) by improving the traditional LBP algorithm and combining it with SLIC. To verify our method's effectiveness, we use medical images which contain complex texture from cardiac MRI dataset and compare our algorithm with other superpixel algorithms. The experiment results show that SLICT has better performance than the other algorithms in boundary recall, under-segmentation error and coverage rate. Besides, image segmentation results show that SLICT can adhere to boundary more tightly and have better results on consistent area, which proves SLICT is more suitable to texture-complex images.
- Texture deviation /
- simple linear iterative clustering (SLIC) /
- local binary pattern (LBP) /
- medical images /
- superpixel
注释:

1) 本文责任编委刘成林

HTML全文

图 1 LBP算法中有无纹理偏移的效果对比

Fig. 1 The results of LBP algorithm with and without texture deviation

下载: 全尺寸图片幻灯片

图 2 心脏MRI分割结果

Fig. 2 The results of superpixel algorithms on MRI images

下载: 全尺寸图片幻灯片

图 3 心脏MRI数据库运行结果

Fig. 3 Expriment data on MRI dataset

下载: 全尺寸图片幻灯片

图 4 纹理特征图

Fig. 4 Texutre feature

下载: 全尺寸图片幻灯片

参考文献(38)

[1]	Stutz D, Hermans A, Leibe B. Superpixels:an evaluation of the state-of-the-art. Computer Vision amd Image Understanding, 2018, 166(1):1-27 http://d.old.wanfangdata.com.cn/Periodical/gxdxxb201302020
[2]	产思贤, 周小龙, 张卓, 陈胜勇.一种基于超像素的肿瘤自动攻击交互式分割算法.自动化学报, 2017, 43(10):1829-1840 http://www.aas.net.cn/CN/abstract/abstract19158.shtml Chan Si-Xian, Zhou Xiao-Long, Zhang Zhuo, Chen Sheng-Yong. Interactive multi-label image segmentation with multi-layer tumors automat. Acta Automatica Sinica, 2017, 43(10):1829-1840 http://www.aas.net.cn/CN/abstract/abstract19158.shtml
[3]	汪云飞, 冯国强, 刘华伟, 赵搏欣.基于超像素的均值——均方差暗通道单幅图像去雾方法.自动化学报, 2018, 44(3):481-489 http://www.aas.net.cn/CN/abstract/abstract19241.shtml Wang Yun-Fei, Feng Guo-Qiang, Liu Hua-Wei, Zhao Bo-Xin. Superpixel-based mean and mean square deviation dark channel for single image fog removal. Acta Automatica Sinica, 2018, 44(3):481-489 http://www.aas.net.cn/CN/abstract/abstract19241.shtml
[4]	林华锋, 李静, 刘国栋, 梁大川, 李东民.基于自适应背景模板与空间先验的显著性物体检测方法.自动化学报, 2017, 43(10):1736-1748 http://www.aas.net.cn/CN/abstract/abstract19151.shtml Lin Hua-Feng, Li Jing, Liu Guo-Dong, Liang Da-Chuan, Li Dong-Min. Saliency detection method using adaptive background template and spatial prior. Acta Automatica Sinica, 2017, 43(10):1736-1748 http://www.aas.net.cn/CN/abstract/abstract19151.shtml
[5]	Yang F, Lu H, Yang M H. Robust superpixel tracking. IEEE Transactions on Image Processing, 2014, 23(4):1639-1651 doi: 10.1109/TIP.2014.2300823
[6]	刘大千, 刘万军, 费博雯, 曲海成.前景约束下的抗干扰匹配目标跟踪方法.自动化学报, 2018, 44(6):1138-1152 http://www.aas.net.cn/CN/abstract/abstract19303.shtml Liu Da-Qian, Liu Wan-Jun, Fei Bo-Wen, Qu Hai-Cheng. A new method of anti-interference matching under foreground constraint for target tracking. Acta Automatica Sinica, 2018, 44(6):1138-1152 http://www.aas.net.cn/CN/abstract/abstract19303.shtml
[7]	Wang Z L, Feng J S, Yan S C, Xi H S. Image classification via object-aware holistic superpixel selection. IEEE Transactions on Image Processing, 2013, 22(11):4341-4352. doi: 10.1109/TIP.2013.2272514
[8]	Bodis-Szomoru A, Riemenschneider H, Gool L V. Superpixel meshes for fast edge-preserving surface reconstruction. In: Proceedings of the 2015 Computer Vision and Pattern Recognition. Boston, USA: IEEE, 2015. 2011-2020 https://ieeexplore.ieee.org/document/7298812/?reload=true&arnumber=7298812
[9]	Geiger A, Wang C. Joint 3D object and layout inference from a single RGB-D image. In: Proceedings of the 2015 German Conference on Pattern Recognition. Aachen, Germany: Springer, 2015. 183-195 http://www.mendeley.com/research/joint-3d-object-layout-inference-single-rgbd-image/
[10]	Gadde R, Jampani V, Kiefel M, Kappler D, Gehler P V. Superpixel convolutional networks using bilateral inceptions. In: Proceedings of the 2016 European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016. 597-613 doi: 10.1007/978-3-319-46448-0_36.pdf
[11]	Shi J, Malik J. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):888-905 doi: 10.1109/34.868688
[12]	Moore A P, Prince S J D, Warrell J, Mohammed U, Jones G. Superpixel lattices. In: Proceedings of the 2008 Computer Vision and Pattern Recognition. Anchorage, USA: IEEE, 2008. 1-8 http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=4587471
[13]	Veksler O, Boykov Y, Mehrani P. Superpixels and supervoxels in an energy optimization framework. In: Proceedings of the 2010 European Conference on Computer Vision. Heraklion, Greece: Springer, 2010. 211-224 http://www.springerlink.com/content/cx875711vq5p7234
[14]	Liu M Y, Tuzel O, Ramalingam S, Chellappa R. Entropy rate superpixel segmentation. In: Proceedings of the 2011 Computer Vision and Pattern Recognition. Colorado Springs, USA: IEEE, 2011. 2097-2104
[15]	Bergh M V D, Boix X, Roig G, Capitani B D, Gool L V. SEEDS: superpixels extracted via energy-driven sampling. In: Proceedings of the 2012 European Conference on Computer Vision. Florence, Italy: Springer, 2012. 13-26
[16]	Shen J B, Du Y F, Wang W G, Li X L. Lazy random walks for superpixel segmentation. IEEE Transactions on Image Processing, 2014, 23(4):1451-1462 doi: 10.1109/TIP.2014.2302892
[17]	Yin S, Qian Y, Gong M. Unsupervised hierarchical image segmentation through fuzzy entropy maximization. Pattern Recognition, 2017, 68(1):245-259 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3035ea132e2e906d04bb353c5431a9ef
[18]	Yin S, Zhao X, Wang W, Gong M. Efficient multilevel image segmentation through fuzzy entropy maximization and graph cut optimization. Pattern Recognition, 2014, 47(9):2894-2907 doi: 10.1016/j.patcog.2014.03.009
[19]	Wei X, Yang Q, Gong Y, Ahuja N, Yang M H. Superpixel hierarchy. IEEE Transactions on Image Processing, 2018, 27(10):4838-4849 doi: 10.1109/TIP.2018.2836300
[20]	Levinshtein A, Stere A, Kutulakos K N, Fleet D J, Dickinson S J, Siddiqi K. TurboPixels:fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12):2290-2297 doi: 10.1109/TPAMI.2009.96
[21]	Wang J, Wang X. VCells:simple and efficient superpixels using edge-weighted centroidal voronoi tessellations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(6):1241-1247 doi: 10.1109/TPAMI.2012.47
[22]	Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 31(11):2274-2282 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=218e2dd693ea07f7be3f296ed4e6aaba
[23]	Achanta R, Susstrunk S. Superpixels and polygons using simple non-iterative clustering. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 4895-4904 http://ieeexplore.ieee.org/document/8100003/
[24]	Shen J B, Hao X P, Liang Z Y, Liu Y, Wang W G, Shao L. Real-time superpixel segmentation by DBSCAN clustering algorithm. IEEE Transactions on Image Processing, 2016, 25(12):5933-5942 doi: 10.1109/TIP.2016.2616302
[25]	Chen J, Li Z, Bo H. Linear spectral clustering superpixel. IEEE Transactions on Image Processing, 2017, 26(7):3317-3330 doi: 10.1109/TIP.2017.2651389
[26]	Hu Z, Qin Z, Li Q. Watershed superpixel. In: Proceedings of the 2015 IEEE International Conference on Image Processing. Quebec City, Canada, 2015. 349-353
[27]	Boemer F, Ratner E, Lendasse A. Parameter-free image segmentation with SLIC. Neurocomputing, 2018, 277(1):228-236 http://www.sciencedirect.com/science/article/pii/S0925231217313978
[28]	张亚亚, 刘小伟, 刘福太, 张建廷.基于改进SLIC方法的彩色图像分割.计算机工程, 2015, 41(4):205-209 http://d.old.wanfangdata.com.cn/Periodical/jsjgc201504039 Zhang Ya-Ya, Liu Xiao-Wei, Liu Fu-Tai, Zhang Jian-Ting. Color image segmentation based on improved SLIC method. Computer Engineering, 2015, 41(4):205-209 http://d.old.wanfangdata.com.cn/Periodical/jsjgc201504039
[29]	Liu Y J, Yu C C, Yu M J, He Y. Manifold SLIC: a fast method to compute content-sensitive superpixels. In: Proceedings of the 2016 Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016. 651-659 http://ieeexplore.ieee.org/document/7780446/
[30]	Liu Y J, Yu M, Li B J, He Y. Intrinsic manifold SLIC:a simple and efficient method for computing content-sensitive superpixels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3):653-666 doi: 10.1109/TPAMI.2017.2686857
[31]	南柄飞, 穆志纯.基于SLIC0融合纹理信息的超像素分割方法.仪器仪表学报, 2014, 35(3):527-534 http://d.old.wanfangdata.com.cn/Periodical/yqyb201403006 Nan Bing-Fei, Mu Zhi-Chun. SLIC0-based superpixel segmentation method with texture fusion. Chinese Journal of Scientific Instrument, 2014, 35(3):527-534 http://d.old.wanfangdata.com.cn/Periodical/yqyb201403006
[32]	Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 24(7):971-987 doi: 10.1007%2F3-540-45054-8_27
[33]	Hafiane A, Seetharaman G, Palaniappan K, Zavidovique B. Rotationally invariant hashing of median binary patterns for texture classification. In: Proceedings of the 2008 International Conference Image Analysis and Recognition. Póvoa de Varzim, Portugal: Springer, 2008. 619-629 doi: 10.1007%2F978-3-540-69812-8_61
[34]	Guo Z, Zhang L, Zhang D. Rotation invariant texture classification using LBP variance (LBPV) with global matching. Pattern Recognition, 2010, 43(3):706-719 doi: 10.1016/j.patcog.2009.08.017
[35]	Andreopoulos A, Tsotsos J K. Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Medical Image Analysis, 2008, 12(3):335-357 doi: 10.1016/j.media.2007.12.003
[36]	Ojala T, Harwood I. A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 1996, 29(1):51-59 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d0f64e305eee42b19af98e65e3d28e3c
[37]	Ojala T, Maenpaa T, Pietikainen M, et al. Outex——new framework for empirical evaluation of texture analysis algorithms. In: Proceedings of the 2002 Pattern Recognition. Quebec City, Canada: IEEE, 2002. 701-706 http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=1044854
[38]	Otsu N. A Thresholding selection method from gray-level histogram. IEEE Transactions on Systems Man and Cybernetics, 1979, 9(1):62-66 doi: 10.1109/TSMC.1979.4310076