Multi-objective Evolutionary Semi-supervised Fuzzy Clustering Image Segmentation Motivated by Region Information
-
摘要:
现有的多目标进化聚类算法应用于图像分割时,往往是在图像像素层面上进行聚类,运行时间过长,而且忽略了图像区域信息使得图像分割效果不太理想。为了提高多目标进化聚类算法的分割效果和时间效率,该文将图像区域信息与部分监督信息引入多目标进化聚类,提出图像区域信息驱动的多目标进化半监督模糊聚类图像分割算法。该算法首先利用超像素策略获得图像的区域信息,然后结合部分监督信息,设计融合区域信息和监督信息的适应度函数,接着通过多目标进化策略对多个适应度函数进行优化得到最优解集。最后构造融合区域信息与监督信息的最优解评价指标,实现从最优解集中选取一个最优解。实验结果表明:与已有多目标进化聚类算法相比,该算法不但分割效果有所提升,而且运行效率得以提高。
Abstract:When multi-objective evolutionary clustering algorithms are applied to image segmentation, the image pixels are always utilized to be clustered. It results in a long running time. In addition, due to not considering the image region information, the image segmentation effect is not ideal. In order to improve the segmentation effect and time efficiency of the multi-objective evolutionary clustering algorithm, the image region information and some supervised information are introduced into multi-objective evolutionary clustering. Then a multi-objective evolutionary semi-supervised fuzzy clustering image segmentation algorithm driven by image region information is presented. First, the region information of the image is obtained through the super-pixel strategy. Second, two novel fitness functions are designed by introducing the supervised information and region information. Third, the multi-objective evolutionary strategy is used to optimize these two fitness functions to obtain an optimal solution set. Finally, an optimal solution evaluation index with region information and supervision information is constructed and utilized to select an optimal solution from the optimal solution set. Experimental results show the proposed algorithm outperforms comparison methods in segmentation performance and running efficiency.
-
表 1 各算法聚类准确率对比
图像 FCM SSFCM SSFC-SC MOVGA 本文算法 #3096 0.9859 0.9860 0.9865 0.5388 0.9931 #135069 0.7368 0.9926 0.9924 0.3301 0.9925 #118035 0.9342 0.9342 0.9337 0.9367 0.9523 #124084 0.7415 0.7418 0.8465 0.8678 0.9457 #86016 0.8394 0.8395 0.8568 0.6190 0.9811 #161062 0.8846 0.8847 0.8988 0.5711 0.9830 #260058 0.7893 0.7898 0.8301 0.3730 0.9904 #8068 0.9517 0.9518 0.9518 0.7112 0.9858 #113044 0.8381 0.8384 0.8395 0.2664 0.9330 #12003 0.7737 0.7735 0.8079 0.4421 0.8919 #296059 0.7397 0.7396 0.7400 0.6364 0.9284 #238011 0.8093 0.9565 0.9565 0.9566 0.9605 #101027 0.8839 0.8840 0.8850 0.5689 0.9024 #28075 0.4479 0.4456 0.5666 0.5873 0.9374 #24063 0.9675 0.9675 0.9696 0.9601 0.9737 #253036 0.6193 0.6195 0.6921 0.6443 0.9448 #42044 0.7524 0.7526 0.7572 0.7055 0.8595 #299091 0.6962 0.6964 0.7220 0.3360 0.9564 #113016 0.8164 0.8142 0.8843 0.7203 0.9426 #147091 0.9316 0.9317 0.9314 0.7781 0.9041 -
章毓晋. 图象分割[M]. 北京: 科学出版社, 2001: 1–5.ZHANG Yujin. Image Segmentation[M]. Beijing: Science Press, 2001: 1–5. 申铉京, 刘翔, 陈海鹏. 基于多阈值Otsu准则的阈值分割快速计算[J]. 电子与信息学报, 2017, 39(1): 144–149. doi: 10.11999/JEIT160248SHEN Xuanjing, LIU Xiang, and CHEN Haipeng. Fast computation of threshold based on multi-threshold Otsu criterion[J]. Journal of Electronics &Information Technology, 2017, 39(1): 144–149. doi: 10.11999/JEIT160248 ZANG Wenke, ZHANG Weining, ZHANG Wenqian, et al. A kernel-based intuitionistic fuzzy c-means clustering using a DNA genetic algorithm for magnetic resonance image segmentation[J]. Entropy, 2017, 19(11): 578. doi: 10.3390/e19110578 ZHANG Yingchun, GUO He, CHEN Feng, et al. Weighted kernel mapping model with spring simulation based watershed transformation for level set image segmentation[J]. Neurocomputing, 2017, 249: 1–18. doi: 10.1016/j.neucom.2017.01.044 BEZDEK J C, EHRLICH R, and FULL W. FCM: the fuzzy c-means clustering algorithm[J]. Computers & Geosciences, 1984, 10(2/3): 191–203. CHEN Shengguo, SUN Zhengxing, ZHOU Jie, et al. Semi-supervised image segmentation combining SSFCM and random walks[C]. Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems, Hangzhou, China, 2012: 185–190. MENG Meng, WEI Jia, WANG Jiabing, et al. Adaptive semi-supervised dimensionality reduction based on pairwise constraints weighting and graph optimizing[J]. International Journal of Machine Learning and Cybernetics, 2017, 8(3): 793–805. doi: 10.1007/s13042-015-0380-3 JOHNSON D M, XIONG Caiming, and CORSO J J. Semi-supervised nonlinear distance metric learning via forests of max-margin cluster hierarchies[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(4): 1035–1046. doi: 10.1109/TKDE.2015.2507130 YASUNORI E, YUKIHIRO H, MAKITO Y, et al. On semi-supervised fuzzy c-means clustering[C]. Proceedings of IEEE International Conference on Fuzzy Systems, Jeju Island, South Korea, 2009: 1119–1124. YIN Xuesong, SHU Ting, and HUANG Qi. Semi-supervised fuzzy clustering with metric learning and entropy regularization[J]. Knowledge-Based Systems, 2012, 35: 304–311. doi: 10.1016/j.knosys.2012.05.016 SON L H and TUAN T M. A cooperative semi-supervised fuzzy clustering framework for dental X-ray image segmentation[J]. Expert Systems with Applications, 2016, 46: 380–393. doi: 10.1016/j.eswa.2015.11.001 SON L H and TUAN T M. Dental segmentation from X-ray images using semi-supervised fuzzy clustering with spatial constraints[J]. Engineering Applications of Artificial Intelligence, 2017, 59: 186–195. doi: 10.1016/j.engappai.2017.01.003 赵凤, 刘汉强, 范九伦. 基于互补空间信息的多目标进化聚类图像分割[J]. 电子与信息学报, 2015, 37(3): 672–678. doi: 10.11999/JEIT140371ZHAO Feng, LIU Hanqiang, and FAN Jiulun. Multi-objective evolutionary clustering with complementary spatial information for image segmentation[J]. Journal of Electronics &Information Technology, 2015, 37(3): 672–678. doi: 10.11999/JEIT140371 ZHAO Feng, LIU Hanqiang, FAN Jiulun, et al. Intuitionistic fuzzy set approach to multi-objective evolutionary clustering with multiple spatial information for image segmentation[J]. Neurocomputing, 2018, 312: 296–309. doi: 10.1016/j.neucom.2018.05.116 HANDL J and KNOWLES J. An evolutionary approach to multiobjective clustering[J]. IEEE Transactions on Evolutionary Computation, 2007, 11(1): 56–76. doi: 10.1109/TEVC.2006.877146 MUKHOPADHYAY A and MAULIK U. A multiobjective approach to MR brain image segmentation[J]. Applied Soft Computing, 2011, 11(1): 872–880. doi: 10.1016/j.asoc.2010.01.007 DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182–197. doi: 10.1109/4235.996017 REN Xiaofeng and MALIK J. Learning a classification model for segmentation[C]. Proceedings of the 9th IEEE International Conference on Computer Vision, Nice, France, 2003: 10–17. 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, 2012, 34(11): 2274–2282. doi: 10.1109/TPAMI.2012.120 WANG Jianzhong, KONG Jun, LU Yinghua, et al. A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints[J]. Computerized Medical Imaging and Graphics, 2008, 32(8): 685–698. doi: 10.1016/j.compmedimag.2008.08.004 湛西羊, 李良群, 张富有. 融入局部信息的直觉模糊核聚类图像分割算法[J]. 信号处理, 2017, 33(3): 397–405. doi: 10.16798/j.issn.1003-0530.2017.03.021ZHAN Xiyang, LI Liangqun, and ZHANG Fuyou. An intuitionistic kernel-based fuzzy c-means clustering algorithm with local information for image segmentation[J]. Journal of Signal Processing, 2017, 33(3): 397–405. doi: 10.16798/j.issn.1003-0530.2017.03.021 HOLLAND J H. Genetic algorithms[J]. Scientific American, 1992, 267(1): 66–72. doi: 10.1038/scientificamerican0792-66 MAULIK U and BANDYOPADHYAY S. Performance evaluation of some clustering algorithms and validity indices[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(12): 1650–1654. doi: 10.1109/TPAMI.2002.1114856 赵凤. 基于模糊聚类的图像分割[M]. 西安: 西安电子科技大学出版社, 2015: 74–80.ZHAO Feng. Fuzzy Clustering for Image Segmentation[M]. Xi’an: Xidian University Press, 2015: 74–80. ARBELAEZ P, MAIRE M, FOWLKES C, et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898–916. doi: 10.1109/TPAMI.2010.161 WU Mingrui and SCHÖLKOPF B. A local learning approach for clustering[C]. Proceedings of the 19th International Conference on Neural Information Processing Systems, Canada, 2006: 1529–1536.