基于形态学重建和GMM的球团颗粒图像分割
|
摘要
机器视觉技术的发展为颗粒粒径的自动测量提供了一种有效方法,但是,重叠颗粒的图像分割问题仍有待进一步解决。针对这一问题,提出一种基于形态学重建和高斯混合模型的球团颗粒图像分割算法。首先利用似圆度将单独颗粒和重叠颗粒进行区分;根据重叠颗粒图像距离变换特征建立了高斯混合模型;为实现无监督的聚类,采用形态学重建结合聚类有效性指标的方法获得最佳聚类数目,并利用期望极大(EM)算法进行求解;最后采用圆拟合的方法对缺失的球团颗粒轮廓进行重构,实现了对重叠球团颗粒的分割。实验结果表明,该算法能够有效地对重叠颗粒进行分割,分割正确率评价指标AC为93.6%,明显优于现有的对比算法,为基于机器视觉的球团颗粒粒径分布测量奠定了基础。
The development of machine vision technology provides an effective method for automatic measurement of particle size distribution. However,the overlapping particles in theimageis still difficult to be segmented. To solve this problem, one kind ofpellet image segmentation algorithm based on morphological reconstruction and Gauss mixture model is proposed. To achieve unsupervised clustering, morphological reconstruction combined with clustering validity index isused to obtain the optimal number of clusters.EM algorithm isutilizedto solve this problem. Finally, the missing particle contours arereconstructed by circle fitting method.The segmentation of overlapping pellets is realized. Experimental results show that the algorithm can effectively segment overlapping pellets.The segmentation accuracy evaluation index AC is 93.6%, which is obviously superior to the compared algorithms. The measurement of particle size distribution based on machine vision is founded.
The development of machine vision technology provides an effective method for automatic measurement of particle size distribution. However,the overlapping particles in theimageis still difficult to be segmented. To solve this problem, one kind ofpellet image segmentation algorithm based on morphological reconstruction and Gauss mixture model is proposed. To achieve unsupervised clustering, morphological reconstruction combined with clustering validity index isused to obtain the optimal number of clusters.EM algorithm isutilizedto solve this problem. Finally, the missing particle contours arereconstructed by circle fitting method.The segmentation of overlapping pellets is realized. Experimental results show that the algorithm can effectively segment overlapping pellets.The segmentation accuracy evaluation index AC is 93.6%, which is obviously superior to the compared algorithms. The measurement of particle size distribution based on machine vision is founded.
引文
[1] 杨晓东,张丁辰,刘锟,等.球团替代烧结—铁前节能低碳污染减排的重要途径[J].工程研究-跨学科视野中的工程,2017,9(1):44- 52.YANG X D,ZHANG D CH,LIU K,et al.Substituted pelleting for sintering:An important approach of energy-saving,low-carbon and emission reduction before ironmaking[J].Journal of Engineering Studies,2017,9(1):44- 52.
[2] HEYDARI M,AMIRFATTAHI R,NAZARI B,et al.An industrial image processing-based approach for estimation of iron ore green pellet size distribution[J].Powder Technology,2016,303(3):260- 268.
[3] LAU Y M,DEEN N G,KUIPERS J A M.Development of an image measurement technique for size distribution in dense bubbly flows[J].Chemical Engineering Science,2013,94(5):20- 29.
[4] 蔡强,刘亚奇,曹健,等.一种基于自适应标记与区域间近邻传播聚类的分水岭图像分割算法[J].电子学报,2017,45(8):1911-1918.CAI Q,LIU Y Q,CAO J,et al.A water image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Chinese Journal of Electronics,2017,45(8):1911-1918.
[5] KAUR S,SAHAMBI J S.Curvelet initialized level set cell segmentation for touching cells in low contrast images[J].Computerized Medical Imaging and Graphics,2016(49):46- 57.
[6] MIAO J,HUANG T Z,ZHOU X,et al.Image segmentation based on an active contour model of partial image restoration with local cosine fitting energy[J].Information Sciences,2018(447):52-71.
[7] 张永德,彭景春,刘罡,等.基于水平集的前列腺磁共振图像分割方法研究[J].仪器仪表学报,2017,38(2):416- 424.ZHANG Y D,PENG J C,LIU G,et al.Research on the segmentation method of prostate magnetic resonance image based on level set[J].Chinese Journal of Scientific Instrument,2017,38(2):416- 424.
[8] BAI X,SUN C,ZHOU F.Splitting touching cells based on concave points and ellipse fitting [J].Pattern Recognition,2009,42(11):2434- 2446.
[9] ZAFARI S,EEROLA T,SAMPO J,et al.Segmentation of partially overlapping nanoparticles using concave points[C].Advances in Visual Computing,Springer,2015.
[10] XU L,LU H,ZHANG M.Automatic segmentation of clustered quantum dots based on improved watershed transformation[J].Digital Signal Processing,2014(34):108-115.
[11] CHEN L M,CHEN ZH,FENG AN SH.Image analysis algorithm and verification for on-line molecular sieve size and shape inspection[J].Advanced Powder Technology,2014,25(2):508- 513.
[12] LU C,MAHMOOD M,JHA N,LU C,et al.A robust automatic nuclei segmentation technique for quantitative histopathological image analysis[J].Analytical & Quantitative Cytopathology & Histopathology,2012,34(6):296.
[13] 郭皓然,邵伟,周阿维,等.全局阈值自适应的高亮金属表面缺陷识别新方法[J].仪器仪表学报,2017,38(11):2797- 2804.GUO H R,SHAO W,ZHOU A W,et al.Novel defect recognition method based on adaptive global threshold for highlight metal surface[J].Chinese Journal of Scientific Instrument,2017,38(11):2797- 2804
[14] BAILEY M,GOMEZ C O,FINCH J A.Development and application of an image analysis method for wide bubble size distributions[J].Minerals Engineering,2005,18(12):1214-1221.
[15] REITER M,ROTA P,KLEBER F,et al.Clustering of cell populations in flow cytometry data using a combination of Gaussian mixtures[J].Pattern Recognition,2016(60):1029-1040.
[16] 张辉,金侠挺,JONATHAN W Q M,等.基于曲率滤波和改进GMM的钢轨缺陷自动视觉检测方法[J].仪器仪表学报,2018,39(4):181-194.ZHANG H,JIN XI T,JONATHAN W Q M,et al.Automatic visual detection method of railway surface defectsbased on curvature filtering and improved GMM[J].Chinese Journal of Scientific Instrument,2018,39(4):181-194.
[17] RANJAN R,HUANG B,FATEHI A.Robust Gaussian process modeling using EM algorithm[J].Journal of Process Control,2016(42):125-136.
[18] OUMA O Y,HAHN M.Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c -means clustering and morphological reconstruction [J].Automation in Construction,2017(83):196- 211.
[19] BOUGUESSA M,WANG S,SUN H.An objective approach to cluster validation [J].Pattern Recognition Letters,2006,27(13):1419-1430.
[20] 俞龙江,杨英,孙圣和,等.基于最小二乘拟合法的焊点形状检测[J].仪器仪表学报,2007,28(7):1255-1258.YU L J,YANG Y,SUN SH H,et al.Solder joint shape inspection using least square fitting[J].Chinese Journal of Scientific Instrument,2007,28(7):1255-1258.
[21] VINCENT L,SOILLE P.Watersheds in digital spaces:An efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583- 598.
[22] LIAO M,ZHAO Y Q,LI X H,et al.Automatic segmentation for cell images based on bottleneck detection and ellipse fitting[J].Neurocomputing,2016,173(P3):615- 622.
[23] 苑玮琦,李绍丽,李德健.基于纹理主、旁瓣特征的雪糕棒裂缝缺陷检测[J].仪器仪表学报,2017,38(11):2781- 2787.YUAN W Q,LI SH L,LI D J.Detection of ice cream stick crack defects based on texture mainlobe and sidelobe features[J].Chinese Journal of Scientific Instrument,2017,38(11):2781- 2787.
[2] HEYDARI M,AMIRFATTAHI R,NAZARI B,et al.An industrial image processing-based approach for estimation of iron ore green pellet size distribution[J].Powder Technology,2016,303(3):260- 268.
[3] LAU Y M,DEEN N G,KUIPERS J A M.Development of an image measurement technique for size distribution in dense bubbly flows[J].Chemical Engineering Science,2013,94(5):20- 29.
[4] 蔡强,刘亚奇,曹健,等.一种基于自适应标记与区域间近邻传播聚类的分水岭图像分割算法[J].电子学报,2017,45(8):1911-1918.CAI Q,LIU Y Q,CAO J,et al.A water image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Chinese Journal of Electronics,2017,45(8):1911-1918.
[5] KAUR S,SAHAMBI J S.Curvelet initialized level set cell segmentation for touching cells in low contrast images[J].Computerized Medical Imaging and Graphics,2016(49):46- 57.
[6] MIAO J,HUANG T Z,ZHOU X,et al.Image segmentation based on an active contour model of partial image restoration with local cosine fitting energy[J].Information Sciences,2018(447):52-71.
[7] 张永德,彭景春,刘罡,等.基于水平集的前列腺磁共振图像分割方法研究[J].仪器仪表学报,2017,38(2):416- 424.ZHANG Y D,PENG J C,LIU G,et al.Research on the segmentation method of prostate magnetic resonance image based on level set[J].Chinese Journal of Scientific Instrument,2017,38(2):416- 424.
[8] BAI X,SUN C,ZHOU F.Splitting touching cells based on concave points and ellipse fitting [J].Pattern Recognition,2009,42(11):2434- 2446.
[9] ZAFARI S,EEROLA T,SAMPO J,et al.Segmentation of partially overlapping nanoparticles using concave points[C].Advances in Visual Computing,Springer,2015.
[10] XU L,LU H,ZHANG M.Automatic segmentation of clustered quantum dots based on improved watershed transformation[J].Digital Signal Processing,2014(34):108-115.
[11] CHEN L M,CHEN ZH,FENG AN SH.Image analysis algorithm and verification for on-line molecular sieve size and shape inspection[J].Advanced Powder Technology,2014,25(2):508- 513.
[12] LU C,MAHMOOD M,JHA N,LU C,et al.A robust automatic nuclei segmentation technique for quantitative histopathological image analysis[J].Analytical & Quantitative Cytopathology & Histopathology,2012,34(6):296.
[13] 郭皓然,邵伟,周阿维,等.全局阈值自适应的高亮金属表面缺陷识别新方法[J].仪器仪表学报,2017,38(11):2797- 2804.GUO H R,SHAO W,ZHOU A W,et al.Novel defect recognition method based on adaptive global threshold for highlight metal surface[J].Chinese Journal of Scientific Instrument,2017,38(11):2797- 2804
[14] BAILEY M,GOMEZ C O,FINCH J A.Development and application of an image analysis method for wide bubble size distributions[J].Minerals Engineering,2005,18(12):1214-1221.
[15] REITER M,ROTA P,KLEBER F,et al.Clustering of cell populations in flow cytometry data using a combination of Gaussian mixtures[J].Pattern Recognition,2016(60):1029-1040.
[16] 张辉,金侠挺,JONATHAN W Q M,等.基于曲率滤波和改进GMM的钢轨缺陷自动视觉检测方法[J].仪器仪表学报,2018,39(4):181-194.ZHANG H,JIN XI T,JONATHAN W Q M,et al.Automatic visual detection method of railway surface defectsbased on curvature filtering and improved GMM[J].Chinese Journal of Scientific Instrument,2018,39(4):181-194.
[17] RANJAN R,HUANG B,FATEHI A.Robust Gaussian process modeling using EM algorithm[J].Journal of Process Control,2016(42):125-136.
[18] OUMA O Y,HAHN M.Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c -means clustering and morphological reconstruction [J].Automation in Construction,2017(83):196- 211.
[19] BOUGUESSA M,WANG S,SUN H.An objective approach to cluster validation [J].Pattern Recognition Letters,2006,27(13):1419-1430.
[20] 俞龙江,杨英,孙圣和,等.基于最小二乘拟合法的焊点形状检测[J].仪器仪表学报,2007,28(7):1255-1258.YU L J,YANG Y,SUN SH H,et al.Solder joint shape inspection using least square fitting[J].Chinese Journal of Scientific Instrument,2007,28(7):1255-1258.
[21] VINCENT L,SOILLE P.Watersheds in digital spaces:An efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583- 598.
[22] LIAO M,ZHAO Y Q,LI X H,et al.Automatic segmentation for cell images based on bottleneck detection and ellipse fitting[J].Neurocomputing,2016,173(P3):615- 622.
[23] 苑玮琦,李绍丽,李德健.基于纹理主、旁瓣特征的雪糕棒裂缝缺陷检测[J].仪器仪表学报,2017,38(11):2781- 2787.YUAN W Q,LI SH L,LI D J.Detection of ice cream stick crack defects based on texture mainlobe and sidelobe features[J].Chinese Journal of Scientific Instrument,2017,38(11):2781- 2787.