煤泥浮选泡沫图像特征提取方法研究
|
摘要
煤泥浮选主要是依据煤粒与矸石颗粒表面的物理化学性质的差异进行分选的,通过加入化学药剂,使可浮性较好、疏水的煤粒上升至表面形成浮选泡沫层,可浮性较差、亲水的矸石颗粒留在煤浆中成为浮选尾煤。泡沫表层粘附精煤颗粒的多少可以由泡沫视觉信息表征出来,所以通过提取浮选泡沫层的表面特征可以判断出浮选状态。目前不同状态下的浮选泡沫主要以图像形式来保存,采用工业CCD相机连续摄取浮选泡沫图像,通过提取图像中的泡沫特征来识别浮选状态。在浮选泡沫图像特征提取过程中需要进行一系列的预处理,方可提取出所需的参数。
本文针对煤泥浮选泡沫图像噪声较大、对比度低、有气泡阴影等特点,分别研究了在图像特征提取过程中适合泡沫图像的各种处理方法,通过对这些方法的分析和比较,提出了一些改进算法,并通过仿真实验证明了本文所提方法的准确性。论文主要从以下几个方面作了研究：
首先研究了图像去噪方法,分别对目前应用较多的面积重构开闭滤波方法和高斯滤波方法进行了改进,提出了一种基于面积重构开闭滤波与交替顺序滤波结合的去噪方法和一种自适应高斯滤波方法,并对两种去噪方法进行了对比,分析了每种方法适用的范围。
然后对图像分割方法进行了研究,通过结合两种分割效果互补的方法——基于高斯滤波的标记分水岭分割和基于FCM的分水岭分割方法,提出了一种基于标记叠加的改进分水岭分割方法,经过仿真实验验证了这种方法的有效性,并将该方法与基于梯度低频成分中提取标记的分水岭分割和基于形态预处理和标记提取的分水岭分割方法进行了对比,进一步证实了这种方法的准确性。
最后对浮选泡沫图像进行了特征提取,主要分析了纹理特征、尺寸特征、泡沫稳定度和泡沫承载量四种特征,并通过实验室浮选实验验证了这四种特征量的有效性。
The main basis for coal flotation is the differences in physical and chemical properties of coal particles and gangue particles surface. Hydrophobic coal particles with better flotability rise to the surface to form the froth layer, while hydrophilic gangue particles with poor flotability remain in the coal slurry become flotation tailing by adding chemicals. The number of coal particles adhered in the bubble surface can be characterized by the foam visual information, so the flotation state can be judged by the surface characteristics of flotation foam layer. Currently, flotation foam under different state is saved in the form of image, flotation froth images are continuous intaked by Industrial CCD camera, the flotation states are identified by foam image's characteristics. In order to extract the required parameters, a series of pretreatment should be done in the process of feature extraction of flotation froth image.
In this paper, various image processing approaches for bubble images which have a large of noise, low contrast, bubble shadow and so on are researched in the image feature extraction process, some improved algorithms are imposed after analyzing and comparing these methods, and the accuracy of the proposed method is verified by simulation. The paper mainly studied the following aspects:
Fistly, the image denoising method is researched, The area reconstruction by opening and closing filter method and the Gaussian filtering method are improved, it proposed two denoising methods-n algorithm combining with area reconstruction by opening and closing filter and alternating sequential filter and an adaptive Gaussian filtering method, and the scope of application of each method is analysed by comparing the two methods.
Secondly, the image segmentation method is researched, it proposed an improved watershed segmentation method based on the mark superimposed by combining a marker watershed segmentation based on Gaussian filtering and a watershed segmentation method based on the FCM. It verifies the effectiveness of this method after simulation experiments. Besides, a watershed segmentation method by extracting the markers from low frequency components of the gradients and a watershed segmentation method based on morphological pre-processing and markers extraction were compared with this improved method, it further confirmed the accuracy of this method.
Finally, the features of flotation froth images are extracted, which mainly include texture characteristics, size characteristics, foam stability and foam carrying capacity, The validity of the four characteristic quantities is verified by laboratory flotation tests.
本文针对煤泥浮选泡沫图像噪声较大、对比度低、有气泡阴影等特点,分别研究了在图像特征提取过程中适合泡沫图像的各种处理方法,通过对这些方法的分析和比较,提出了一些改进算法,并通过仿真实验证明了本文所提方法的准确性。论文主要从以下几个方面作了研究：
首先研究了图像去噪方法,分别对目前应用较多的面积重构开闭滤波方法和高斯滤波方法进行了改进,提出了一种基于面积重构开闭滤波与交替顺序滤波结合的去噪方法和一种自适应高斯滤波方法,并对两种去噪方法进行了对比,分析了每种方法适用的范围。
然后对图像分割方法进行了研究,通过结合两种分割效果互补的方法——基于高斯滤波的标记分水岭分割和基于FCM的分水岭分割方法,提出了一种基于标记叠加的改进分水岭分割方法,经过仿真实验验证了这种方法的有效性,并将该方法与基于梯度低频成分中提取标记的分水岭分割和基于形态预处理和标记提取的分水岭分割方法进行了对比,进一步证实了这种方法的准确性。
最后对浮选泡沫图像进行了特征提取,主要分析了纹理特征、尺寸特征、泡沫稳定度和泡沫承载量四种特征,并通过实验室浮选实验验证了这四种特征量的有效性。
The main basis for coal flotation is the differences in physical and chemical properties of coal particles and gangue particles surface. Hydrophobic coal particles with better flotability rise to the surface to form the froth layer, while hydrophilic gangue particles with poor flotability remain in the coal slurry become flotation tailing by adding chemicals. The number of coal particles adhered in the bubble surface can be characterized by the foam visual information, so the flotation state can be judged by the surface characteristics of flotation foam layer. Currently, flotation foam under different state is saved in the form of image, flotation froth images are continuous intaked by Industrial CCD camera, the flotation states are identified by foam image's characteristics. In order to extract the required parameters, a series of pretreatment should be done in the process of feature extraction of flotation froth image.
In this paper, various image processing approaches for bubble images which have a large of noise, low contrast, bubble shadow and so on are researched in the image feature extraction process, some improved algorithms are imposed after analyzing and comparing these methods, and the accuracy of the proposed method is verified by simulation. The paper mainly studied the following aspects:
Fistly, the image denoising method is researched, The area reconstruction by opening and closing filter method and the Gaussian filtering method are improved, it proposed two denoising methods-n algorithm combining with area reconstruction by opening and closing filter and alternating sequential filter and an adaptive Gaussian filtering method, and the scope of application of each method is analysed by comparing the two methods.
Secondly, the image segmentation method is researched, it proposed an improved watershed segmentation method based on the mark superimposed by combining a marker watershed segmentation based on Gaussian filtering and a watershed segmentation method based on the FCM. It verifies the effectiveness of this method after simulation experiments. Besides, a watershed segmentation method by extracting the markers from low frequency components of the gradients and a watershed segmentation method based on morphological pre-processing and markers extraction were compared with this improved method, it further confirmed the accuracy of this method.
Finally, the features of flotation froth images are extracted, which mainly include texture characteristics, size characteristics, foam stability and foam carrying capacity, The validity of the four characteristic quantities is verified by laboratory flotation tests.
引文
[1]许灿辉.矿物浮选气泡速度和尺寸分布特征提取方法与应用[D].长沙：中南大学,2011.
[2]Aldrich C,Marais C,Shean B J,et al. Online Monitoring And Control of Froth Flotation Systems with Machine Vision[J]. International Journal of Mineral Processing,2010, 96:1-13.
[3]Sadr-Kazemi N.. An image processing algorithm for measurement of flotation froth bubble size and shape distributions[J]. Minerals Engineering,1997,10(10):1075-1083.
[4]BonifaziG, SerrantiS., VolpeF., et al. Characterisation of flotation froth colour and structure by machine vision[J]. Computers & Geosciences,2001,27(9):1111-1117.
[5]Wang W, Bergholm F. Minerals Engineering[J], Yang B. Froth delineation based on image classification.2003,16(3):1183-1192.
[6]曾荣.浮选泡沫图像边缘检测方法的研究[J].中国矿业大学学报,2002,31(5)：421-425.
[7]黄玉华,李庆利,韩忠义等.基于灰色系统理论的煤泥浮选泡沫数字图像处理算法研究[J].选煤技术,2006,(4)：6-8.
[8]杨洪薇,肖志涛,翁秀梅等.基于分水岭和模糊C均值聚类的图像分割方法[J].天津工业大学学报,2008,27(1)：53-55.
[9]阳春华,杨尽英,牟学民等.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008,30(6)：1286-1290.
[10]牟春洁,张国英.基于区域边界生长的图像分割方法[J].北京石油化工学院学报,2009,17(4)：8-12.
[11]Bonifazi G, Massacci P, Meloni A. Prediction of complex sulfide flotation performances by combined 3D fractal and colour analysis of the froths[J]. Minerals Engineering, 2000,13(7):7-37.
[12]GrauR. A., Heiskanen K.. Visual technique for measuring bubble size in flotation machines[J]. Minerals Engineering.2002,15(7):507-513.
[13]Lin X. Z., Zhao G Q., Gu Y Y.. A classification of flotation froth based on geometry[A]. In:Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, Harbin.China,2007:2716-2720.
[14]Lin B., ReckeB., Knudsen J. K. H., et al. Bubble size estimation for flotation processes[J]. Minerals Engineering.2008,21(7):539-548.
[15]王凡.煤泥浮选柱泡沫的图像处理与识别[D].北京：中国矿业大学(北京校区),2001.
[16]王凡,王勇,刘文礼等.煤泥浮选泡沫的图像处理[J].煤炭科学技术,2001,29(11)：28-29.
[17]周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].长沙：中南大学,2010.
[18]MoolmanD. W, Aldrich C., SchmitzG. P. J., et al. The interrelationship between surface froth characteristics and industrial flotation performance[J]. Minerals Engeering, 1996,10(6):837-855.
[19]Harrave J M, Hall S T. Diagnosis of concentrate grade and mass flowrate in tin flotation from colour and surface texture analysis[J]. Minerals Engineering,1997,10(6): 6-13.
[20]Bartolacci G, Pelletier P, Tessier J, et al. Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes-Part I: Flotation control based on froth textural characteristics[J]. Mineral Engineering,2006, 19(6-8):734-747.
[21]刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002,30(3)：198-203.
[22]刘文礼,路迈西,王振翀等.煤泥浮选泡沫数字图像处理研究(之一)—浮选泡沫视觉特征的线邻域提取算法[J].中国矿业大学学报,2002,31(2)：120-123.
[23]刘文礼,路迈西,王振翀等.煤泥浮选泡沫数字图像处理研究(之二)—浮选泡沫视觉特征的面邻域提取算法[J].中国矿业大学学报,2002,31(3)：233-236.
[24]王勇.煤泥浮选泡沫图像特征的研究[D].北京：中国矿业大学(北京校区),2002.
[25]王建昆.浮选过程泡沫图像特征识别研究[J].云南冶金,2009,38(1)：65-67.
[26]Sadr-Kazemi N., CilliersJ. J.. An image processing algorithm For measurement of flotation froth bubble size and shape distributions[J]. Minerals Engineering,1997, 10(10):1075-1083.
[27]Holtham P. N., Nguyen K. K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam[J]. International Journal of Mineral Processing,2002, 64(2/3):163-180.
[28]曾荣,沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002,11(1)：37-41.
[29]唐朝晖,刘金平,桂卫华等.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009,40(6)：1616-1622.
[30]徐博,徐岩,于刚.煤泥浮选技术与实践[M].北京：化学工业出版社,2006：2,68-81.
[31]张强,王正林.精通MATLAB图像处理[M].北京：电子工业出版社,2010：136-152,158-194,290-295.
[32]Rafael C. Gonzalez, Richard E. Woods著；阮秋琦,阮宇智等译.数字图像处理(第三版)[M].北京：电子工业出版社,2011：160-182.
[33]Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins著；阮秋琦等译.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2009：94,252-284,315-320,349-352.
[34]Li C. H., Huang W. C., Kuo B. C., et al. A novelfuzzy weighted c-means method for image classification[J]. International Journal of Fuzzy Systems,2008,10(3): 168-173.
[35]鲜燚.耦合马尔可夫随机场与模糊聚类的纹理图像分割算法研究[D].武汉：中南民族大学,2011.
[36]余旺盛,侯志强,宋建军.基于标记分水岭和区域合并的彩色图像分割[J].电子学报,2011,39(5)：1007-1012.
[37]朱俊良,王茂芝,郭科.基于形态预处理和标记提取的分水岭分割算法[J].信息技术,2010(9)：17-20.
[38]唐朝晖,朱楚梅,刘金平.基于LBPV的浮选泡沫图像纹理特征提取[J].计算机应用研究,2011,28(10)：3934-3936.
[39]张铮,王艳平,薛桂香.数字图像处理与机器视觉[M].北京：人民邮电出版社,2010：270-288,383-386.
[40]李智峰,朱谷昌,董泰锋.基于灰度共生矩阵的图像纹理特征地物分类应用[J].地质与勘探,2011,47(3)：456-461.
[41]何桂春,冯金妮,吴艺鹏等.浮选泡沫图像处理技术研究现状与进展[J].有色金属 科学与工程,2011,2(2)：57-63.
[42]周开军,阳春华,牟学民等.基于泡沫特征与LS2SVM的浮选回收率预测[J].仪器仪表学报,2009,30(6)：1295-1300.
[43]Jani K, Van Deventer, Morne BeZuidenhout, Derick W. Moolman. On-line visualization of flotation performance using neural computer vision of the froth texture[A]. Proceedings of the XXIMPC,1997:315-325.
[44]Kaartinen J., Hatonen J., HyotyniemiH., et al. Machine vision based control of zinc flotation-A case study[J]. Control Engineering Practice,2006,14(12):1455-1466.
[45]时愈,汪国有,刘建国.基于拓扑结构的分水岭算法[J].华中科技大学学报(自然科学版),2011,39(11)：5-9.
[46]程翠兰.基于颜色与纹理特征的矿物浮选精矿泡沫分类[D].长沙：中南大学,2010.
[47]吴秀芸,李艳.基于改进标记分水岭的遥感影像建筑物提取[J].水电能源科学,2010,28(4)：72-74.
[48]徐曼.基于改进快速分水岭算法的图像分割技术研究[D].武汉：华中科技大学,2010.
[49]许新征,丁世飞,史忠植等.图像分割的新理论和新方法[J].电子学报,2010,38(2A)：76-82.
[50]卢中宁,强赞霞.基于梯度修正和区域合并的分水岭分割算法[J].计算机工程与设计,2009,30(8)：2075-2077.
[51]何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008,386(8)：96-101.
[51]吴昊,刘正熙,罗以宁等.改进多尺度分水岭算法在医学图像分割中的应用研究[J].计算机应用,2006,26(8)：1975-1979.
[52]王宇,陈殿仁.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11)：2176-2180.
[53]包振健,邸书灵.一种基于分水岭变换的细胞图像分割方法[J].计算机工程与应用,2008,44(4)：230-232.
[54]肖助明,冯月亮,李涛等.形态分水岭算法在重叠米粒图像分割中的应用[J].计算机工程与应用,2007,43(24)：196-199.
[55]谷莹莹,林小竹,李左丽等.基于分水岭变换的浮选泡沫图像分割[J].北京石油化 工学院学报,2007,15(1)：61-65.
[56]林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007,32(3)：304-308.
[57]高丽,杨树元,夏杰等.基于标记的Watershed图像分割新算法[J].电子学报,2006,34(11)：2018-2023.
[58]王麓雅,唐文胜.浮选中泡沫图像的分割算法[J].湖南师范大学学报,2002,25(2)：23-26.
[2]Aldrich C,Marais C,Shean B J,et al. Online Monitoring And Control of Froth Flotation Systems with Machine Vision[J]. International Journal of Mineral Processing,2010, 96:1-13.
[3]Sadr-Kazemi N.. An image processing algorithm for measurement of flotation froth bubble size and shape distributions[J]. Minerals Engineering,1997,10(10):1075-1083.
[4]BonifaziG, SerrantiS., VolpeF., et al. Characterisation of flotation froth colour and structure by machine vision[J]. Computers & Geosciences,2001,27(9):1111-1117.
[5]Wang W, Bergholm F. Minerals Engineering[J], Yang B. Froth delineation based on image classification.2003,16(3):1183-1192.
[6]曾荣.浮选泡沫图像边缘检测方法的研究[J].中国矿业大学学报,2002,31(5)：421-425.
[7]黄玉华,李庆利,韩忠义等.基于灰色系统理论的煤泥浮选泡沫数字图像处理算法研究[J].选煤技术,2006,(4)：6-8.
[8]杨洪薇,肖志涛,翁秀梅等.基于分水岭和模糊C均值聚类的图像分割方法[J].天津工业大学学报,2008,27(1)：53-55.
[9]阳春华,杨尽英,牟学民等.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008,30(6)：1286-1290.
[10]牟春洁,张国英.基于区域边界生长的图像分割方法[J].北京石油化工学院学报,2009,17(4)：8-12.
[11]Bonifazi G, Massacci P, Meloni A. Prediction of complex sulfide flotation performances by combined 3D fractal and colour analysis of the froths[J]. Minerals Engineering, 2000,13(7):7-37.
[12]GrauR. A., Heiskanen K.. Visual technique for measuring bubble size in flotation machines[J]. Minerals Engineering.2002,15(7):507-513.
[13]Lin X. Z., Zhao G Q., Gu Y Y.. A classification of flotation froth based on geometry[A]. In:Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation, Harbin.China,2007:2716-2720.
[14]Lin B., ReckeB., Knudsen J. K. H., et al. Bubble size estimation for flotation processes[J]. Minerals Engineering.2008,21(7):539-548.
[15]王凡.煤泥浮选柱泡沫的图像处理与识别[D].北京：中国矿业大学(北京校区),2001.
[16]王凡,王勇,刘文礼等.煤泥浮选泡沫的图像处理[J].煤炭科学技术,2001,29(11)：28-29.
[17]周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].长沙：中南大学,2010.
[18]MoolmanD. W, Aldrich C., SchmitzG. P. J., et al. The interrelationship between surface froth characteristics and industrial flotation performance[J]. Minerals Engeering, 1996,10(6):837-855.
[19]Harrave J M, Hall S T. Diagnosis of concentrate grade and mass flowrate in tin flotation from colour and surface texture analysis[J]. Minerals Engineering,1997,10(6): 6-13.
[20]Bartolacci G, Pelletier P, Tessier J, et al. Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes-Part I: Flotation control based on froth textural characteristics[J]. Mineral Engineering,2006, 19(6-8):734-747.
[21]刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002,30(3)：198-203.
[22]刘文礼,路迈西,王振翀等.煤泥浮选泡沫数字图像处理研究(之一)—浮选泡沫视觉特征的线邻域提取算法[J].中国矿业大学学报,2002,31(2)：120-123.
[23]刘文礼,路迈西,王振翀等.煤泥浮选泡沫数字图像处理研究(之二)—浮选泡沫视觉特征的面邻域提取算法[J].中国矿业大学学报,2002,31(3)：233-236.
[24]王勇.煤泥浮选泡沫图像特征的研究[D].北京：中国矿业大学(北京校区),2002.
[25]王建昆.浮选过程泡沫图像特征识别研究[J].云南冶金,2009,38(1)：65-67.
[26]Sadr-Kazemi N., CilliersJ. J.. An image processing algorithm For measurement of flotation froth bubble size and shape distributions[J]. Minerals Engineering,1997, 10(10):1075-1083.
[27]Holtham P. N., Nguyen K. K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam[J]. International Journal of Mineral Processing,2002, 64(2/3):163-180.
[28]曾荣,沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002,11(1)：37-41.
[29]唐朝晖,刘金平,桂卫华等.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009,40(6)：1616-1622.
[30]徐博,徐岩,于刚.煤泥浮选技术与实践[M].北京：化学工业出版社,2006：2,68-81.
[31]张强,王正林.精通MATLAB图像处理[M].北京：电子工业出版社,2010：136-152,158-194,290-295.
[32]Rafael C. Gonzalez, Richard E. Woods著；阮秋琦,阮宇智等译.数字图像处理(第三版)[M].北京：电子工业出版社,2011：160-182.
[33]Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins著；阮秋琦等译.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2009：94,252-284,315-320,349-352.
[34]Li C. H., Huang W. C., Kuo B. C., et al. A novelfuzzy weighted c-means method for image classification[J]. International Journal of Fuzzy Systems,2008,10(3): 168-173.
[35]鲜燚.耦合马尔可夫随机场与模糊聚类的纹理图像分割算法研究[D].武汉：中南民族大学,2011.
[36]余旺盛,侯志强,宋建军.基于标记分水岭和区域合并的彩色图像分割[J].电子学报,2011,39(5)：1007-1012.
[37]朱俊良,王茂芝,郭科.基于形态预处理和标记提取的分水岭分割算法[J].信息技术,2010(9)：17-20.
[38]唐朝晖,朱楚梅,刘金平.基于LBPV的浮选泡沫图像纹理特征提取[J].计算机应用研究,2011,28(10)：3934-3936.
[39]张铮,王艳平,薛桂香.数字图像处理与机器视觉[M].北京：人民邮电出版社,2010：270-288,383-386.
[40]李智峰,朱谷昌,董泰锋.基于灰度共生矩阵的图像纹理特征地物分类应用[J].地质与勘探,2011,47(3)：456-461.
[41]何桂春,冯金妮,吴艺鹏等.浮选泡沫图像处理技术研究现状与进展[J].有色金属 科学与工程,2011,2(2)：57-63.
[42]周开军,阳春华,牟学民等.基于泡沫特征与LS2SVM的浮选回收率预测[J].仪器仪表学报,2009,30(6)：1295-1300.
[43]Jani K, Van Deventer, Morne BeZuidenhout, Derick W. Moolman. On-line visualization of flotation performance using neural computer vision of the froth texture[A]. Proceedings of the XXIMPC,1997:315-325.
[44]Kaartinen J., Hatonen J., HyotyniemiH., et al. Machine vision based control of zinc flotation-A case study[J]. Control Engineering Practice,2006,14(12):1455-1466.
[45]时愈,汪国有,刘建国.基于拓扑结构的分水岭算法[J].华中科技大学学报(自然科学版),2011,39(11)：5-9.
[46]程翠兰.基于颜色与纹理特征的矿物浮选精矿泡沫分类[D].长沙：中南大学,2010.
[47]吴秀芸,李艳.基于改进标记分水岭的遥感影像建筑物提取[J].水电能源科学,2010,28(4)：72-74.
[48]徐曼.基于改进快速分水岭算法的图像分割技术研究[D].武汉：华中科技大学,2010.
[49]许新征,丁世飞,史忠植等.图像分割的新理论和新方法[J].电子学报,2010,38(2A)：76-82.
[50]卢中宁,强赞霞.基于梯度修正和区域合并的分水岭分割算法[J].计算机工程与设计,2009,30(8)：2075-2077.
[51]何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008,386(8)：96-101.
[51]吴昊,刘正熙,罗以宁等.改进多尺度分水岭算法在医学图像分割中的应用研究[J].计算机应用,2006,26(8)：1975-1979.
[52]王宇,陈殿仁.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11)：2176-2180.
[53]包振健,邸书灵.一种基于分水岭变换的细胞图像分割方法[J].计算机工程与应用,2008,44(4)：230-232.
[54]肖助明,冯月亮,李涛等.形态分水岭算法在重叠米粒图像分割中的应用[J].计算机工程与应用,2007,43(24)：196-199.
[55]谷莹莹,林小竹,李左丽等.基于分水岭变换的浮选泡沫图像分割[J].北京石油化 工学院学报,2007,15(1)：61-65.
[56]林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007,32(3)：304-308.
[57]高丽,杨树元,夏杰等.基于标记的Watershed图像分割新算法[J].电子学报,2006,34(11)：2018-2023.
[58]王麓雅,唐文胜.浮选中泡沫图像的分割算法[J].湖南师范大学学报,2002,25(2)：23-26.