GLCM和NGLDM特征提取方法在锑浮选泡沫图像上的比较
|
摘要
泡沫图像特征与工况紧密相关,对于指导生产操作,调节生产状态发挥着重要作用.纹理特征是泡沫图像中的关键特征,它能表征泡沫表面纹理粗细、形态、灰度等.分别采用GLCM和NGLDM提取锑浮选泡沫图像纹理特征,采用最近邻分类器对工况进行离线识别.结果表明,GLCM具有相对较高的分类正确率,而NGLDM由于具有远优于前者的处理速度更适用于在线工况识别.
The feature of the froth image is closely related to the working condition,which plays an important role in guiding the production operation and regulating the production state.The texture feature is the key feature of froth image,which can characterize the roughness,shape and gray level of the froth surface.In this paper,GLCM and NGLDM are used to extract the texture features of the froth image of antimony floatation,and the off-line recognition of the working condition is carried out by the nearest neighborhood classifier.The results show that,though GLCM has a relatively higher classification accuracy,NGLDM is more suitable for on-line working condition recognition for the high speed in processing.
The feature of the froth image is closely related to the working condition,which plays an important role in guiding the production operation and regulating the production state.The texture feature is the key feature of froth image,which can characterize the roughness,shape and gray level of the froth surface.In this paper,GLCM and NGLDM are used to extract the texture features of the froth image of antimony floatation,and the off-line recognition of the working condition is carried out by the nearest neighborhood classifier.The results show that,though GLCM has a relatively higher classification accuracy,NGLDM is more suitable for on-line working condition recognition for the high speed in processing.
引文
[1]桂卫华,阳春华,谢永芳,等.矿物浮选泡沫图像处理与过程监测技术[M].长沙:中南大学出版社,2013.
[2]Bonifazi G,Massacci P,Meloni A.Prediction of Complex Sulfide Flotation Performances by a Combined 3DFractal and Colour Analysis of the Froths[J].Minerals Engineering,2000,13(7):737-746.
[3]Peng X,Peng T,Zhao L,et al.Working Condition Recognition Based on an Improved NGLDM and Interval Data-based Classifier for the Antimony Roughing Process[J].Minerals Engineering,2016,86:1-9.
[4]桂卫华,阳春华,徐德刚,等.基于机器视觉的矿物浮选过程监控技术研究进展[J].自动化学报,2013,39(11):1879-1888.
[5]吴佳,谢永芳,阳春华,等.泡沫图像特征驱动的锑粗选加药控制策略[J].控制理论与应用,2015,32(12):1599-1606.
[6]刘金平.泡沫图像统计建模及其在矿物浮选过程监控中的应用[D].中南大学硕士学位论文,2013.
[7]周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].中南大学硕士学位论文,2010.
[8]Haralick R M,Shanmugam K,Dinstein I.Textural Features for Image Classification[J].Systems Man&Cybernetics IEEE Transactions on,1973,(6):610-621.
[9]Sun C,Wee W G.Neighboring Gray Level Dependence Matrix for Texture Classification[J].Computer Vision,Graphics,and Image Processing,1983,23(3):341-352.
[10]路迈西,王勇.利用阈值分割技术提取煤泥浮选泡沫图像的物理特征[J].煤炭科学技术,2002,30(8):34-37.
[11]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.
[12]路迈西,王凡,刘晓,等.Analysis of Texture of Froth Image in Coal Flotation[J].中国矿业大学学报:英文版,2001,11(2):100-103.
[13]Haralick R M.Statistical and Structural Approaches to Texture[J].Proceedings of the IEEE,1979,67(5):786-804.
[14]Zhao L,Peng T,Zhao L,et al.Fault Condition Recognition Based on Multi-scale Texture Features and Embedding Prior Knowledge K-means for Antimony Flotation Process[J].IFAC-Papers On Line,2015,48(21):864-870.
[2]Bonifazi G,Massacci P,Meloni A.Prediction of Complex Sulfide Flotation Performances by a Combined 3DFractal and Colour Analysis of the Froths[J].Minerals Engineering,2000,13(7):737-746.
[3]Peng X,Peng T,Zhao L,et al.Working Condition Recognition Based on an Improved NGLDM and Interval Data-based Classifier for the Antimony Roughing Process[J].Minerals Engineering,2016,86:1-9.
[4]桂卫华,阳春华,徐德刚,等.基于机器视觉的矿物浮选过程监控技术研究进展[J].自动化学报,2013,39(11):1879-1888.
[5]吴佳,谢永芳,阳春华,等.泡沫图像特征驱动的锑粗选加药控制策略[J].控制理论与应用,2015,32(12):1599-1606.
[6]刘金平.泡沫图像统计建模及其在矿物浮选过程监控中的应用[D].中南大学硕士学位论文,2013.
[7]周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].中南大学硕士学位论文,2010.
[8]Haralick R M,Shanmugam K,Dinstein I.Textural Features for Image Classification[J].Systems Man&Cybernetics IEEE Transactions on,1973,(6):610-621.
[9]Sun C,Wee W G.Neighboring Gray Level Dependence Matrix for Texture Classification[J].Computer Vision,Graphics,and Image Processing,1983,23(3):341-352.
[10]路迈西,王勇.利用阈值分割技术提取煤泥浮选泡沫图像的物理特征[J].煤炭科学技术,2002,30(8):34-37.
[11]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.
[12]路迈西,王凡,刘晓,等.Analysis of Texture of Froth Image in Coal Flotation[J].中国矿业大学学报:英文版,2001,11(2):100-103.
[13]Haralick R M.Statistical and Structural Approaches to Texture[J].Proceedings of the IEEE,1979,67(5):786-804.
[14]Zhao L,Peng T,Zhao L,et al.Fault Condition Recognition Based on Multi-scale Texture Features and Embedding Prior Knowledge K-means for Antimony Flotation Process[J].IFAC-Papers On Line,2015,48(21):864-870.