基于Gabor小波和LPP的浮选过程泡沫纹理特征提取及应用

上海交通大学学报（自然版） ›› 2014, Vol. 48 ›› Issue (07): 942-947.

• 自动化技术、计算机技术 • 上一篇下一篇

基于Gabor小波和LPP的浮选过程泡沫纹理特征提取及应用

赵洪伟，谢永芳，曹斌芳，蒋朝辉

(中南大学信息科学与工程学院，长沙 410083)

收稿日期:2013-07-03 出版日期:2014-07-28 发布日期:2014-07-28
基金资助:
国家自然科学基金资助项目(61134006),高等学校博士学科点专项基金博导类资助课题(20120162110076),高等学校博士学科点专项科研基金优先发展领域资助课题(20110162130011)

Extraction and Application of Froth Texture Feature Based on Gabor Wavelets and LPP in Flotation Process

ZHAO Hongwei,XIE Yongfang,CAO Binfang,JIANG Zhaohui

(Institute of Information Science and Engineering, Central South University, Changsha 410083, China)

Received:2013-07-03 Online:2014-07-28 Published:2014-07-28

摘要/Abstract

摘要：

针对Gabor小波进行特征提取时易造成维数灾难和识别效率不高的问题，提出一种基于Gabor小波滤波和局部保持投影（LPP）降维算法相结合的泡沫纹理特征提取方法.首先，利用Gabor滤波器获得原始泡沫图像5个尺度和8个方向的高维特征描述向量；然后，利用LPP算法得到降维特征向量；最后，利用此降维特征向量通过反向传播（BP）神经网络进行不同工况下泡沫类别的识别，进而指导实际矿物浮选生产. 实验结果表明，相对于传统的GLCM方法和Gabor小波纹理特征提取方法，该方法可有效降低泡沫纹理特征向量维数并具有更高的识别效率.

关键词: 浮选控制过程, 纹理特征, Gabor小波, 局部保持投影算法, 反向传播神经网络识别

Abstract:

Considering the problems of dimensional disaster and low recognition efficiency that appear when extracting texture feature using Gabor wavelets method only, a method based on both Gabor wavelets filter and LPP dimensionality reduction algorithm was proposed. First, the description of highdimensional feature vectors of five scales and eight orientations of the image were obtained by using Gabor filters. Next, lowerdimensional feature vectors were obtained by using LPP algorithm. Finally, the lowerdimensional feature vectors were used to recognize different types of froth under different conditions using BP (back propagation) neural network to direct actual mineral manufacture. It is demonstrated by experimental results that this method has a less texture feature vector dimension and a higher recognition efficiency relative to the traditional methods based on GLCM and Gabor wavelets only when extracting texture feature.

Key words: flotation control process, texture feature, Gabor wavelet, locality preserving projections（LPP） algorithm, back propagation (BP) neural network recognition

中图分类号:

TP 391.41

赵洪伟，谢永芳，曹斌芳，蒋朝辉. 基于Gabor小波和LPP的浮选过程泡沫纹理特征提取及应用[J]. 上海交通大学学报（自然版）, 2014, 48(07): 942-947.

ZHAO Hongwei,XIE Yongfang,CAO Binfang,JIANG Zhaohui. Extraction and Application of Froth Texture Feature Based on Gabor Wavelets and LPP in Flotation Process[J]. Journal of Shanghai Jiaotong University, 2014, 48(07): 942-947.

参考文献

［1］龚明光. 泡沫浮选［M］. 北京: 冶金工业出版社, 2007: 295296.

［2］任会峰, 阳春华, 周璇, 等. 基于最小二乘支持向量回归机的矿浆酸碱度鲁棒软测量［J］. 上海交通大学学报, 2011, 45(8): 11361139.

REN Huifeng, YANG Chunhua, ZHOU Xuan, et al. Robust softsensing of slurry pH using LSSVR for mineral flotation process［J］. Journal of Shanghai Jiaotong University, 2011, 45(8): 11361139.

［3］Aldrich C, Marais C, Shean B J, et al. Online monitoring and control of froth flotation systems with machine vision: A review ［J］. International Journal of Mineral Processing, 2010, 96(14):113.

［4］刘文礼, 路迈西, 王凡, 等. 煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别［J］. 化工学报, 2003, 54(6): 830835.

LIU Wenli, LU Maixi, WANG Fan, et al. Extraction of textural feature and recognition of coal flotation froth ［J］. Journal of Chemical Industry and Engineering (China), 2003, 54(6): 830835.

［5］刘金平, 桂卫华, 牟学民, 等. 基于Gabor小波的浮选泡沫图像纹理特征提取［J］. 仪器仪表学报, 2010, 31(8): 17691775.

LIU Jinping, GUI Weihua, MOU Xuemin，et al. Flotation froth image texure feature extraction based on gabor wavelet ［J］. Chinese Journal of Science Instrument, 2010, 31(8): 17691775.

［6］Soundar K R, Murugesan K. Preserving global and local information—A combined approach for recognising face images ［J］. Computer Vision IET, 2010, 4(3): 173182.

［7］Lee Yichun, Chen Chinhsing. Feature extraction for face recognition based on gabor filters and twodimensional locality preserving projections ［C］∥5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Kyoto: Fifth International Conference on IEEE, 1214 Sept, 2009: 106109.

［8］吴秀永, 徐科, 徐金梧. 基于Gabor小波和核保局投影算法的表面缺陷自动识别方法［J］. 自动化学报, 2010, 36(3): 438441.

WU Xiuyong, XU Ke, XU Jinwu. Automatic recognition method of surface defects based on gabor wavelet and kernel locality preserving projections ［J］. ACTA Automatica Sinica, 2010, 36(3): 438441.

［9］Idrissa M, Acheroy M. Texture classification using gabor filters ［J］. Pattern Recognition Letters, 2002, 23(9): 10951102.

［10］张刚, 马宗民. 一种采用Gabor小波的纹理特征提取方法［J］. 中国图像图形学报, 2010, 15(2): 247

254.

ZHANG Gang, MA Zongmin. An approach of using gabor wavelets for texture feature extraction ［J］. Journal of Images and Graghics, 2010, 15(2): 247254.

［11］Li Wei, Prasad S, Fowler J E, et al. LocalityPreserving dimensionality reduction and classification for hyperspectral image analysis ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(4): 11851198.

［12］Lu Guifu, Lin Zhong, Jin Zhong. Orthogonal complete discriminant locality preserving projections for face recognition ［J］. Neural Processing Letters, 2011, 33(3): 235250.

［13］Yu Weiwei, Teng Xiaolong, Liu Chongqing. Face recognition using discriminant locality preserving projections ［J］. Image and Vision Computing, 2006, 24(3): 239248.

［14］阳春华, 任会峰, 桂卫华, 等. 基于泡沫纹理信度分配SVM的矿物浮选工况识别［J］. 仪器仪表学报, 2011, 32(10): 22052209.

YANG Chunhua, REN Huifeng, GUI Weihua, et al. Performance recognition using texture credit distributed SVM for froth flotation process ［J］. Chinese Journal of Scientific Instrument, 2011, 32(10): 22052209.

［15］蒋天一, 胡德金, 许开州, 等. 改进型BP神经网络对球面磨削最高温度的模拟与预测［J］. 上海交通大学学报, 2011, 45(6): 901906.

JIANG Tianyi, HU Dejin, XU Kaizhou, et al. Simulation and prediction of the maximum yemperature in sphere grinding with improved BP neural network model［J］. Journal of Shanghai Jiaotong University, 2011, 45(6): 901906.

基于Gabor小波和LPP的浮选过程泡沫纹理特征提取及应用

Extraction and Application of Froth Texture Feature Based on Gabor Wavelets and LPP in Flotation Process

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价