Novel Methods for Separation of Gangue from Limestone and Coal using Multispectral and Joint Color-Texture Features

Ore sorting is a useful tool to remove gangue material from the ore and increase the quality of the ore. The vast developments in the area of artificial intelligence allow fast processing of full-color digital images for the preferred investigations. The associated gangue minerals from limestone and coal mines were identified using three different approaches. All the methods were based on extensions of the co-occurrence matrix method. In the first method, the color features were extracted from RGB color planes and texture features were extracted using a multispectral extension, in which co-occurrence matrices were computed both between and within the color bands. The second method used joint color-texture features where color features were added to gray scale texture features. The last method used gray scale texture features computed on a quantized color image. Results showed that the accuracy for separation of gangue from limestone, a joint color-texture method was 98 % and for separation of gangue from coal, multispectral method with correlation and joint color-texture method were 100 % respectively. Combined multispectral and joint color-texture methods gave good accuracy with 64 gray levels quantization for separation of gangue from limestone and coal.

[1]  Xiao-Ru Song,et al.  Research on Coal Gangue On-Line Automatic Separation System Based on the Improved BP Algorithm and ARM , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[2]  Zhe Liang,et al.  Automatic Separation System of Coal Gangue Based on DSP and Digital Image Processing , 2011, 2011 Symposium on Photonics and Optoelectronics (SOPO).

[3]  Snehamoy Chatterjee,et al.  Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model , 2010 .

[4]  Qian Mu,et al.  The Application of Coal Cleaning Detection System Based on Embedded Real-Time Image Processing , 2013, 2013 Fifth International Conference on Measuring Technology and Mechatronics Automation.

[5]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[6]  Debi Prasad Tripathy,et al.  Separation Of Gangue From Coal Based On Histogram Thresholding , 2013 .

[7]  Veerendra Singh,et al.  Application of image processing and radial basis neural network techniques for ore sorting and ore classification , 2005 .

[8]  T. D. Jong,et al.  AUTOMATIC SORTING AND CONTROL IN SOLID FUEL PROCESSING: OPPORTUNITIES IN EUROPEAN PERSPECTIVE , 2004 .

[9]  J. D. Salter,et al.  Sorting in the minerals industry: Past, present and future , 1991 .

[10]  Claudio A. Perez,et al.  Ore grade estimation by feature selection and voting using boundary detection in digital image analysis , 2011 .

[11]  Jayson Tessier,et al.  A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor belts , 2007 .

[12]  Yin Zhong,et al.  Identification of Coal and Gangue by Self-Organizing Competitive Neural Network and SVM , 2010, 2010 Second International Conference on Intelligent Human-Machine Systems and Cybernetics.

[13]  A. Benassi,et al.  GENERALIZATION OF THE COOCCURRENCE MATRIX FOR COLOUR IMAGES: APPLICATION TO COLOUR TEXTURE CLASSIFICATION , 2011 .

[14]  H. Soltanian-Zadeh,et al.  Limestone chemical components estimation using image processing and pattern recognition techniques , 2011 .

[15]  Malini Roy Choudhury,et al.  Rock type classification by image analysis using the quaternion colour extraction model and support vector machine classifier , 2014 .

[16]  Naresh Singh,et al.  Textural identification of basaltic rock mass using image processing and neural network , 2010 .

[17]  Xian-Min Ma,et al.  A Revised Edge Detection Algorithm Based on Wavelet Transform for Coal Gangue Image , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[18]  Richard W. Conners,et al.  A Theoretical Comparison of Texture Algorithms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  C. S. Rai,et al.  Comparative analysis of Bayesian regularization and Levenberg-Marquardt training algorithm for localization in wireless sensor network , 2013, 2013 15th International Conference on Advanced Communications Technology (ICACT).

[20]  Xian-Min Ma,et al.  Application of Rough Set Theory in Coal Gangue Image Process , 2009, 2009 Fifth International Conference on Information Assurance and Security.

[21]  Nor Ashidi Mat Isa,et al.  A novel aggregate classification technique using moment invariants and cascaded multilayered perceptron network , 2009 .

[22]  Reiner Lenz,et al.  Generalized co-occurrence matrix for multispectral texture analysis , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[23]  Paul F. Whelan,et al.  Experiments in colour texture analysis , 2001, Pattern Recognit. Lett..

[24]  Snehamoy Chatterjee,et al.  Image-based quality monitoring system of limestone ore grades , 2010, Comput. Ind..

[25]  Xianmin Ma,et al.  Coal Gangue Image Process Approaches with Wavelet Analysis , 2008, 2008 Congress on Image and Signal Processing.

[26]  Haoxiang Wang,et al.  An Efficient of Coal and Gangue Recognition Algorithm , 2013 .

[27]  Chen Zhang,et al.  Coal gangue separation system based on density measurement , 2012, 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE).

[28]  Snehamoy Chatterjee.  Vision-based rock-type classification of limestone using multi-class support vector machine , 2012, Applied Intelligence.

[29]  Bo Fu,et al.  Coal and Coal Gangue Separation Based on Computer Vision , 2010, 2010 Fifth International Conference on Frontier of Computer Science and Technology.

[30]  Zelin Zhang,et al.  Estimation of coal particle size distribution by image segmentation , 2012 .