Multi-scale image segmentation of coal piles on a belt based on the Hessian matrix

Abstract Segmenting images of coal piles on a belt is an unsolved problem in coal-based machine vision research, though it is an essential step for estimating size distribution and classifying coal. In this investigation, a new algorithm for segmenting images of coal piles on a belt is proposed. A multi-scale linear filter, constructed of a Hessian matrix and Gaussian function, forms the core of this algorithm and obtains an edge intensity image to form good seed regions for a watershed segmentation. Manual segmentation is used to define ground truth segmentation images to quantify the errors of the proposed method. Tests indicate that 12.76% of the visible regions are under- or over-segmented, and that this algorithm is feasible and effective in practical applications.

[1]  Nick J. Miles,et al.  Estimation of the size distribution of particles moving on a conveyor belt , 2007 .

[2]  Pheng-Ann Heng,et al.  A double-threshold image binarization method based on edge detector , 2008, Pattern Recognit..

[3]  John M Kemeny,et al.  Improvements in blast fragmentation models using digital image processing , 2001 .

[4]  Guido Gerig,et al.  Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1998, Medical Image Anal..

[5]  Xing-Qiang Wu,et al.  A segmentation method for multi-connected particle delineation , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

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

[7]  David LaRosa,et al.  VisioRock, an integrated vision technology for advanced control of comminution circuits , 2004 .

[8]  Wang Wei-xing,et al.  Particle Size Estimation Based on Edge Density , 2005 .

[9]  Weixing Wang.  Image analysis of aggregates , 1999 .

[10]  Guido Gerig,et al.  3D Multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1997, CVRMed.

[11]  Kim C. Ng,et al.  Identifying, visualizing, and comparing regions in irregularly spaced 3D surface data , 2005, Comput. Vis. Image Underst..

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

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

[14]  Norbert H. Maerz.  Automated Online Optical Sizing Analysis , 2001 .

[15]  Samir Kumar Bandyopadhyay,et al.  Technique for preprocessing of digital mammogram , 2012, Comput. Methods Programs Biomed..

[16]  Marcel van Herk.  A fast algorithm for local minimum and maximum filters on rectangular and octagonal kernels , 1992, Pattern Recognit. Lett..

[17]  U. Raff,et al.  Automated estimation of rock fragment distributions using computer vision and its application in mining , 2005 .