Volume 11 Issue 5
您当前的位置:首页 > 期刊文章 > 过刊浏览 > Volume 11 (2013) > Volume 11 Issue 5
Zhang, Z., JianguoYang, Su, X., Ding, L., & Wang, Y. (2013). Multi-scale image segmentation of coal piles on a belt based on the Hessian matrix. Particuology, 11(5), 549–555. https://doi.org/10.1016/j.partic.2013.02.011
Multi-scale image segmentation of coal piles on a belt based on the Hessian matrix
Zelin Zhang, JianguoYang, Xiaolan Su, Lihua Ding, Yuling Wang *
School of Chemical Engineering & Technology, China University of Mining & Technology, Xuzhou, Jiangsu 221116, China
10.1016/j.partic.2013.02.011
Volume 11, Issue 5, October 2013, Pages 549-555
Received 20 July 2012, Revised 28 November 2012, Accepted 5 February 2013, Available online 15 June 2013.
E-mail: scetyjg@126.com

Highlights

• A new image segmentation algorithm for coal piles on belt was proposed.

• A multi-scale linear filter was constructed of Hessian matrix and Gaussian function.

• Good seed regions for watershed segmentation were obtained by a series of sub-algorithms.

• Verification showed that the new algorithm is feasible and effective in practical applications.


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.

Graphical abstract
Keywords
Image segmentation; Coal pile; Hessian matrix; Multi-scale linear filter