Image segmentation method for coal particle size distribution analysis_中国颗粒学会


Volurnes 54-56 (2021)

Volurnes 48-53 (2020)

Volurnes 42-47 (2019)

Volurnes 36-41 (2018)

Volurnes 30-35 (2017)

Volurnes 24-29 (2016)

Volurnes 18-23 (2015)

Volurnes 12-17 (2014)

Volurne 11 (2013)

Volurne 10 (2012)

Volurne 9 (2011)

Volurne 8 (2010)

Volurne 7 (2009)

Volurne 6 (2008)

Volurne 5 (2007)

Volurne 4 (2006)

Volurne 3 (2005)

Volurne 2 (2004)

Volurne 1 (2003)


Partic. vol. 56 pp. 163-170 (June 2021)
doi: 10.1016/j.partic.2020.10.002

Image segmentation method for coal particle size distribution analysis

Feiyan Bai, Minqiang Fan*,Hongli Yang, Lianping Dong

Show more


    • Image segmentation is utilised for coal particle size distribution analysis. • A watershed algorithm with gradient is employed for preliminary segmentation. • The k-nearest neighbour algorithm is utilised to merge small pieces to particles. • The convex shell method is introduced to segment adhered particles.


Particle size distribution is extremely important in the coal preparation industry. It is traditionally analysed by a manual screening method, which is relatively time-consuming and cannot immediately guide production. In this paper, an image segmentation method for images of coal particles is proposed. It employs the watershed algorithm, k-nearest neighbour algorithm, and convex shell method to achieve preliminary segmentation, merge small pieces with large pieces, and split adhered particles, respectively. Comparing the automated segmentation using this method with manual segmentation, it is found that the results are comparable. The size distributions obtained by the automated and manual segmentation methods are nearly identical, and the standard deviation is less than 3%, indicating good reliability. This automated image segmentation method provides a new approach for rapidly analysing the size distribution of coal particles with size fractions defined according to consumer requirements.

Graphical abstract


Particle size distribution; Image segmentation; Watershed algorithm using gradient; KNN algorithm; Region merging; Convex shell