Improved Extracting Algorithm of Internal Markers for Froth Image Watershed Segmentation of Coal Flotation

Special Issues Editor (Nottingham Tent University, United Kingdom (Great Britain))

In view of much noise and low contrast and difficulty of segmenting froth in froth image of coal flotation, by a large number of experiments and simulations, this paper presents an improved algorithm to extract internal markers in watershed segmentation of coal flotation froth images. The improved algorithm is a fusion of particle swarm optimization algorithm and one dimensional histogram weighted fuzzy C -means clustering method in order to identify the internal markers of watershed segmentation exactly. By particle swarm optimization algorithm, image thresholds to binarize froth image were optimized by selecting 2-D maximum entropy as the fitness function based on gray level co-occurrence matrix. The simulation results proved the applicability and accuracy of improved method in internal marker extraction by comparing this method with other general of extracting marker method for watershed image segmentation.

Journal: International Journal of Simulation: Systems, Science & Technology, IJSSST V17

Published: Jul 14, 2016

DOI: 10.5013/IJSSST.a.17.26.16