Research on small target segmentation method in dual-energy X-ray images of coal and gangue based on APSO-C_Otsu

Abstract

ABSTRACT Compared with wet coal preparation and traditional dry coal preparation, detection of coal and gangue with small particle size is a difficult problem for dual-energy X-ray separation technology. And small target segmentation is the premise of its detection, which is poor due to the fewer number of pixels and texture information in coal and gangue dual-energy X-ray images. So, the Otsu with crotch structure based on Adaptive Particle Swarm Optimization (APSO) for small target segmentation method is proposed, called after APSO-C_Otsu. Firstly, the Otsu with crotch structure is used to increase the contrast between small target and background. Meanwhile, the APSO algorithm was used to optimize the Otsu algorithm with crotch structure in order to improve its convergence speed and reduce its calculation amount. Finally, after binarization, the location of the targets are labeled based on the bwlabel algorithm. The results revealed that the APSO-C_Otsu algorithm could effectively segment the coal and gangue with a particle size of 5–30 mm, and was also applicable to the coal and gangue with the particle size larger than 30 mm, which was of great significance for accurate detection of coal and gangue and the improvement of coal utilization.