Bubble Image Segmentation Based on a Novel Watershed Algorithm With an Optimized Mark and Edge Constraint

Bubble size contains important indication information that is closely related to flotation production conditions and process indicators. However, bubble images often have low contrast, noise, many other shortcomings, making foam segmentation a difficult problem the existing methods cannot solve. In this article, an improved watershed algorithm based on optimal labeling edge constraints proposed. Three algorithms are designed obtain different initial tags, then extracted content of tags fused combined foreground tag. To reduce offset line, operator applied extract boundary, boundary priori condition used as constraint correct line. Finally, line obtained by fusing markers external constraints. Industrial experiments show method effective has higher accuracy than methods. The average value variance rand index (RI) 92.88% 0.69, respectively.