In order to solve the problem of flotation bubbles that the information is weak in bubble edges, which causes image segmentation hard, the new algorithm combining the Fractional Differential, improved level set and Watershed was proposed. The algorithm includes three steps: Image enhancement: the Fractional differential order is automatically determined on image texture information by using fractal analysis, and the improved adaptive fractional differential algorithm is used to enhance bubble edges; Bubble white spot extraction: the traditional Level set algorithm is improved, and it is applied for extracting white spots of bubbles; Image segmentation: the internal and external markers of bubbles are utilized to correct the gradient images, and finally the marked Watershed segmentation algorithm is used to delineate bubbles. For a number of Lead Zink ore froth images with different bubble sizes, we compared several traditional image segmentation algorithms with the new algorithm, the experimental result shows the proposed algorithm can improve the image segmentation accuracy and is effective in reducing the over-segmentation problem. The proposed algorithm is effective in segmenting flotation bubbles.
