Image segmentation incorporating double-mask via graph cuts - Computer Vision Research Group（计算机视觉实验室）

This paper described a novel strategy to apply double-masking in image segmentation based on graph cuts. We provided a reasonable method for imposing seed information automatically at object regions where image labels are difficult to determine during complex underwater scene segmentation. Crcomponent pre-segmentation based on Mahalanobis distance played a role inYCrCbspace. The pre-segmentation region was used as object mask for the graph model of the original image in Crpre-segment binary image. The minimum-enclosing rectangle of the object mask could reduce the calculative area in graph model and the bounding box-provided graph model of the original image with the background mask. Our approach was easily realized and did not require specialized hardware, prior knowledge of underwater conditions, or scene structure. Experimental results demonstrated the robustness and accuracy of the performance of our proposed method.