Heart segmentation based on mathematical morphology And Otsu in visible human project images / 生物医学工程学杂志

A multi-step method for extracting the heart image from visible human project (VHP) data was proposed in this paper. In the first step, Otsu's thresholding segmentation based on mathematical morphological techniques called opening-by-reconstruction and closing-by-reconstruction was used to preprocess the original image in order to effectively overcome the disadvantages of using only thresholding segmentation. The second step was to extract heart data from the proposed image. This multi-step method improved the computation efficiency and attained higher precision, suggesting its significant value for application in VHP.