Skip to main content
. 2014 Feb 27;9(2):e90036. doi: 10.1371/journal.pone.0090036

Figure 4. Comparison of the segmentation quality achieved by the investigated algorithms on 2D benchmark images from the Broad Bioimage Benchmark Collection (BBBC006v1).

Figure 4

Original image (A), adaptive thresholding using Otsu’s method [23] (B), Otsu’s method combined with watershed-based blob splitting [23], [30] (C), geodesic active contours [31] (D), gradient vector flow tracking [16] (E), graph-cuts segmentation [17] (F), TWANG segmentation (G) and a false colored original image (H). The symbols indicate segmentation errors for nuclei that are either split (#), merged (+), missing (o) or spurious (∼).