Skip to main content


Springer Nature is making Coronavirus research free. View research | View latest news | Sign up for updates

Figure 3 | BMC Bioinformatics

Figure 3

From: Unsupervised segmentation of noisy electron microscopy images using salient watersheds and region merging

Figure 3

Under- and over-segmentation error of each algorithm with respect to ground-truth. The average and standard deviation of A) APD and B) SPD for each algorithm on our EM benchmark dataset. Overall, our algorithm preserves more true ground-truth boundaries (APD) and better captures true ground-truth segments within a single region (SPD) compared to TurboPixels and SLIC.

Back to article page