Efficient BFCN for Automatic Retinal Vessel Segmentation

Figure 8

Comparison between model changes and segmentation images. Row (a) is the images of the DRIVE dataset, and row (b) is a local enlargement of the images in row a; row (c) is the images of the STARE dataset, and row (d) is a local enlargement of the images in row (c); row (e) is the images of the CHASE dataset, and row (f) is a local enlargement of the images in row (e). The dark blue in Figure 8 is the background. The yellow in the figure is blood vessels, and the light blue that appears in yellow blood vessels is also blood vessels, but the pixel value of this part of the blood vessel is low, which is easier to segment and break.

(a)

(b)

(c)

(d)

(e)

(f)