2.3 Vessel process detection

In the first step, our approach starts with the extraction of vessel centerlines, i.e., the preprocessing phase.

## 2.3.1 Binarization phase

The binarization phase is used to convert the gray image to a binary image using the thresholding technique [28–32]. The intensity Io (x, y) of the binary image is transformed using the following equation:

$$I\_o(\varkappa, \jmath) = \begin{cases} 1 & I\_i(\varkappa, \jmath) > \text{Threshold} \\ 0 & \text{Otherwise} \end{cases} \tag{1}$$

where Ii (x, y) is the intensity of the initial image.

Figure 3.

Example fundus image from the STARE database. (a) Example raw retinal image from the proposed database im0139.ppm. (b) The manual segmentation of the vessels im0139.ah.ppm.

Reconstruction of Three-Dimensional Blood Vessel Model Using Fractal Interpolation DOI: http://dx.doi.org/10.5772/intechopen.82247
