| This software calculates the distance transform of a binary image. Providing a binary image with object pixels shown by 0 and background pixels shown by 255, the program creates an image where the value at a pixel is proportional to the distance of that pixel to the object pixel closest to it. Euclidean Distance Transform: The value at a pixel is set linearly proportional to the Euclidean distance between that pixel and the object pixel closest to it. Since the method uses the value at a single object pixel to determine the value at the pixel of interest, the process is sensitive to noise. If the image is noisy, use the Gaussian distance transform to reduce the effect of noise. If noise is not present Euclidean distance transform is preferred over the Gaussian distance transform because, Euclidean distance transform is faster than the Gaussian distance transform. If noise is present, use the Gaussian distance transformed selecting the standard deviation of the Gaussian proportion to the noise level in the image. Euclidean and Gaussian distance transforms are compared below. |
(a) (b)
(c) (d)
(e) (f)
| Fig. 1. (a) A binary image containing a circle. (b) The same binary image with 5 added random points. (c) Euclidean distance transform of (a). (d) Euclidean distance transform of (b).(e) Gaussian distance transform of (a). (f) Gaussian distance transform of (b). |
To obtain a license for this software, please follow this link =>
| Euclidean distance transform |
| Image Registration and Fusion Systems |
 | |  |