| Paper: | TA-L2.1 |
| Session: | Image and Video Segmentation III: Edge or Color Segmentation |
| Time: | Tuesday, September 18, 09:50 - 10:10 |
| Presentation: |
Lecture
|
| Title: |
SKELETONIZATION BY GRADIENT DIFFUSION AND REGULARIZATION |
| Authors: |
Frank Le Bourgeois; INSA de Lyon | | |
| | Hubert Emptoz; INSA de LYON | | |
| Abstract: |
This paper describes a skeletonization process for grayscale or color images which uses gradient vectors diffusion. We propose to diffuse the native gradients of the original images to obtain the skeleton of the main contrasted objects. In the opposite to a distance transform or thinning based skeleton, the gradient vectors diffusion is a straightforward and simple efficient approach to compute the skeleton, which requires no parameters or predefined criteria and no preliminary binarization of the image. In comparison to other approaches based on potential field functions, our method do not require the segmentation of the objects or the precise localization of the contours. Our method is very simple to implement and can be applied to natural noisy color images. Some results on real color and grayscale images are reported. |
