Abstract
Since 1994, a clinical study has been established to digitize melanocytic lesions from patients who are referred to the Colored Pigment Lesion Clinic in the University of British Columbia. In the past, we have been using circularity as the main feature to reflect the asymmetrical aspect of skin lesions. However, its significance often depends on the accuracy of image segmentation while the borders of many lesions are often fuzzy and irregular. In this paper, we investigate how to use symmetry distance (SD) to improve the measurement of the asymmetries of skin lesions. Two SDs, including the basic SD and the fuzzy SD, and the simple circularity are calculated based on the new set of color images which are digitized under the controlled environment.
| Original language | English |
|---|---|
| Pages (from-to) | 4211-4216 |
| Number of pages | 6 |
| Journal | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
| Volume | 5 |
| Publication status | Published - 1 Dec 1997 |
| Event | Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, United States Duration: 12 Oct 1997 → 15 Oct 1997 |
ASJC Scopus subject areas
- Hardware and Architecture
- Control and Systems Engineering