Image processing techniques constitutes an important tool to improve skin cancer diagnose, whose early detection is still the most relevant prognostic factor. Nowadays, the follow-up of suspicious melanocytic skin lesions using standard protocols is possible after the development of digital image technology, enhancing the early detection strategy of the skin cancer diagnose. The correct selection of the borders in these particular images of skin microscopy is sometimes demanding, as these images possess particular artifacts (hairs and air bubbles).A stable algorithm to segment the border of the lesion is also important when the following up of suspicious melanocytic lesions uses quantitative markers, as accessing the geometry of the growth border, symmetry, area, among others. In this paper a new strategy to segment dermoscopy images is presented by merging two different approaches in image processing, the Empirical Mode Decomposition of the Hilbert- Huang Transform to remove common artifacts, followed by a Local Normalization to improve segmentation.
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|