Title :
Edge Detection of Skin Lesions Using Anisotropic Diffusion
Author :
Pires, Vincius Borges ; Barcelos, Celia A Zorzo
Author_Institution :
Fed. Univ. of Uberlandia, Uberlandia
Abstract :
In this paper the problem of skin lesions segmentation is studied. The clinical diagnosis of skin lesions is not an easy task for dermatologists. The segmentation method that makes the extraction of important characteristics of the image as edges possible, can also aid the dermatologists doctors in the diagnosis of lesions. In this paper we propose a segmentation method that combines partial differential equations and the Canny edges detector to the automatic detection of edges. Experimental results show the efficacy of the method proposed even when the lesion is noisy or contains hair.
Keywords :
edge detection; image segmentation; medical image processing; partial differential equations; skin; Canny edges detector; anisotropic diffusion; clinical diagnosis; dermatologists doctors; edge detection; partial differential equations; skin lesions segmentation; Active contours; Anisotropic magnetoresistance; Detectors; Image edge detection; Image segmentation; Intelligent systems; Lesions; Malignant tumors; Partial differential equations; Skin cancer;
Conference_Titel :
Intelligent Systems Design and Applications, 2007. ISDA 2007. Seventh International Conference on
Conference_Location :
Rio de Janeiro
Print_ISBN :
978-0-7695-2976-9
DOI :
10.1109/ISDA.2007.139