Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/23559
Author(s): Alex F. Araújo
Aledir Silveira Pereira
Norian Marranghello
João Manuel R. S. Tavares
Title: Segmentation of skin lesions by watershed using Mumford-Shah in the seeding process
Issue Date: 2010
Abstract: In this work, image regions are segmented using the Mumford-Shah method. Thus, eachregion is elastically modeled by a set of image pixels and the segmentation process isdriven by image forces until the region becomes steady. Then, a merging algorithmbased on the usual intensity of lesion-image pixels is applied to connect the lesion areaspreviously segmented. The contour of the merged regions approximates the lesionborder, but needs further refinements in order to conveniently represent the desiredborder, particularly in terms of irregularity that is over smoothed. To overcome thisproblem, the watershed method is used considering points on the smoothed contour asseeds. This computational approach successfully detects regions on the injured skin andextracts their contours maintaining the original irregularity.
Subject: Ciências Tecnológicas, Outras ciências da engenharia e tecnologias
Technological sciences, Other engineering and technologies
Scientific areas: Ciências da engenharia e tecnologias::Outras ciências da engenharia e tecnologias
Engineering and technology::Other engineering and technologies
URI: https://repositorio-aberto.up.pt/handle/10216/23559
Source: Workshop on Imaging Sciences and Medical Applications
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: restrictedAccess
License: https://creativecommons.org/licenses/by-nc/4.0/
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
56056.1.pdf
  Restricted Access
185.87 kBAdobe PDF    Request a copy from the Author(s)
56056.pdf
  Restricted Access
12.48 kBAdobe PDF    Request a copy from the Author(s)


This item is licensed under a Creative Commons License Creative Commons