Utilize este identificador para referenciar este registo: https://hdl.handle.net/10216/83203
Autor(es): Roberta B. Oliveira
Mercedes E. Filho
Zhen Ma
João P. Papa
Aledir S. Pereira
João Manuel R. S. Tavares
Título: Computational methods for the image segmentation of pigmented skin lesions: a review
Data de publicação: 2016
Resumo: Background and objectives: Because skin cancer affects millions of people worldwide, computationalmethods for the segmentation of pigmented skin lesions in images have beendeveloped in order to assist dermatologists in their diagnosis. This paper aims to present areview of the current methods, and outline a comparative analysis with regards to severalof the fundamental steps of image processing, such as image acquisition, pre-processingand segmentation.Methods: Techniques that have been proposed to achieve these tasks were identified andreviewed. As to the image segmentation task, the techniques were classified according totheir principle.Results: The techniques employed in each step are explained, and their strengths and weaknessesare identified. In addition, several of the reviewed techniques are applied to macroscopicand dermoscopy images in order to exemplify their results.Conclusions: The image segmentation of skin lesions has been addressed successfully in manystudies; however, there is a demand for new methodologies in order to improve the efficiency.
Assunto: Ciências Tecnológicas, Ciências da engenharia e tecnologias
Technological sciences, Engineering and technology
Áreas do conhecimento: Ciências da engenharia e tecnologias
Engineering and technology
URI: https://repositorio-aberto.up.pt/handle/10216/83203
Tipo de Documento: Artigo em Revista Científica Internacional
Condições de Acesso: openAccess
Licença: https://creativecommons.org/licenses/by-nc/4.0/
Aparece nas coleções:FEUP - Artigo em Revista Científica Internacional

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
124423.pdfDraft paper2.96 MBAdobe PDFThumbnail
124423.1.png1st Page354.24 kBimage/pngThumbnail

Este registo está protegido por Licença Creative Commons Creative Commons