1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	Joana Raquel Martins Veiga
Title:	Analysis of Temporal Variations in Dermoscopy Images of Pigmented Skin Lesions by Machine Learning Techniques
Issue Date:	2018-07-19
Description:	Each year more people are diagnosed with skin cancer all over the world. The large incidence in populations is causing a huge concern to the scientific community, which leads the development of multiple studies related to diagnose this type of cancer. Therefore computer-aided systems are becoming more important in this field due to the challenging task of discriminate benign from malignant skin lesions. These systems can process several images and are intended to make a decision based on the diagnosis achieved by the processing of the images which will reduce the dependency on the experience of the dermatologist and the time consumed in the visual interpretation of each lesion. The main goal of this thesis is the study of the evolution of pigmented skin lesions. Starting from two images of the same lesion at different moments of evaluation, that is the identification of changes that may lead to the intervention of the specialist. These possible alterations may be evidenced through image processing techniques implemented using MATLAB which may help the physician to make a decision. This work addresses three main steps in image processing namely pre-processing, segmentation and feature extraction and aims to obtain results based on the temporal analysis of the lesion.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
TID identifier:	202115437
URI:	https://hdl.handle.net/10216/114122
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.