Development and Research of Skin Lesion Detection and Classification Method
Ver/
Identificadores
URI: http://hdl.handle.net/10317/9718Compartir
Métricas
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemDirector/a
Raudonis, VidasEscuela/Centro
Escuela Técnica Superior de Ingeniería IndustrialUniversidad
Universidad Politécnica de CartagenaDepartamento
Automática, Ingeniería Eléctrica y Tecnología ElectrónicaÁrea de conocimiento
Ingeniería de Sistemas y AutomáticaFecha de publicación
2021Palabras clave
Inteligencia artificialArtificial intelligence
Resumen
[ENG]The aim of the final project is to develop a method for the detection and classification of skin moles.
The written work of the bachelor's project consists of an introduction, in which the reader is
introduced to the problems to be solved, an analysis of the latest literature, which provides
information on similar solutions. The project pays great attention to the mathematical substantiation
of the proposed method, which explains the principles of digital image segmentation and the
classification of moles using the ABCD rule. The section of the proposed method details the method
of skin mole detection and classification, which consists of three main steps, i.e. 1) segmentation of
skin moles using UNet deep neural network, 2) extraction of marks from segmented images, and 3)
classification of skin moles. The experimental research section of the bachelor's final project presents
the results of the accuracy of the proposed skin mole detection and classification algorithm. At ...
Colecciones
El ítem tiene asociados los siguientes ficheros de licencia:
Redes sociales