Abstract (EN):
Melanoma detection using medical oriented approaches has been a trend in skin cancer research. This paper uses a Bag-of-Feature model for the detection of melanomas in dermoscopy images and aims at identifying the role of different local texture and color descriptors. This is a medical oriented approach and the reported results are promising (Sensitivity = 93%, Specificity=85%), showing the ability of this method to describe medical dermoscopic features. Moreover, the results show that color descriptors outperform texture ones.
Idioma:
Inglês
Tipo (Avaliação Docente):
Científica
Contacto:
ana.c.fidalgo.barata@ist.utl.pt; jsm@isr.ist.utl.pt; tmendo@fc.up.pt
Nº de páginas:
9