Independent Component Clustering for Skin Lesions Characterization - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Independent Component Clustering for Skin Lesions Characterization

S. K. Tasoulis
  • Function : Author
  • PersonId : 1008059
C. N. Doukas
  • Function : Author
  • PersonId : 1014230
I. Maglogiannis
  • Function : Author
  • PersonId : 1008041
V. P. Plagianakos
  • Function : Author
  • PersonId : 1000611

Abstract

In this paper, we propose a clustering technique for the recognition of pigmented skin lesions in dermatological images. It is known that computer vision-based diagnosis systems have been used aiming mostly at the early detection of skin cancer and more specifically the recognition of malignant melanoma tumor. The feature extraction is performed utilizing digital image processing methods, i.e. segmentation, border detection, color and texture processing. The proposed method combines an already successful clustering technique from the field of projection based clustering with a projection pursuit method. Experimental results show great performance on detecting the skin cancer.
Fichier principal
Vignette du fichier
978-3-642-23960-1_55_Chapter.pdf (142.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01571494 , version 1 (02-08-2017)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

S. K. Tasoulis, C. N. Doukas, I. Maglogiannis, V. P. Plagianakos. Independent Component Clustering for Skin Lesions Characterization. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.472-482, ⟨10.1007/978-3-642-23960-1_55⟩. ⟨hal-01571494⟩
35 View
85 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More