Change search
ReferencesLink to record
Permanent link

Direct link
Melanoma recognition using representative and discriminative kernel classifiers
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2006 (English)In: Computer Vision Approaches To Medical Image Analysis / [ed] Beichel, RR, 2006, Vol. 4241, 1-12 p.Conference paper (Refereed)
Abstract [en]

Malignant melanoma is the most deadly form of skin lesion. Early diagnosis is of critical importance to patient survival. Existent visual recognition algorithms for skin lesions classification focus mostly on segmentation and feature extraction. In this paper instead we put the emphasis on the learning process by using two kernel-based classifiers. We chose a discriminative approach using support vector machines, and a probabilistic approach using spin glass-Markov random fields. We benchmarked these algorithms against the (to our knowledge) state-of-the-art method on melanoma recognition, exploring how performance changes by using color or textural features, and how it is affected by the quality of the segmentation mask. We show with extensive experiments that the support vector machine approach outperforms the existing method and, on two classes out of three, it achieves performances comparable to those obtained by expert clinicians.

Place, publisher, year, edition, pages
2006. Vol. 4241, 1-12 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 4241
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-42003ISI: 000241602500001ScopusID: 2-s2.0-33750738872ISBN: 3-540-46257-0OAI: diva2:445821
2nd International ECCV Workshop on Computer Vision Approaches to Medical Image Analysis, CVAMIA 2006; Graz; 12 May 2006 through 12 May 2006
QC 20111005Available from: 2011-10-05 Created: 2011-10-05 Last updated: 2011-10-05Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Caputo, Barbara
By organisation
Computer Vision and Active Perception, CVAP
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 14 hits
ReferencesLink to record
Permanent link

Direct link