We present a novel technique for melanocytic lesion segmentation, based on one-dimensional Principal Component Analysis (PCA) in colour space. Our technique is simple and extremely fast, segmenting high-resolution images in a fraction of a second even with the modest computational resources available on a cell phone - an improvement of an order of magnitude or more over state-of-the-art techniques. Our technique is also extremely accurate: very experienced dermatologists disagree with its segmentations less than they disagree with the segmentations of all state-of-the-art techniques we tested, and in fact less than they disagree with the segmentations of dermatologists of moderate experience.
Simple, fast, accurate melanocytic lesion segmentation in 1D colour space / F. Peruch, F. Bogo, M. Bonazza, M. Bressan, V. Cappelleri, E. Peserico - In: Proceedings of the International Conference on Computer Vision Theory and Applications. 1 / [a cura di] S. Battiato, J. Braz. - [s.l] : SCITEPRESS, 2013. - ISBN 978-989-8565-47-1. - pp. 191-200 (( Intervento presentato al 8. convegno International Conference on Computer Vision Theory and Applications tenutosi a Barcelona nel 2013 [10.5220/0004289601910200].
Simple, fast, accurate melanocytic lesion segmentation in 1D colour space
M. Bressan;
2013
Abstract
We present a novel technique for melanocytic lesion segmentation, based on one-dimensional Principal Component Analysis (PCA) in colour space. Our technique is simple and extremely fast, segmenting high-resolution images in a fraction of a second even with the modest computational resources available on a cell phone - an improvement of an order of magnitude or more over state-of-the-art techniques. Our technique is also extremely accurate: very experienced dermatologists disagree with its segmentations less than they disagree with the segmentations of all state-of-the-art techniques we tested, and in fact less than they disagree with the segmentations of dermatologists of moderate experience.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.