Graph-based skin lesion segmentation of multispectral dermoscopic images - Archive ouverte HAL Access content directly
Conference Papers Year :

Graph-based skin lesion segmentation of multispectral dermoscopic images

Abstract

Accurate skin lesion segmentation is critical for automated early skin cancer detection and diagnosis. We present a novel method to detect skin lesion borders in multispectral der-moscopy images. First, hairs are detected on infrared images and removed by inpainting visible spectrum images. Second, skin lesion is pre-segmented using a clustering of a superpixel partition. Finally, the pre-segmentation is globally regular-ized at the superpixel level and locally regularized in a narrow band at the pixel level.
Fichier principal
Vignette du fichier
Lezoray_ICIP14.pdf (964.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01080036 , version 1 (04-11-2014)

Identifiers

  • HAL Id : hal-01080036 , version 1

Cite

Olivier Lézoray, Marinette Revenu, Michel Desvignes. Graph-based skin lesion segmentation of multispectral dermoscopic images. ICIP 2014 - 21st IEEE International Conference on Image Processing, Oct 2014, Paris, France. ⟨hal-01080036⟩
431 View
320 Download

Share

Gmail Facebook Twitter LinkedIn More