Texture-Aware Superpixel Segmentation - Archive ouverte HAL
Communication Dans Un Congrès Année : 2019

Texture-Aware Superpixel Segmentation

Résumé

Most superpixel algorithms compute a trade-off between spatial and color features at the pixel level. Hence, they may need fine parameter tuning to balance the two measures, and highly fail to group pixels with similar local texture properties. In this paper, we address these issues with a new Texture-Aware SuperPixel (TASP) method. To accurately segment textured and smooth areas, TASP automatically adjusts its spatial constraint according to the local feature variance. Then, to ensure texture homogeneity within superpixels, a new pixel to superpixel patch-based distance is proposed. TASP outperforms the segmentation accuracy of the state-of-the-art methods on texture and also natural color image datasets.
Fichier principal
Vignette du fichier
Giraud_TASP_2019.pdf (3.26 Mo) Télécharger le fichier
Vignette du fichier
text_img_S2_bsd_1_b_crop.png (48.67 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Domaine public
Format Figure, Image
Loading...

Dates et versions

hal-01995819 , version 2 (05-02-2019)
hal-01995819 , version 3 (09-02-2019)

Licence

Domaine public

Identifiants

  • HAL Id : hal-01995819 , version 3

Citer

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, Yannick Berthoumieu. Texture-Aware Superpixel Segmentation. IEEE International Conference on Image Processing (ICIP'19), Sep 2019, Taipei, Taiwan. pp.1465-1469. ⟨hal-01995819v3⟩
210 Consultations
557 Téléchargements

Partager

More