Texture-Aware Superpixel Segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Texture-Aware Superpixel Segmentation


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
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

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


  • HAL Id : hal-01995819 , version 3


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⟩
191 View
526 Download


Gmail Facebook Twitter LinkedIn More