Texture-Aware Superpixel Segmentation
GIRAUD, Rémi
Laboratoire de l'intégration, du matériau au système [IMS]
Institut Polytechnique de Bordeaux [Bordeaux INP]
Laboratoire de l'intégration, du matériau au système [IMS]
Institut Polytechnique de Bordeaux [Bordeaux INP]
TA, Vinh-Thong
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut Polytechnique de Bordeaux [Bordeaux INP]
See more >
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut Polytechnique de Bordeaux [Bordeaux INP]
GIRAUD, Rémi
Laboratoire de l'intégration, du matériau au système [IMS]
Institut Polytechnique de Bordeaux [Bordeaux INP]
Laboratoire de l'intégration, du matériau au système [IMS]
Institut Polytechnique de Bordeaux [Bordeaux INP]
TA, Vinh-Thong
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut Polytechnique de Bordeaux [Bordeaux INP]
< Reduce
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Institut Polytechnique de Bordeaux [Bordeaux INP]
Language
en
Communication dans un congrès
This item was published in
IEEE International Conference on Image Processing (ICIP'19), 2019-09-28, Taipei. 2019-08-23p. 1465-1469
English Abstract
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 ...Read more >
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.Read less <
European Project
Nonlocal Methods for Arbitrary Data Sources
Origin
Hal imported