GIRAUD, Rémi; TA, Vinh-Thong; PAPADAKIS, Nicolas; BERTHOUMIEU, Yannick

Metadatos

Licencia de uso del documento

GIRAUD, Rémi
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]

PAPADAKIS, Nicolas
Institut de Mathématiques de Bordeaux [IMB]

Idioma

Communication dans un congrès

Este ítem está publicado en

IEEE International Conference on Image Processing (ICIP'19), 2019-09-28, Taipei. 2019-08-23p. 1465-1469

Resumen en inglés

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.< Leer menos

URI

https://oskar-bordeaux.fr/handle/20.500.12278/192813

Proyecto europeo

Nonlocal Methods for Arbitrary Data Sources

Orígen

Importado de Hal

Centros de investigación

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251