Texture-Aware Superpixel Segmentation

Rémi Giraud (1, 2) , Vinh-Thong Ta (2) , Nicolas Papadakis (3) , Yannick Berthoumieu (1)

1 IMS - Laboratoire de l'intégration, du matériau au système
2 Bordeaux INP - Institut Polytechnique de Bordeaux
3 IMB - Institut de Mathématiques de Bordeaux

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.

Mots clés: Superpixels; Texture; Patch; Segmentation

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, Yannick Berthoumieu. Texture-Aware Superpixel Segmentation. 2019. ⟨hal-01995819v2⟩