Comparative Study of Segmentation Methods for Tree Leaves Extraction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Comparative Study of Segmentation Methods for Tree Leaves Extraction

Résumé

In this paper, we present a comparative study of segmentation methods, tested for an issue of tree leaves extraction. Approaches implemented include processes using thresholding, clustering, or even active contours. The observation criteria, such as the Dice index, Hamming measure or SSIM for example, allow us to highlight the performance obtained by our guided active coutour algorithm that is specially dedicated to tree leaf segmentation (G. Cerutti et al., Guiding Active Contours for Tree Leaf Segmentation and Identification. ImageCLEF2011). We currently offer a dedicated segmentation tree leaf benchmark, comparing fourteen segmentation methods (ten unsupervised and four supervised) following twenty evaluation criteria.
Fichier non déposé

Dates et versions

hal-01339221 , version 1 (29-06-2016)

Identifiants

Citer

Manuel Grand-Brochier, Antoine Vacavant, Guillaume Cerutti, Kevin Bianchi, Laure Tougne. Comparative Study of Segmentation Methods for Tree Leaves Extraction. ACM ICVS, Workshop VIGTA (International Workshop on Video and Image Ground Truth in computer vision Applications), Jul 2013, St Petersbourg, Russia. pp.1-10, ⟨10.1145/2501105.2501109⟩. ⟨hal-01339221⟩
137 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More