Rechercher

[YFC16] Classification-Driven Active Contour for Dress Segmentation

Conférence Internationale avec comité de lecture : 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), February 2016, pp.22-29, Rome, Italie, (DOI: 10.5220/0005721000220029)

Mots clés: Dress Extraction, Clothing Extraction, Segmentation, SVM Classification, Active Contour

Résumé: In this work we propose a new approach for dress segmentation in fashion images by combining local information with a learning prior to implement a dedicated object extractor. First, a person detector is applied to localize sites in the image that are likely to contain the object. Then, an intra-image two-stage learning process is developed to roughly separate foreground pixels from the background. Finally, the object is finely segmented by employing an active contour algorithm that takes into account the previous segmentation and injects specific knowledge about local curvature in the energy function. The method is validated on a database of manually segmented images. We show examples of both successful segmentation and difficult cases. We quantitatively analyze each component and compare with the well-known GrabCut foreground extraction method.

Equipe: vertigo

BibTeX

@inproceedings {
YFC16,
title="{Classification-Driven Active Contour for Dress Segmentation}",
author=" L. YANG and M. Ferecatu and M. Crucianu and H. Rodrigues ",
booktitle="{11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)}",
year=2016,
month="February",
pages="22-29",
address="Rome, Italie",
doi="10.5220/0005721000220029",
}