Bags of Spatial Relations and Shapes Features for Structural Object Description - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Bags of Spatial Relations and Shapes Features for Structural Object Description

Abstract

We introduce a novel bags-of-features framework based on relative position descriptors, modeling both spatial relations and shape information between the pairwise structural subparts of objects. First, we propose a hierarchical approach for the decomposition of complex objects into structural subparts, as well as their description using the concept of Force Histogram Decomposition (FHD). Then, an original learning methodology is presented, in order to produce discriminative hierarchical spatial features for object classification tasks. The cornerstone is to build an homogeneous vocabulary of shapes and spatial configurations occurring across the objects at different scales of decomposition. An advantage of this learning procedure is its compatibility with traditional bags-of-features frameworks, allowing for hybrid representations of both structural and local features. Classification results obtained on two datasets of images highlight the interest of this approach based on hierarchical spatial relations descriptors to recognize structured objects.
Fichier principal
Vignette du fichier
icpr2016.pdf (1.69 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01496896 , version 1 (01-06-2017)

Identifiers

Cite

Michaël Clément, Camille Kurtz, Laurent Wendling. Bags of Spatial Relations and Shapes Features for Structural Object Description. International Conference on Pattern Recognition (ICPR), Dec 2016, Cancún, Mexico. pp.1994-1999, ⟨10.1109/ICPR.2016.7899929⟩. ⟨hal-01496896⟩
110 View
216 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More