PaTHOS: Part-based Tree Hierarchy for Object Segmentation

Loreta Suta 1, 2 Mihaela Scuturici 2 Vasile-Marian Scuturici 3 Serge Miguet 1, 2
1 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 BD - Base de Données
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : The problem we address in this paper is the segmentation and hierarchical grouping in digital images. In terms of image acquisition protocol, no constraints are posed to the user. At first, a histogram thresholding provides numerous segments where a homogeneity criterion is respected. Segments are merged together using similarity properties and aggregated in a hierarchy based on spatial inclusions. Shape and color features are extracted on the produced segments. Tests performed on Oxford Flower 17 show that our method outperforms a similar one and allow the relevant object selection from the hierarchy. In our case, this approach represents the first stage towards flower variety identification.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01339200
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, June 29, 2016 - 3:48:38 PM
Last modification on : Thursday, November 21, 2019 - 2:31:45 AM

Identifiers

  • HAL Id : hal-01339200, version 1

Citation

Loreta Suta, Mihaela Scuturici, Vasile-Marian Scuturici, Serge Miguet. PaTHOS: Part-based Tree Hierarchy for Object Segmentation. International Conference on Computer Analysis of Images and Patterns (CAIP), Aug 2013, York, United Kingdom. pp.393-400. ⟨hal-01339200⟩

Share

Metrics

Record views

208