A New CBIR Model Using Semantic Segmentation and Fast Spatial Binary Encoding - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A New CBIR Model Using Semantic Segmentation and Fast Spatial Binary Encoding

Achref Ouni
  • Fonction : Auteur
  • PersonId : 1087983
Thierry Chateau
  • Fonction : Auteur
Eric Royer
  • Fonction : Auteur
Michel Dhome
  • Fonction : Auteur

Résumé

Content Based Image Retrieval(CBIR) is the task of finding similar images from a query one. Since the term similar means here "with the same semantic content", we propose to explore in this paper, a framework that uses Deep Neural Networks based semantic segmentation networks, coupled with a binary spatial encoding. Such simple representation has several relevant properties: 1) It takes advantage of the state of the art semantic segmentation networks and 2) the proposed binary encoding allows a Hamming distance that requests a very low computation budget resulting to a fast CBIR method. Several experiments achieved on public datasets show that our binary semantic signature leads to increase the CBIR accuracy and reduce the execution time. We study the performance of the proposed approach on six different public datasets:
Fichier principal
Vignette du fichier
A_new_CBIR_model_using_semantic_segmentation_and_fast_spatial_binary_encoding___springer_.pdf (4.67 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03813973 , version 1 (13-10-2022)

Identifiants

Citer

Achref Ouni, Thierry Chateau, Eric Royer, Marc Chevaldonné, Michel Dhome. A New CBIR Model Using Semantic Segmentation and Fast Spatial Binary Encoding. International Conference on Computational Collective Intelligence, Oct 2022, Hammamet, Tunisia. pp.437-449, ⟨10.1007/978-3-031-16014-1_35⟩. ⟨hal-03813973⟩
19 Consultations
62 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More