An Effective Visual Descriptor Based on Color and Shape Features for Image Retrieval - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

An Effective Visual Descriptor Based on Color and Shape Features for Image Retrieval

Atoany Fierro-Radilla
  • Fonction : Auteur
Karina Perez-Daniel
  • Fonction : Auteur
Mariko Nakano-Miyatakea
  • Fonction : Auteur
Hector Perez-Meana
  • Fonction : Auteur

Résumé

In this paper we present a Content-Based Image Retrieval (CBIR) system which extracts color features using Dominant Color Correlogram Descriptor (DCCD) and shape features using Pyramid Histogram of Oriented Gradients (PHOG). The DCCD is a descriptor which extracts global and local color features, whereas the PHOG descriptor extracts spatial information of shape in the image. In order to evaluate the image retrieval effectiveness of the proposed scheme, we used some metrics commonly used in the image retrieval task such as, the Average Retrieval Precision (ARP), the Average Retrieval Rate (ARR) and the Average Normalized Modified Retrieval Rank (ANMRR) and the Average Recall (R)-Average Precision (P) curve. The performance of the proposed algorithm is compared with some other methods which combine more than one visual feature (color, texture, shape). The results show a better performance of the proposed method compared with other methods previously reported in the literature.
Fichier non déposé

Dates et versions

hal-01436999 , version 1 (16-01-2017)

Identifiants

Citer

Atoany Fierro-Radilla, Karina Perez-Daniel, Mariko Nakano-Miyatakea, Hector Perez-Meana, Jenny Benois-Pineau. An Effective Visual Descriptor Based on Color and Shape Features for Image Retrieval. Mexican International Conference on Artificial Intelligence MICAI 2014, Nov 2014, Tuxtla Gutiérrez, Mexico. pp.336-348, ⟨10.1007/978-3-319-13647-9_31⟩. ⟨hal-01436999⟩

Collections

CNRS
68 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More