Cristin-resultat-ID: 1849068
Sist endret: 18. november 2020, 09:42
Resultat
Vitenskapelig Kapittel/Artikkel/Konferanseartikkel
2008

Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image Retrieval

Bidragsytere:
  • Youcef Djenouri og
  • Jon M. Hjelmervik

Bok

Om resultatet

Vitenskapelig Kapittel/Artikkel/Konferanseartikkel
Publiseringsår: 2008
Revidert utgave

Klassifisering

Fagfelt (NPI)

Fagfelt: Informatikk og datateknikk
- Fagområde: Realfag og teknologi

Beskrivelse Beskrivelse

Tittel

Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image Retrieval

Sammendrag

This paper introduces a highly efficient image retrieval technique called DCNN-vForest (Decomposition Convolution Neural Network and vocabulary Forest), which aims to retrieve the relevant images to the given image query by studying the correlation between images in the image database based on decomposition. The regional and global features of the image database are first extracted using the convolution neural network, and then divided into clusters of similar images using the Kmeans algorithm. We propose a new structure called vForest (vocabulary Forest), by calculating the vocabulary tree on each cluster of images. The retrieval process benefits from the knowledge provided by the vForest, and instead of considering the whole image database, only the most similar cluster to the image query is explored. To demonstrate the usefulness of our approach, intensive experiments have been carried out on ground-truth image databases, the results reveal the superiority of DCNN-vForest against the baseline image retrieval solutions, in terms of runtime and accuracy.

Bidragsytere

Youcef Djenouri

  • Tilknyttet:
    Forfatter
    ved Mathematics and Cybernetics ved SINTEF AS

Jon Mikkelsen Hjelmervik

Bidragsyterens navn vises på dette resultatet som Jon M. Hjelmervik
  • Tilknyttet:
    Forfatter
    ved Mathematics and Cybernetics ved SINTEF AS
1 - 2 av 2

Resultatet er en del av Resultatet er en del av

International Conference on Pattern Recognition [proceedings].

2008, IEEE conference proceedings. Vitenskapelig antologi/Konferanseserie
1 - 1 av 1