Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloAggregating binary local descriptors for image retrieval
Anno di pubblicazione2018
Formato
  • Elettronico
  • Cartaceo
Autore/iAmato G.; Falchi F.; Vadicamo L.
Affiliazioni autoriCNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy
Autori CNR e affiliazioni
  • LUCIA VADICAMO
  • GIUSEPPE AMATO
  • FABRIZIO FALCHI
Lingua/e
  • inglese
AbstractContent-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature. On one hand, the cost for extracting, representing, and comparing local visual descriptors has been dramatically reduced by recently proposed binary local features. On the other hand, aggregation techniques provide a meaningful summarization of all the extracted feature of an image into a single descriptor, allowing us to speed up and scale up the image search. Only a few works have recently mixed together these two research directions, defining aggregation methods for binary local features, in order to leverage on the advantage of both approaches.In this paper, we report an extensive comparison among state-of-the-art aggregation methods applied to binary features. Then, we mathematically formalize the application of Fisher Kernels to Bernoulli Mixture Models. Finally, we investigate the combination of the aggregated binary features with the emerging Convolutional Neural Network (CNN) features. Our results show that aggregation methods on binary features are effective and represent a worthwhile alternative to the direct matching. Moreover, the combination of the CNN with the Fisher Vector (FV) built upon binary features allowed us to obtain a relative improvement over the CNN results that is in line with that recently obtained using the combination of the CNN with the FV built upon SIFTs. The advantage of using the FV built upon binary features is that the extraction process of binary features is about two order of magnitude faster than SIFTs.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da5385
Pagine a5415
Pagine totali31
RivistaMultimedia tools and applications
Attiva dal 1995
Editore: Kluwer Academic Publishers - Dordrecht ;
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 1380-7501
Titolo chiave: Multimedia tools and applications
Numero volume della rivista77
Fascicolo della rivista5
DOI10.1007/s11042-017-4450-2
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85014088854)
  • ISI Web of Science (WOS) (Codice:000427132800013)
Parole chiaveBag of words, Binary local feature, Content-based image retrieval, Convolutional neural network, Fisher vector, VLAD
Link (URL, URI)https://link.springer.com/article/10.1007/s11042-017-4450-2
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioniOnline First 02 March 2017
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR
  • ICT.P08.010.002 : Digital Libraries
Progetti Europei
Allegati
Aggregating binary local descriptors for image retrieval (documento privato )
Descrizione: Online published version
Tipo documento: application/pdf
Aggregating binary local descriptors for image retrieval (documento privato )
Descrizione: print published version
Tipo documento: application/pdf
Aggregating binary local descriptors for image retrieval
Descrizione: postprint
Tipo documento: application/pdf