Centre de documentation
scientifique

A feature fusion framework for hashing / I-Hong Jhuo (2016)  

Public Titre : A feature fusion framework for hashing Type de document : Article/Communication Auteurs : I-Hong Jhuo, Auteur ; Li Weng , Auteur ; Wen-Huang Cheng, Auteur ; D.T. Lee, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2016 Conférence : ICPR 2016, 23rd International Conference on Pattern Recognition 04/12/2016 08/12/2016 Cancun Mexique Proceedings IEEE Importance : pp 2289 - 2294 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] fusion de données [Termes IGN] graphe [Termes IGN] mesure de similitude Résumé : (auteur) A hash algorithm converts data into compact strings. In the multimedia domain, effective hashing is the key to large-scale similarity search in high-dimensional feature space. A limit of existing hashing techniques is that they typically use single features. In order to improve search performance, it is necessary to utilize multiple features. Due to the compactness requirement, concatenation of hash values from different features is not an optimal solution. Thus a fusion process is desired. In this paper, we solve the multiple feature fusion problem by a hash bit selection framework. Given multiple features, we derive an n-bit hash value of improved performance compared with hash values of the same length computed from each individual feature. The framework utilizes a feature-independent hash algorithm to generate a sufficient number of bits from each feature, and selects n bits from the hash bit pool by leveraging pair-wise label information. The metric bit reliability is used for ranking the bits. It is estimated by bit-level hypothesis testing. In addition, we also take into account the dependence among bits. A weighted graph is constructed for refined bit selection, where the bit reliability is used as vertex weights and the mutual information among hash bits is used as edge weights. We demonstrate our framework with LSH. Extensive experiments confirm that our method is effective, and outperforms several state-of-the-art methods. Numéro de notice : C2016-042 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/ICPR.2016.7899977 Date de publication en ligne : 24/04/2017 En ligne : https://doi.org/10.1109/ICPR.2016.7899977 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91854