A scalable approach for content based image retrieval in cloud datacenter

Liao, Jianxin; Yang, Di; Li, Tonghong; Wang, Jingyu; Qi, Qi y Zhu, Xiaomin (2013). A scalable approach for content based image retrieval in cloud datacenter. "Information Systems Frontiers", v. 6 (n. 1); pp. 129-141. ISSN 1387-3326. https://doi.org/10.1007/s10796-013-9467-0.

Descripción

Título: A scalable approach for content based image retrieval in cloud datacenter
Autor/es:
  • Liao, Jianxin
  • Yang, Di
  • Li, Tonghong
  • Wang, Jingyu
  • Qi, Qi
  • Zhu, Xiaomin
Tipo de Documento: Artículo
Título de Revista/Publicación: Information Systems Frontiers
Fecha: 2013
Volumen: 6
Materias:
Escuela: Facultad de Informática (UPM) [antigua denominación]
Departamento: Lenguajes y Sistemas Informáticos e Ingeniería del Software
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (3MB) | Vista Previa

Resumen

The emergence of cloud datacenters enhances the capability of online data storage. Since massive data is stored in datacenters, it is necessary to effectively locate and access interest data in such a distributed system. However, traditional search techniques only allow users to search images over exact-match keywords through a centralized index. These techniques cannot satisfy the requirements of content based image retrieval (CBIR). In this paper, we propose a scalable image retrieval framework which can efficiently support content similarity search and semantic search in the distributed environment. Its key idea is to integrate image feature vectors into distributed hash tables (DHTs) by exploiting the property of locality sensitive hashing (LSH). Thus, images with similar content are most likely gathered into the same node without the knowledge of any global information. For searching semantically close images, the relevance feedback is adopted in our system to overcome the gap between low-level features and high-level features. We show that our approach yields high recall rate with good load balance and only requires a few number of hops.

Más información

ID de Registro: 28920
Identificador DC: http://oa.upm.es/28920/
Identificador OAI: oai:oa.upm.es:28920
Identificador DOI: 10.1007/s10796-013-9467-0
URL Oficial: http://www.springer.com/business+%26+management/business+information+systems/journal/10796
Depositado por: Memoria Investigacion
Depositado el: 20 Ene 2015 11:52
Ultima Modificación: 04 Dic 2017 15:53
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM