Content based image retrieval based on geo-location driven image tagging on the social web

Muhammad Hammad Memon, Jian Ping Li, Imran Memon, Asif Khan, Riaz Ahmed Shaikh, Samundra Deep

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

22 Citations (Scopus)

Abstract

In recently years, in the era of multimedia technologies need for information/data retrieval systems getting more attention. The data might be image, video, audio and/or text files. Digital libraries, surveillance application, web applications and many other applications that handle huge volume of data essentially have data retrieval components. These data always include large-scale of independent information with both textual and visual contents. The large numbers of images has posed increasing challenges to computer systems to store and manage data effectively and efficiently. In this paper, we proposed a method of Geo-location-based image retrieval (GLBIR. The proposed method identifies a geo location in an image using visual attention-based mechanism and represents them using its color layout descriptors and curve let descriptors. These features are extracted from geo location of query image from Flickr. The likeness between the query geo coordinates and image is ranked according to a similarity measure computed from the feature vectors. Our proposed model does not full semantic understanding of image content, uses visual metrics for example proximity, color contrast, size and nearness to image's boundaries to locate viewer's attention. We evaluate our approach on the image dataset from Flickr. We analyzed results analyzed and compared with state of art CBIR Systems and GLBIR Technique.

Original languageEnglish
Title of host publicationICCWAMTIP 2014
Subtitle of host publication2014 11th International Computer Conference on Wavelet Active Media Technology and Information Processing
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages280-283
Number of pages4
ISBN (Electronic)9781479972081
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event2014 11th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2014 - Sichuan Province, Chengdu, China
Duration: 19 Dec 201421 Dec 2014

Other

Other2014 11th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2014
CountryChina
CitySichuan Province, Chengdu
Period19/12/1421/12/14

Keywords

  • location-based social network
  • curvelet transform
  • color layout descriptor
  • machine learning
  • visual attention

Fingerprint Dive into the research topics of 'Content based image retrieval based on geo-location driven image tagging on the social web'. Together they form a unique fingerprint.

Cite this