Skip to main content
placeholder image

Incorporating local and global information using a novel distance function for scene recognition

Conference Paper


Abstract


  • In the field of scene recognition using only one type of visual feature is not powerful enough to discriminate scene categories. In this paper we propose an innovative method to integrate global and local feature space into a map function based on a novel distance function. A subset of train images denoted as exemplar-set are selected. The local and global distances are defined according to the images in the exemplar-set. Distances are defined such that they indicate the contribution of different semantic aspects and global information in each scene category. An empirical study has been performed on the 15-Scene dataset in order to demonstrate the impact of appropriately incorporating both local and global information for the purpose of scene recognition. The experiments show, our model achieved state-of-the-art accuracy of 87.47.

UOW Authors


  •   Farahzadeh, Elahe (external author)
  •   Cham, Tat-Jen (external author)
  •   Li, Wanqing

Publication Date


  • 2013

Citation


  • Farahzadeh, E., Cham, T. & Li, W. (2013). Incorporating local and global information using a novel distance function for scene recognition. IEEE Workshop on Robot Vision, WORV (pp. 132-137). IEEE Xplore: Institute of Electrical and Electronics Engineers (IEEE).

Scopus Eid


  • 2-s2.0-84880254227

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1582

Has Global Citation Frequency


Start Page


  • 132

End Page


  • 137

Place Of Publication


  • IEEE Xplore

Abstract


  • In the field of scene recognition using only one type of visual feature is not powerful enough to discriminate scene categories. In this paper we propose an innovative method to integrate global and local feature space into a map function based on a novel distance function. A subset of train images denoted as exemplar-set are selected. The local and global distances are defined according to the images in the exemplar-set. Distances are defined such that they indicate the contribution of different semantic aspects and global information in each scene category. An empirical study has been performed on the 15-Scene dataset in order to demonstrate the impact of appropriately incorporating both local and global information for the purpose of scene recognition. The experiments show, our model achieved state-of-the-art accuracy of 87.47.

UOW Authors


  •   Farahzadeh, Elahe (external author)
  •   Cham, Tat-Jen (external author)
  •   Li, Wanqing

Publication Date


  • 2013

Citation


  • Farahzadeh, E., Cham, T. & Li, W. (2013). Incorporating local and global information using a novel distance function for scene recognition. IEEE Workshop on Robot Vision, WORV (pp. 132-137). IEEE Xplore: Institute of Electrical and Electronics Engineers (IEEE).

Scopus Eid


  • 2-s2.0-84880254227

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1582

Has Global Citation Frequency


Start Page


  • 132

End Page


  • 137

Place Of Publication


  • IEEE Xplore