Skip to main content
placeholder image

Visual descriptors for scene categorization: experimental evaluation

Journal Article


Download full-text (Open Access)

Abstract


  • Humans are endowed with the ability to grasp the overall meaning or the gist of a complex visual scene at a glance. We need only a fraction of a second to decide if a scene is indoors, outdoors, on a busy street, or on a clear beach. In recent years, computational gist recognition or scene categorization has been actively pursued, given its numerous applications in image and video search, surveillance, and assistive navigation. Many visual descriptors have been developed to address the challenges in scene categorization, including the large number of semantic categories and the tremendous variations caused by imaging conditions. This paper provides a critical review of visual descriptors used for scene categorization, from both methodological and experimental perspectives. We present an empirical study conducted on four benchmark data sets assessing the classification accuracy and class separability of state-of-the-art visual descriptors.

Publication Date


  • 2016

Citation


  • X. Wei, S. Lam. Phung & A. Bouzerdoum, "Visual descriptors for scene categorization: experimental evaluation," Artificial Intelligence Review: an international survey and tutorial journal, vol. 45, pp. 333-368, 2016.

Scopus Eid


  • 2-s2.0-84957843069

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=6816&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5788

Has Global Citation Frequency


Number Of Pages


  • 35

Start Page


  • 333

End Page


  • 368

Volume


  • 45

Place Of Publication


  • Netherlands

Abstract


  • Humans are endowed with the ability to grasp the overall meaning or the gist of a complex visual scene at a glance. We need only a fraction of a second to decide if a scene is indoors, outdoors, on a busy street, or on a clear beach. In recent years, computational gist recognition or scene categorization has been actively pursued, given its numerous applications in image and video search, surveillance, and assistive navigation. Many visual descriptors have been developed to address the challenges in scene categorization, including the large number of semantic categories and the tremendous variations caused by imaging conditions. This paper provides a critical review of visual descriptors used for scene categorization, from both methodological and experimental perspectives. We present an empirical study conducted on four benchmark data sets assessing the classification accuracy and class separability of state-of-the-art visual descriptors.

Publication Date


  • 2016

Citation


  • X. Wei, S. Lam. Phung & A. Bouzerdoum, "Visual descriptors for scene categorization: experimental evaluation," Artificial Intelligence Review: an international survey and tutorial journal, vol. 45, pp. 333-368, 2016.

Scopus Eid


  • 2-s2.0-84957843069

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=6816&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5788

Has Global Citation Frequency


Number Of Pages


  • 35

Start Page


  • 333

End Page


  • 368

Volume


  • 45

Place Of Publication


  • Netherlands