CENTRIST: A visual descriptor for scene categorization

Jianxin Wu, Jim M. Rehg

Research output: Contribution to journalArticlepeer-review


CENsus TRansform hISTogram (CENTRIST), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene recognition, especially for indoor environments, require its visual descriptor to possess properties that are different from other vision domains (e.g., object recognition). CENTRIST satisfies these properties and suits the place and scene recognition task. It is a holistic representation and has strong generalizability for category recognition. CENTRIST mainly encodes the structural properties within an image and suppresses detailed textural information. Our experiments demonstrate that CENTRIST outperforms the current state of the art in several place and scene recognition data sets, compared with other descriptors such as SIFT and Gist. Besides, it is easy to implement and evaluates extremely fast.

Original languageEnglish (US)
Article number5674051
Pages (from-to)1489-1501
Number of pages13
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number8
StatePublished - 2011
Externally publishedYes


  • Census Transform
  • Gist
  • Place recognition
  • scene recognition
  • SIFT
  • visual descriptor

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'CENTRIST: A visual descriptor for scene categorization'. Together they form a unique fingerprint.

Cite this