CENTRIST: A Visual Descriptor for Scene Categorization | IEEE Journals & Magazine | IEEE Xplore

CENTRIST: A Visual Descriptor for Scene Categorization


Abstract:

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...Show More

Abstract:

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.
Page(s): 1489 - 1501
Date of Publication: 23 December 2010

ISSN Information:

PubMed ID: 21173449

Contact IEEE to Subscribe

References

References is not available for this document.