Authors:
Kelly Assis de Souza Gazolli
and
Evandro Ottoni Teatini Salles
Affiliation:
Universidade Federal do Espíırito, Brazil
Keyword(s):
Visual Descriptor, Scene Classification, Gist Descriptor, Contextual Information, Census Transform, Holistic
Approach.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Image and Video Analysis
Abstract:
Scene classification is an important issue in the field of computer vision. To face this problem we explore in
this paper a combination of Holistic Descriptors to scene categorization task. Therefore, we first describe the
Contextual Mean Census Transform (CMCT), an image descriptor that combines distribution of local structures
with contextual information. CMCT is a holistic descriptor based on CENTRIST and, as CENTRIST,
encodes the structural properties within an image and suppresses detailed textural information. Second, we
present the GistCMTC, a combination of Contextual Mean Census Transform descriptor with Gist in order
to generate a new holistic descriptor representing scenes more accurately. Experimental results on four
used datasets demonstrate that the proposed methods could achieve competitive performance against previous
methods.