Please use this identifier to cite or link to this item:
Title: On the use of spatial relations between objects for image classification
Authors: Tsapatsoulis, Nicolas 
Petridis, Sergios 
Perantonis, Stavros J.
Keywords: Image classification;Object detection;Spatial realations
Category: Arts
Field: Humanities
Issue Date: 2007
Publisher: Springer
Source: Artificial Intelligence and Innovations 2007: from Theory to Applications, 2007, pp.347-356
Series/Report no.: IFIP International Federation for Information Processing;
Abstract: Image classification is addressed in this paper by utilizing spatial relation of detected objects in a rule-based fashion. Instances of particular object classes are detected combining bottom-up (learn-able models based on simple features) and top-down information(object models consisting of primitive geometric shapes such as lines). The rule-based system acts as a model for the spatial configuration of objects, also providing a human interpretable justification of image classification. Experimental results in the athletic domain show that despite inefficiencies in object detection, spatial relations allow for efficient discrimination between visually similar images classes.
ISBN: 9780387741604
DOI: 10.1007/978-0-387-74161-1_38
Rights: © Springer
Type: Book Chapter
Appears in Collections:Κεφάλαια βιβλίων/Book chapters

Show full item record


checked on Jul 7, 2019

Page view(s)

Last Week
Last month
checked on Jan 27, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.