Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/4070
Title: | On the use of spatial relations between objects for image classification |
Authors: | Tsapatsoulis, Nicolas Petridis, Sergios Perantonis, Stavros J. |
metadata.dc.contributor.other: | Τσαπατσούλης, Νικόλας |
Major Field of Science: | Humanities |
Field Category: | Arts |
Keywords: | Image classification;Object detection;Spatial realations |
Issue Date: | 2007 |
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. |
URI: | https://hdl.handle.net/20.500.14279/4070 |
ISBN: | 9780387741604 |
DOI: | 10.1007/978-0-387-74161-1_38 |
Rights: | © Springer |
Type: | Book Chapter |
Affiliation : | Athens Information Technology |
Appears in Collections: | Κεφάλαια βιβλίων/Book chapters |
CORE Recommender
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.