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.
This work was partially supported by the European Commission under the FP6-027538 contract.
Chapter PDF
Similar content being viewed by others
References
Smith, J., Chang, S.: Visually searching the Web for content. Multimedia, IEEE 4(3) (1997) 12–20
Borenstein, E., Sharon, E., Ullman, S.: Combining Top-Down and Bottom-Up Segmentation. Computer Vision and Pattern Recognition Workshop, 2004 Conference on (2004) 46–46
Levin, A., Weiss, Y.: Learning to Combine Bottom-Up and Top-Down Segmentation. LECTURE NOTES IN COMPUTER SCIENCE 3954 (2006) 581
Kapoor, A., Winn, J.: Located Hidden Random Fields: Learning Discriminative Parts for Object Detection. European Conference on Computer Vision (2006)
Fan, X.: Contextual disambiguation for multi-class object detection. Image Processing, 2004. ICIP’04. 2004 International Conference on 5 (2004)
Wolf, L., Bileschi, S.: A Critical View of Context. International Journal of Computer Vision 69(2) (2006) 251–261
Amit, Y., Geman, D., Fan, X.: A coarse-to-fine strategy for multiclass shape detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on 26(12) (2004) 1606–1621
Singhal, A., Luo, J., Zhu, W.: Probabilistic spatial context models for scene content understanding. Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on 1 (2003)
Fleuret, F., Geman, D.: Coarse-to-Fine Face Detection. International Journal of Computer Vision 41(1) (2001) 85–107
Petridis, S., Tsapatsoulis, N., et al.: Methodology for Semantics Extraction from Multimedia Content. Deliverable, BOEMIE, FP6-027538 (2007) http://www.boemie.org/files/BOEMIE-d2_l-v2.pdf.
Li, W., Candan, K., Hirata, K., Hara, Y.: Hierarchical image modeling for object-based media retrieval. Data & Knowledge Engineering 27(2) (1998) 139–176
Haarslev, V., Möller, R.: Racer: A Core Inference Engine for the Semantic Web. Proceedings of the 2nd International Workshop on Evaluation of Ontology-based Tools (2003) 27–36
Tsapatsoulis, N., Avrithis, Y., Kollias, S.: Facial Image Indexing in Multimedia Databases. Pattern Analysis & Applications 4(2) (2001) 93–107
Tsapatsoulis, N., Pattichis, C, Kounoudes, A., Loizou, C, Constantinides, A., Taylor, J.: Visual Attention based Region of Interest Coding for Video-telephony Applications. In: Proc. CSNDSP, Patras, Greece. (2006)
Deng, Y., Manjunath, B.: Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(8) (2001) 800–810
Bischog, W.: Learning Spatio-temporal relational structures. Applied Artificial Intelligence 15(8) (2001) 707–722
IAAF: International association of athletics federations. http://www.iaaf.org (1996–2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 International Federation for Information Processing
About this paper
Cite this paper
Tsapatsoulis, N., Petridis, S., Perantonis, S.J. (2007). On the use of spatial relations between objects for image classification. In: Boukis, C., Pnevmatikakis, A., Polymenakos, L. (eds) Artificial Intelligence and Innovations 2007: from Theory to Applications. AIAI 2007. IFIP The International Federation for Information Processing, vol 247. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-74161-1_38
Download citation
DOI: https://doi.org/10.1007/978-0-387-74161-1_38
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-74160-4
Online ISBN: 978-0-387-74161-1
eBook Packages: Computer ScienceComputer Science (R0)