Abstract
In this paper we present an approach for image region classification that combines low-level processing with high-level scene understanding. For the low-level training, predefined image concepts are statistically modelled using wavelet features extracted directly from image pixels. For classification, features of a given test region compared with these statistical models provide probabilistic evaluations for all possible image concepts. Maximising these values themselves already leads to a classification result (label). However, in our paper they are used as an input for the high-level approach exploiting explicitly represented spatial arrangements of labels, so called spatial prototypes. We formalise the problem using Fuzzy Constraint Satisfaction Problems and Linear Programming. They provide a model with explicit knowledge that is suitable to aid the task of region labelling. Experiments performed for nearly 6000 test image regions show that combining low-level and high-level image analysis increases the labelling accuracy significantly.
The research activity leading to this work has been supported by the European Commission under the contract FP6-027026-K-SPACE.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hollink, L., Schreiber, T.A., Wielinga, B.J., Worring, M.: Classification of user image descriptions. International Journal of Human-Computer Studies 61(5) (2004)
Barnard, K., Fan, Q., Swaminathan, R., Hoogs, A., Collins, R., Rondot, P., Kaufhold, J.: Evaluation of localized semantics: data, methodology, and experiments. International Journal of Computer Vision 77, 127–199 (2008)
Fan, J., Gao, Y., Luo, H.: Multi-level annotation of natural scenes using dominant image components and semantic concepts. In: Proc. of ACM Multimedia 2004, pp. 540–547. ACM, New York (2004)
Torralba, A.: Contextual priming for object detection. Int. J. Comput. Vision 53(2), 169–191 (2003)
Grzegorzek, M., Izquierdo, E.: Statistical 3d object classification and localization with context modeling. In: Domanski, M., Stasinski, R., Bartkowiak, M. (eds.) 15th European Signal Processing Conference, Poznan, Poland, PTETiS, Poznan, pp. 1585–1589 (2007)
Yuan, J., Li, J., Zhang, B.: Exploiting spatial context constraints for automatic image region annotation. In: Proc. of ACM Multimedia 2007, pp. 595–604. ACM, New York (2007)
Panagi, P., Dasiopoulou, S., Papadopoulos, T.G., Kompatsiaris, Strintzis, M.G.: A genetic algorithm approach to ontology-driven semantic image analysis. In: Proc. of VIE 2006, pp. 132–137 (2006)
Saathoff, C., Staab, S.: Exploiting spatial context in image region labelling using fuzzy constraint reasoning. In: WIAMIS: Ninth International Workshop on Image Analysis for Multimedia Interactive Services (2008)
Manjunath, B.S., Salembier, P., Sikora, T.: Introduction to MPEG-7 - Multimedia Content Description Interface. John Willey & Sons Ltd., Chichester (2002)
Mallat, S.: A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7), 674–693 (1989)
Webb, A.R.: Statistical Pattern Recognition. John Wiley & Sons Ltd., Chichester (2002)
Grzegorzek, M., Reinhold, M., Niemann, H.: Feature extraction with wavelet transformation for statistical object recognition. In: Kurzynski, M., Puchala, E., Wozniak, M., Zolnierek, A. (eds.) 4th International Conference on Computer Recognition Systems, Rydzyna, Poland, pp. 161–168. Springer, Heidelberg (2005)
Grzegorzek, M.: Appearance-Based Statistical Object Recognition Including Color and Context Modeling. Logos Verlag, Berlin (2007)
Ruttkay, Z.: Fuzzy constraint satisfaction. In: Proc. of Fuzzy Systems 1994, vol. 2, pp. 1263–1268 (1994)
Dasiopoulou, S., Heinecke, J., Saathoff, C., Strintzis, M.G.: Multimedia reasoning with natural language support. In: Proc. of ICSC 2007, pp. 413–420 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saathoff, C., Grzegorzek, M., Staab, S. (2008). Labelling Image Regions Using Wavelet Features and Spatial Prototypes. In: Duke, D., Hardman, L., Hauptmann, A., Paulus, D., Staab, S. (eds) Semantic Multimedia. SAMT 2008. Lecture Notes in Computer Science, vol 5392. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92235-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-92235-3_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92234-6
Online ISBN: 978-3-540-92235-3
eBook Packages: Computer ScienceComputer Science (R0)