Exploiting Problem Domain Knowledge for Accurate Building Image Classification
An approach for classification of building images through rule-based fuzzy inference is presented. It exploits rough matching and problem domain knowledge to improve precision results. This approach uses knowledge representation based on a fuzzy reasoning model for establishing a bridge between visual primitives and their interpretations.
Knowledge representation goes from low level to high level features. The knowledge is acquired from both visual content and users. These users provide the interpretations of low level features as well as their knowledge and experience to improve the rule base.
Experiments are tailored to building image classification. This approach can be extended to other semantic categories, i.e. skyline, vegetation, landscapes. Results show that proposed method is promising support for semantic annotation of image/video content.
KeywordsFuzzy Model Semantic Category Semantic Annotation Rule Weight Building Image
Unable to display preview. Download preview PDF.
- 3.Iqbal, Q., Aggarwal, J.K.: Applying Perceptual Grouping to Content-Based Image Retrieval: Building Images. In: Proc. IEEE Int’l Conf. on Computer Vision and Pattern Recognition (CVPR 1999), vol. 1, pp. 42–48 (1999)Google Scholar
- 5.Wang, Y.-N., Chen, L.-B., Hu, B.-G.: Semantic Extraction of the Building Images using Support Vector Machines. In: Proc. IEEE Int’l Conf. on Machine Learning and Cybernetics, vol. 3, pp. 1608–1613 (2002)Google Scholar
- 6.Dorado, A., Izquierdo, E.: Semantic Labeling of Images Combining Color, Texture and Keywords. In: Proc. IEEE Int’l Conf. on Image Processing (ICIP 2003), vol. 3, pp. 9–12 (2003)Google Scholar
- 7.Zeljkovic, V., Dorado, A., Izquierdo, E.: A Modified Shading Model Method for Building Detection. In: 5th Int’l Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2004) (2004) (to appear)Google Scholar
- 8.Dorado, A., Calic, J., Izquierdo, E.: A Rule-Based Video Annotation System. IEEE Trans. on Circuits and Systems for Video Technology (2004) (to appear)Google Scholar
- 9.Choi, Y., Won, C.S., Ro, Y.M., Manjunath, B.S.: Texture Descriptors. In: Manjunath, B.S., Salembier, P., Sikora, T. (eds.) Introduction to MPEG-7, Multimedia Content Description Interface. ch.14, pp. 213–229. Wiley, Chichester (2002)Google Scholar
- 10.TRECVID: TREC Video Retrieval Evaluation (2003), http://www-nlpir.nist.gov/projects/trecvid/