Naming of Image Regions for User-Friendly Image Retrieval
This paper presents a novel method for facilitating user-friendly image retrieval by attaching names to image regions. We first detect only the most prominent regions in images when such entities exist, using our own nonlinear image segmentation technique. Besides their visual features, the layout and relations between selected regions are also emphasized. Next, we apply an adaptive and multi-modal classification and naming of image regions using subsequent clustering methods to the features of the regions and related words as well as relevancy information. For both the naming and the testing, we have added a set of illustrations acting as abstract prototypes of the regions to randomly selected natural images. Experiments on 20,000 natural images show the efficacy of using this multilayer region naming model as well as of extensively interacting with users, enabling them to present their queries by a combination of region names, sketches and example images or regions.
KeywordsVisual Feature Image Retrieval Image Region Natural Image Vector Quantization
Unable to display preview. Download preview PDF.
- 1.Smeulders, A., et al.: Content-based image retrieval at the end of the early years. IEEE Trans. PAMI 22(12), 1349–1380 (2000)Google Scholar
- 5.Hofmann, T.: Learning and Representing Topic. A Hierarchical Mixture Model for Word Occurrences in Document Databases. In: Proc. of CONALD, Pittsburgh (1998)Google Scholar
- 6.Wang, J.Z., Li, J.: Learning-based linguistic indexing of pictures with 2-D MHMMs. In: Proc. ACM Multimedia, pp. 436–445 (2002)Google Scholar
- 7.Lim, J.-H., Tian, Q., Mulhem, P.: Home Photo Content Modeling for Personalized Event-Based Retrieval. IEEE Multimedia 9(2), 28–37 (2003)Google Scholar
- 9.Gabrilovich, E., Markovitch, S.: Feature Generation for Text Categorization Using World Knowledge. In: Proc. of The 19th International Joint Conf. for Artificial Intelligence (2005)Google Scholar
- 11.Kutics, A., Nakagawa, A.: Detecting Prominent Objects for Image Retrieval. In: IEEE International Conference on ICIP, vol. 3, pp. 445–448 (2005)Google Scholar
- 13.Mojsilovic, A.: A method for color naming and description of color composition in images. In: Proc. of the ICIP (2002)Google Scholar
- 15.Hanbury, A.: MUSCLE, Guide to annotation, Version 2.0, Tech. Univ. of Vienna (2005)Google Scholar