Abstract
Certain components in images can be recognized with high accuracy, for example, backgrounds such as leaves, grass, snow, sky, water. These components provide the human eye with context for identifying items in the foreground. Likewise for the machine, the identification of background should help in the recognition of foreground objects. But, in this case, the computer needs explicit lists of object and background co-occurrence probabilities. We examine two ways of deriving estimates of these a priori object co-occurrence probabilities: using an online social network of people storing annotated images, FlickR; and using variations on co-occurrence frequencies in natural language text. We show that the object co-occurrence probabilities derived from both sources are very similar. The possibility of using non-image derived semantic knowledge drawn from text processing for object recognition opens up possibilities of mining a priori probabilities for a much wider class of objects than those found in manually annotated collections.
This research was funded by a grant from the Fondation Jean-Luc Lagardère http://www.fondation-jeanluclagardere.com.
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
Barnard, K., Duygulu, P., de Freitas, N., Forsyth, D., Blei, D., Jordan, M.I.: Matching words and pictures. Journal of Machine Learning Research 3, 1107–1135 (2003)
Bar-Ilan, J.: Expectations versus reality - Search engine features needed for Web research at mid 2005. Int. Journal of Scientometrics, Informetrics and Bibliometrics 9(1) (2005)
Carbonetto, P., de Freitas, N., Barnard, K.: A Statistical model for general contextual object recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 350–362. Springer, Heidelberg (2004)
Davon, D.: Forest before the trees: the precedence of global features in visual perception. Cognitive Psychology 9, 353–383 (1977)
De Graef, P., Christiaens, D., d’Ydewalle, G.: Perceptual effects of scene context on object identification. Psychological Research 52, 317–329 (1990)
Duygulu, P., Barnard, K., de Freitas, N., Forsyth, D., Jordan, M.I.: Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 97–112. Springer, Heidelberg (2002)
Fei-Fei, L., Perona, P.: A Bayesian Hierarchical Model for Learning Natural Scene Categories. In: Proc. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition (2005)
Gonzalo, J., Karlgren, J., Clough, P.: iCLEF 2006 Overview: Searching the Flickr WWW photo-sharing repository. In: Proceedings of CLEF 2006 workshop. LNCS, vol. 4730, pp. 186–194 (2006)
Hoiem, D., Efros, A.A., Hebert, M.: Putting Objects in Perspective. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2137–2144 (2006)
Jin, Y., Khan, L., Wang, L., Awad, M.: Image annotations by combining multiple evidence & wordNet. In: Proceedings of the 13th Annual ACM international Conference on Multimedia, pp. 706–715 (2005)
Kilgarriff, A.: Googleology is Bad Science. Computational Linguistics 33(1), 147–151 (2007)
Millet, C., Bloch, I., Hede, P., Moellic, P.A.: Using relative spatial relationships to improve individual region recognition. In: Proceedings of EWIMT (2005)
Moëllic, P.A., Hède, P., Grefenstette, G., Millet, C.: Evaluating Content Based Image Retrieval Techniques with the One Million Images CLIC TestBed. In: Proc. World Enformatika Congress, pp. 171–174 (2005)
Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. Journal of Computer Vision 42 (2001)
R Development Core Team: R: A language and environment for statistical computing (2007)
Sarkar, D.: lattice: Lattice Graphics. R package version 0.14–17 (2007)
Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: Proceedings Ninth IEEE International Conference on Computer Vision pp. 273–280 (2003)
Tuffield, M., Harris, S., Dupplaw, D.P., Chakravarthy, A., Brewster, C., Gibbins, N., O’Hara, K., Ciravegna, F., Sleeman, F., Shadbolt, N.R., Wilks, Y.: Image annotation with Photocopain. In: Proceedings of the Fifteenth World Wide Web Conference (2006)
Vogel, J., Schiele, B.: A semantic typicality measure for natural scene categorization. In: Proceedings of DAGM04 Annual Pattern Recognition Symposium (2004)
Wang, L., Khan, L.: Automatic image annotation and retrieval using weighted feature selection. Multimedia Tools Appl. 29(1), 55–71 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pitel, G., Millet, C., Grefenstette, G. (2007). Deriving a Priori Co-occurrence Probability Estimates for Object Recognition from Social Networks and Text Processing. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76856-2_50
Download citation
DOI: https://doi.org/10.1007/978-3-540-76856-2_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76855-5
Online ISBN: 978-3-540-76856-2
eBook Packages: Computer ScienceComputer Science (R0)