Abstract
Generative models of images should take into account transformations of geometry and reflectance. Then, they can provide explanations of images that are factorized into intrinsic properties that are useful for subsequent tasks, such as object classification. It was previously shown how images and objects within images could be described as compositions of regions called structural elements or ‘stels’. In this way, transformations of the reflectance and illumination of object parts could be accounted for using a hidden variable that is used to ‘paint’ the same stel differently in different images. For example, the stel corresponding to the petals of a flower can be red in one image and yellow in another. Previous stel models have used a fixed number of stels per image and per image class. Here, we introduce a Bayesian stel model, the colour − invariant admixture (CIA) model, which can infer different numbers of stels for different object types, as appropriate. Results on Caltech101 images show that this method is capable of automatically selecting a number of stels that reflects the complexity of the object class and that these stels are useful for object recognition.
This is a preview of subscription content, log in via an institution to check access.
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
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. Journal of Machine Learning Research 3, 993–1022 (2003)
Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Recognition and Machine Intelligence 8(6), 679–698 (1986)
Cao, L., Li, F.-F.: Spatially coherent latent topic model for concurrent object segmentation and classification. In: Proceedings of the Eleventh IEEE International Conference on Computer Vision (2007)
Chang, C., Lin, C.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research 11, 625–660 (2010)
Frey, B.J., Jojic, N.: Estimating mixture models of images and inferring spatial transformations using the EM algorithm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 416–422 (1999)
Frey, B.J., Jojic, N.: Transformation-invariant clustering using the EM algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(1) (2003)
Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, pp. 1458–1465 (2005)
Grenander, U.: Lectures in Pattern Theory I, II and III: Pattern Analysis, Pattern Synthesis and Regular Structures. Springer, Berlin (1976-1981)
Hinton, G.E.: Connectionist learning procedures. Artificial Intelligence 40, 185–234 (1989)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Jojic, N., Caspi, Y.: Capturing image structure with probabilistic index maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–219 (2004)
Jojic, N., Frey, B.J.: Learning flexible sprites in video layers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2001)
Jojic, N., Perina, A., Cristani, M., Murino, V., Frey, B.J.: Stel component analysis: Modeling spatial correlations in image class structure. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2044–2051 (2009)
Jojic, N., Perina, A., Cristani, M., Murino, V., Frey, B.J.: Stel component analysis: Modeling spatial correlations in image class structure. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2044–2051 (2009)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2169–2178 (2006)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Li, F.-F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In: Proceedings of the IEEE CVPR Workshop on Generative Model Based Vision, p. 178 (2004)
Lowe, D.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision (1999)
Marr, D.: Vision: A computational investigation into human representation and processing of visual information. W. H. Freeman and Company, San Franciso (1982)
Mumford, D.: Neuronal architectures for pattern-theoretic problems. In: Koch, C., Davis, J. (eds.) Large-Scale Theories of the Cortex, pp. 125–152. MIT Press, Cambridge (1994)
Murphy, K.P.: Conjugate Bayesian analysis of the Gaussian distribution. Technical report. University of British Columbia (2007)
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)
Perina, A., Jojic, N., Castellani, U., Cristani, M., Murino, V.: Object Recognition with Hierarchical Stel Models. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 15–28. Springer, Heidelberg (2010)
Rifkin, R., Klautau, A.: In defense of one-vs-all classification. Journal of Machine Learning Research 5, 101–141 (2004)
Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. International Journal of Computer Vision 77, 157–173 (2008)
Serre, T., Oliva, A., Poggio, T.: A feedforward architecture accounts for rapid categorization. Proceedings of the National Academy of Sciences 104(15), 6424–6429 (2007)
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their locations in images. In: Proceedings of the Tenth IEEE International Conference on Computer Vision (2005)
Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Describing visual scenes using transformed object parts. International Journal of Computer Vision 77 (2008)
Teh, Y.W., Jordan, M.I., Beal, M.J., Blei, D.M.: Hierarchical Dirichlet processes. Journal of the American Statistical Association 101(476), 1566–1581 (2006)
Zhu, S.C., Mumford, D.: GRADE: Gibbs reaction and diffusion equations — a framework for pattern synthesis, image denoising, and removing clutter. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Berlin Heidelberg
About this chapter
Cite this chapter
Chua, J.C., Givoni, I.E., Adams, R.P., Frey, B.J. (2013). Bayesian Painting by Numbers: Flexible Priors for Colour-Invariant Object Recognition. In: Cipolla, R., Battiato, S., Farinella, G. (eds) Machine Learning for Computer Vision. Studies in Computational Intelligence, vol 411. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28661-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-28661-2_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28660-5
Online ISBN: 978-3-642-28661-2
eBook Packages: EngineeringEngineering (R0)