Abstract
This article introduces a segmentation method to automatically extract object parts from a reduced set of images. Given a database of objects and dividing all of them using local color histograms, we obtain an object part as the conjunction of the most similar ones. The similarity measure is obtained analyzing the behaviour of a local vector with respect to the whole object database. Furthermore, the proposed technique is able to associate an energy to each object part being possible to find the most discriminant object parts. We present the non-negative matrix factorization (NMF) technique to improve the internal data representation by compacting the original local histograms (50D instead of 512D). Moreover, the NMF based projected histograms only contain a few activated components and this fact improves the clustering results with respect to the use of the original local color histograms. We present a set of experimental results validating the use of the NMF in conjunction with the clustering technique.
This work is supported by Comissionat per a Universitats i Recerca de la Generalitat de Catalunya and Ministerio de Ciencia y Tecnología grant TIC2000-0399-C02-01.
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
Biederman, I.: Recognition-by-components: A theory of human understanding. Psychological Review 94(2) (1987) 115–147
Lee, D., Seung, H.: Learning the parts of objects by non-negative matrix factorization. Nature 401 (1999) 788–791
Ohba, K.: and Ikeuchi, K.: Detectability, uniqueness and reliability of eigen windows for stable verification of partially occluded objects. PAMI 19(9) (1997) 1043–1048
Pope, A.: Learning to recognize objects in images: acquiring and using probabilistic models of appearance. PhD. thesis, University of British Columbia (1995)
Shams, L.: Development of Visual Shape Primitives. PhD. thesis. University of Southern California (1999)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transaction on Pattern Analysis and Machine Intelligence 22(8) (2000) 888–905
Swain, M., Ballard, D.: Color indexing. IJCV 7(1) (1991) 11–32
Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Neuroscience 3(1) (1991) 71–86
M.Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. Proc. of 6th European Conference of Computer Vision (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guillamet, D., Vitrià, J. (2001). Unsupervised Learning of Part-Based Representations. In: Skarbek, W. (eds) Computer Analysis of Images and Patterns. CAIP 2001. Lecture Notes in Computer Science, vol 2124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44692-3_84
Download citation
DOI: https://doi.org/10.1007/3-540-44692-3_84
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42513-7
Online ISBN: 978-3-540-44692-7
eBook Packages: Springer Book Archive