Abstract
Object discovery is one of the most important applications of unsupervised learning. This paper addresses several spectral clustering techniques to attain a categorization of objects in images without additional information such as class labels or scene descriptions. Due to the fact that background textures bias the performance of image categorization methods, a generic object detector based on some general requirements on objects is applied. The object detector provides rectangular regions of interest (ROIs) as object hypotheses independent of the underlying object class. Feature extraction is simply constrained to these bounding boxes to decrease the influence of background clutter. Another aspect of this work is the utilization of a Gaussian mixture model (GMM) instead of k-means as usually used after feature transformation in spectral clustering. Several experiments have been done and the combination of spectral clustering techniques with the object detector is compared to the standard approach of computing features of the whole image.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Recommended for submission to YRF2011 by Prof. Dr.-Ing. Joachim Denzler.
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
Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: CVPR, pp. 73–80 (2010)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)
Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR, pp. 401–408 (2007)
Jenssen, R.: Kernel entropy component analysis. TPAMI 32(5), 847–860 (2010)
von Luxburg, U.: A tutorial on spectral clustering. Statistics and Computing 17(4), 395–416 (2007)
Meila, M., Shi, J.: Learning segmentation by random walks. In: NIPS, pp. 873–879 (2000)
Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS, pp. 849–856 (2001)
Renyi, A.: On measures of entropy and information. In: Proceedings of the Berkeley Symposium on Mathematics, Statistics and Probability, vol. 1, pp. 547–561 (1960)
Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR, pp. 1605–1614 (2006)
Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10(5), 1299–1319 (1998)
Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22(8), 888–905 (2000)
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: ICCV, pp. 370–377 (2005)
Sivic, J., Russell, B.C., Zisserman, A., Freeman, W.T., Efros, A.A.: Unsupervised discovery of visual object class hierarchies. In: CVPR, pp. 1–8 (2008)
Tuytelaars, T., Lampert, C.H., Blaschko, M.B., Buntine, W.: Unsupervised object discovery: A comparison. IJCV 88(2), 284–302 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bodesheim, P. (2011). Spectral Clustering of ROIs for Object Discovery. In: Mester, R., Felsberg, M. (eds) Pattern Recognition. DAGM 2011. Lecture Notes in Computer Science, vol 6835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23123-0_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-23123-0_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23122-3
Online ISBN: 978-3-642-23123-0
eBook Packages: Computer ScienceComputer Science (R0)