iccv iccv2013 iccv2013-388 iccv2013-388-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Kim Steenstrup Pedersen, Kristoffer Stensbo-Smidt, Andrew Zirm, Christian Igel
Abstract: A texture descriptor based on the shape index and the accompanying curvedness measure is proposed, and it is evaluated for the automated analysis of astronomical image data. A representative sample of images of low-redshift galaxies from the Sloan Digital Sky Survey (SDSS) serves as a testbed. The goal of applying texture descriptors to these data is to extract novel information about galaxies; information which is often lost in more traditional analysis. In this study, we build a regression model for predicting a spectroscopic quantity, the specific star-formation rate (sSFR). As texture features we consider multi-scale gradient orientation histograms as well as multi-scale shape index histograms, which lead to a new descriptor. Our results show that we can successfully predict spectroscopic quantities from the texture in optical multi-band images. We successfully recover the observed bi-modal distribution of galaxies into quiescent and star-forming. The state-ofthe-art for predicting the sSFR is a color-based physical model. We significantly improve its accuracy by augmenting the model with texture information. This study is thefirst step towards enabling the quantification of physical galaxy properties from imaging data alone.
[1] http://www.gama-survey.org.
[2] http://www.sdss.org.
[3] R. G. Abraham, P. Nair, P. J. McCarthy, et al. The Gemini Deep Deep Survey. VIII. When Did Early-Type Galaxies Form? Astrophys. J., 669: 184–201, 2007.
[4] M. Banerji, O. Lahav, C. J. Lintott, et al. Galaxy zoo: Reproducing galaxy mophologies via machine learning. MNRAS, 406:342–353, 2010.
[5] P. L. Bartlett. The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE T Inform Theory, 44(2):525–536, 1998.
[6] E. Bertin and S. Arnouts. SExtractor: Software for source extraction. Astron. Astrophys. Supp. , 117:393–404, 1996.
[7] M. R. Blanton and J. Moustakas. Physical Properties and Environments of Nearby Galaxies. Ann. Rev. Astron. Astrophys., 47: 159, 2009.
[8] M. R. Blanton, D. J. Schlegel, M. A. Strauss, et al. New York University Value-Added Galaxy Catalog: A Galaxy Catalog Based on New Public Surveys. Astron. J., 129:2562, 2005.
[9] S. Bridle, S. T. Balan, M. Bethge, et al. Results of the GREAT08 challenge: An image analysis competition for cosmological lensing. MNRAS, 405(3):2044–2061, 2010.
[10] J. Brinchmann. Private communication.
[11] J. Brinchmann, S. Charlot, S. D. M. White, et al. The physical properties of star-forming galaxies in the low-redshift Universe. MNRAS, 351:1 151, 2004.
[12] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, volume 1, pages 886–893, 2005.
[13] S. P. Driver, D. T. Hill, L. S. Kelvin, et al. Galaxy and Mass Assembly (GAMA): survey diagnostics and core data release. MNRAS, 413:971, 2011.
[14] G. Fasano, E. Vanzella, A. Dressler, et al. Morphology of galaxies in the WINGS clusters. MNRAS, 420(2):926–948, 2012.
[15] A. Gallazzi, J. Brinchmann, S. Charlot, et al. A census of metals and baryons in stars in the local Universe. MNRAS, 383: 1439–1458, 2008.
[16] A. Gallazzi, S. Charlot, J. Brinchmann, et al. The ages and metallicities of galaxies in the local universe. MNRAS, 362:41–58, 2005.
[17] T. J. Hastie and R. J. Tibshirani. Generalized Additive Models. Chapman & Hall, 1990.
[18] C. Igel, T. Glasmachers, and V. Heidrich-Meisner. Shark. JMLR, 9:993–996, 2008.
[19] C. Igel and M. H ¨usken. Empirical evaluation of the improved Rprop learning algorithm. Neurocomputing, 50(C): 105–123, 2003.
[20] J. J. Koenderink. The structure of images. Biol. Cybern., 50:363–370, 1984.
[21] J. J. Koenderink and A. J. van Doorn. Surface shape and curvature scale. Image Vision Comput., 10(8):557–564, 1992.
[22] J. J. Koenderink and A. J. van Doorn. The structure of locally orderless images. IJCV, 31(2/3):159–168, 1999.
[23] J. J. Koenderink and A. J. van Doorn. Local structure of Gaussian texture. IEICE Trans Inf Syst, E86-D(7):1 165– 1171, 2003.
[24] A. B. L. Larsen, S. Darkner, A. L. Dahl, and K. S. Pedersen. Jet-based local image descriptors. In ECCV 2012, volume LNCS 7574, pages 638–650. Springer, 2012.
[25] T. Leung and J. Malik. Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV, 43(1):29–44, 2001.
[26] D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91–1 10, 2004.
[27] C. E. Rasmussen and C. K. I. Williams. Gaussian Processes for Machine Learning. The MIT Press, 2005.
[28] S. Salim, R. M. Rich, S. Charlot, et al. UV Star Formation Rates in the Local Universe. Astrophys. J. Suppl. Ser., 173:267–292, 2007.
[29] B. M. ter Haar Romeny. Front-End Vision and Multi-Scale Image Analysis. Kluwer Academic Publishers, 2003.
[30] E. Tola, V. Lepetit, and P. Fua. DAISY: An efficient dense descriptor applied to wide-baseline stereo. IEEE TPAMI, 32(5):815–830, 2009. [3 1] M. Varma and A. Zisserman. A statistical approach to texture classification from single images. IJCV, 62(1/2):61–81, 2005.
[32] S. C. Zhu, Y. N. Wu, and D. Mumford. Filters, random fields, and maximum entropy (frame): Towards a unified theory for texture modeling. IJCV, 27(2): 107–126, 1998. 22444477