When the a contrario approach becomes generative

详细信息    查看全文

• 作者：Agnès Desolneux
• 关键词：Detection theory ; Non ; accidentalness principle ; Maximum entropy distributions ; Clusters of points ; Line segments detection ; Image reconstruction ; Visual information theory
• 刊名：International Journal of Computer Vision
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：116
• 期：1
• 页码：46-65
• 全文大小：8,628 KB
• 参考文献：Abraham, I., Abraham, R., Desolneux, A., & Li-Thiao-Té, S. (2007). Significant edges in the case of non-stationary Gaussian noise. Pattern Recognition, 40(11), 3277–3291.CrossRef MATH
  Ayer, M., Brunk, H., Ewing, G., Reid, W., & Silverman, E. (1955). An empirical distribution function for sampling with incomplete information. Annals of Mathematical Statistics, 26(4), 641–647.MathSciNet CrossRef MATH
  Blusseau, S., Lezama, J., Grompone von Gioi, R., Morel, J.M. & Randall, G. (2012). Comparing human and machine detection thresholds: An a-contrario model for non accidentalness. In: European Conference on Visual Perception.
  Cao, F. (2004). Application of the Gestalt principles to the detection of good continuations and corners in image level lines. Computing and Visualisation in Science. Special Issue, Proceeding of the Algoritmy 2002 Conference 7, 3–13 (2004).
  Cao, F., Delon, J., Desolneux, A., Musé, P., & Sur, F. (2007). A unified framework for detecting groups and application to shape recognition. Journal of Mathematical Imaging and Vision, 27(2), 91–119.MathSciNet CrossRef MATH
  Cover, T., & Thomas, J. (1991). Elements of information theory. New York: Wiley.CrossRef MATH
  Delon, J., Desolneux, A., Lisani, J. L., & Petro, A. B. (2007). Automatic color palette. Inverse Problems and Imaging, 1(2), 265–287.MathSciNet CrossRef MATH
  Delon, J., Desolneux, A., Lisani, J. L., & Petro, A. B. (2007). A non parametric approach for histogram segmentation. IEEE Transactions on Image Processing, 16(1), 253–261.MathSciNet CrossRef
  Desolneux, A., Moisan, L., & Morel, J. M. (2000). Meaningful alignments. International Journal of Computer Vision, 40(1), 7–23.CrossRef MATH
  Desolneux, A., Moisan, L., & Morel, J. M. (2001). Edge detection by Helmholtz principle. Journal of Mathematical Imaging and Vision, 14(3), 271–284.CrossRef MATH
  Desolneux, A., Moisan, L., & Morel, J. M. (2003). Computational Gestalts and perception thresholds. Journal of Physiology, 97(2–3), 311–324.
  Desolneux, A., Moisan, L., & Morel, J. M. (2003). A grouping principle and four applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(4), 508–513.CrossRef
  Desolneux, A., Moisan, L., & Morel, J. M. (2003). Maximal meaningful events and applications to image analysis. Annals of Statistics, 31(6), 1822–1851.MathSciNet CrossRef MATH
  Desolneux, A., Moisan, L., & Morel, J. M. (2008). From gestalt theory to image analysis: A probabilistic approach. Heidelberg: Springer.CrossRef
  von Gioi, R. G., Jakubowicz, J., Morel, J. M., & Randall, G. (2010). LSD: A fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis, 32(4), 722–732.CrossRef
  von Gioi, R. G., Jakubowicz, J., Morel, J. M., & Randall, G. (2012). LSD: A line segment detector. Image Processing on Line, 2, 35–55. doi:10.​5201/​ipol.​2012.​gjmr-lsd .CrossRef
  Grosjean, B., & Moisan, L. (2009). A-contrario detectability of spots in textured backgrounds. Journal of Mathematical Imaging and Vision, 33(3), 313–337.MathSciNet CrossRef
  Harremoës, P. (2001). Binomial and Poisson distributions as maximum entropy distributions. IEEE Transactions on Information Theory, 47(5), 2039–2041.CrossRef MATH
  von Helmholtz, H. (1999). Treatise on physiological optics. Bristol: Thoemmes Press.
  Igual, L., Preciozzi, J., Garrido, L., Almansa, A., Caselles, V., & Rougé, B. (2007). Automatic low baseline stereo in urban areas. Inverse Problems and Imaging, 1(2), 319–348.MathSciNet CrossRef MATH
  Kaas, R., & Buhrman, J. (1980). Mean, median and mode in binomial distributions. Statistica Neerlandica, 34, 13–18.MathSciNet CrossRef MATH
  Kato, H. & Harada, T. (2014). Image reconstruction from bag-of-visual-words. 2014 IEEE Conference on Computer Vision and Pattern Recognition (pp. 955–962). CVPR 2014, Columbus, OH, USA.
  Lezama, J., Blusseau, S., Morel, J. M., Randall, G., & von Gioi, R. G. (2014). Psychophysics, gestalts and games. In G. Citti & A. Sarti (Eds.), Neuromathematics of vision (pp. 217–242)., Lecture Notes in Morphogenesis Berlin: Springer.
  Lowe, D. (1985). Perceptual organization and visual recognition. Amsterdam: Kluwer Academic Publishers.CrossRef
  Lowe, D. (1990). Visual recognition as probabilistic inference from spatial relations. In A. Blake & T. Troscianko (Eds.), AI and the eye (pp. 261–2793). London: Wiley.
  Moisan, L., & Stival, B. (2004). A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix. International Journal of Computer Vision, 57(3), 201–218.CrossRef
  Mumford, D., & Desolneux, A. (2010). Pattern theory : The stochastic analysis of real-world signals. Boca Raton: AK Peters—CRC Press.
  Musé, P., Sur, F., Cao, F., Gousseau, Y., & Morel, J. M. (2006). An a contrario decision method for shape element recognition. International Journal of Computer Vision, 69(3), 295–315.CrossRef
  Myaskouvskey, A., Gousseau, Y., & Lindenbaum, M. (2013). Beyond independence: An extension of the a contrario decision procedure. International Journal of Computer Vision, 101(1), 22–44.MathSciNet CrossRef MATH
  Payton, M., Young, L., & Young, J. (1989). Bounds for the difference between median and mean of beta and negative binomial distributions. Metrika, 36, 347–354.MathSciNet CrossRef MATH
  Pérez, P., Gangnet, M., & Blake, A. (2003). Poisson image editing. ACM Transactions on Graphics (SIGGRAPH’03), 22(3), 313–318.CrossRef
  Veit, T., Cao, F., & Bouthemy, P. (2006). An a contrario decision framework for region-based motion detection. International Journal on Computer Vision, 68(2), 163–178.CrossRef
  Waterhouse, W. C. (1983). Do symmetric problems have symmetric solutions? The American Mathematical Monthly, 90(6), 378–387.MathSciNet CrossRef MATH
  Weinzaepfel, P., Jegou, H. & Pérez, P. (2011). Reconstructing an image from its local descriptors. In: The 24th IEEE Conference on Computer Vision and Pattern Recognition (pp. 337–344). CVPR 2011, Colorado Springs, CO, USA.
  Witkin, A., & Tenenbaum, J. (1983). On the role of structure in vision. In A. Rosenfeld (Ed.), Human and Machine Vision (pp. 481–543). New York: Academic Press.
  Zhu, S. C. (1999). Embedding gestalt laws in Markov random fields. IEEE Transactions on pattern analysis and machine intelligence, 21(11), 1170–1187.CrossRef
  Zhu, S. C., Wu, Y. N., & Mumford, D. (1997). Minimax entropy principle and its application to texture modeling. Neural Computation, 9(8), 1627–1660.CrossRef
  Zhu, S. C., Wu, Y. N., & Mumford, D. (1998). Filters, random fields and maximum entropy (frame): Towards a unified theory for texture modeling. International Journal of Computer Vision, 27(2), 107–126.CrossRef
  
• 作者单位：Agnès Desolneux (1)
  
  1. CNRS and CMLA, Ecole Normale Supérieure de Cachan, 61 avenue du Président Wilson, 94235, Cachan cedex, France
  
• 刊物类别：Computer Science
• 刊物主题：Computer Imaging, Vision, Pattern Recognition and Graphics
  Artificial Intelligence and Robotics
  Image Processing and Computer Vision
  Pattern Recognition
  
• 出版者：Springer Netherlands
• ISSN：1573-1405

文摘

The a contrario approach is a statistical, hypothesis testing based approach to detect geometric meaningful events in images. The general methodology consists in computing the probability of an observed geometric event under a noise model (null hypothesis) \(H_0\) and then declare the event meaningful when this probability is small enough. Generally, the noise model is taken to be the independent uniform distribution on the considered elements. Our aim in this paper will be to question the choice of the noise model: What happens if we “enrich” the noise model? How to characterize the noise models such that there are no meaningful events against them? Among them, what is the one that has maximum entropy? What does a sample of it look like? How is this noise model related to probability distributions on the elements that would produce, with high probability, the same detections? All these questions will be formalized and answered in two different frameworks: the detection of clusters in a set of points and the detection of line segments in an image. The general idea is to capture the perceptual information contained in an image, and then generate new images having the same visual content. We believe that such a generative approach can have applications for instance in image compression or for clutter removal. Keywords Detection theory Non-accidentalness principle Maximum entropy distributions Clusters of points Line segments detection Image reconstruction Visual information theory