Abstract
In this paper, the similarity measurement issue, in the context of texture images comparison, is tackled from a geometrical point of view by computing the Rao Geodesic distance on the Generalized Gamma distributions (G\(\Gamma \)D) manifold. This latter permits a generic and flexible characterization thanks to its three-parameters modeling. We take advantage of information geometry tools to consider the G\(\Gamma \)D as a geometrical manifold and thus to define the geodesic distance (GD) as a real and intuitive similarity measure rather than the purely statistical Kullback-Leibler divergence. However, the three-parameter space turns out to be cumbersome when it comes to solving the geodesic equations. This explains why the main studies that tried to solve this problem have been content to use mappings to some embedded submanifolds to modify and approximate the accurate geodesic model by computing geodesic distances only on integrable submanifolds. Our main contribution is to approximate the GD in a more general manner, i.e considering all cases of the manifold coordinates. We managed to derive a closed-form of the modified geodesic model on sub-manifolds when the shape parameters are fixed. In the case of the fixed scale parameters, the geodesic equations are solved and a numerical approximation is directly applied to derive the geodesic distance. When the three parameters are allowed to vary, we approximate the GD using two different ways. The first is treated by the mean of a polynomial approach, while the second is subject to a graph-based approach. The proposed approaches are evaluated considering the Content-Based Texture Retrieval (CBTR) application on three different databases (VisTex, Brodatz, and USPTex) in order to show their effectiveness over the state-of-the-art methods.
Similar content being viewed by others
References
Abbad, Z., Maliani, A.E., Ouatik, S., Hassouni, M.E.: Rao-geodesic distance on the generalized gamma manifold: Study of three sub-manifolds and application in the texture retrieval domain. Note Di Math. J. 37(suppl), 1 (2017)
Alli, H., Ucar, A., Demir, Y.: The solutions of vibration control problems using artificial neural networks. J. Franklin Inst. 340(5), 307–325 (2003)
Allili, M.S.: Wavelet modeling using finite mixtures of generalized gaussian distributions application to texture discrimination and retrieval. IEEE Trans. Image Process. 21(4), 1452–1464 (2012)
Attila, A.: On the geometry of generalized gaussian distributions. J. Multivar. Anal. 100(4), 777–793 (2009)
Basseville, M.: Distance measures for signal processing and pattern recognition. Signal Process. 18(4), 349–369 (1989)
Beidokhti, R.S., Malek, A.: Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques. J. Franklin Inst. 346(9), 898–913 (2009)
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by their probability distributions. Bul. Calcutta Math. Soc. 7(4), 401–406 (1943)
Brigant, A.L., Puechmorel, S.: Quantization and clustering on riemannian manifolds with an application to air traffic analysis. J. Multivar. Anal. 173, 685–703 (2019)
Brodatz, P.: Brodatz dataset (1966). http://www.ux.uis.no/~tranden/brodatz.html
Castaño-Moraga, C., Lenglet, C., Derichea, R., Ruiz-Alzola, J.: A riemannian approach to anisotropic filtering of tensor fields. Signal Proces. 87(2), 263–276 (2007)
Chen, Y., Georgiou, T.T., Pavon, M.: Optimal steering of a linear stochastic system to a final probability distribution—part iii. Proc. Cambridge Philos. Soc. 63(9), 3112–3118 (1925)
Chen, Y., Georgiou, T.T., Tannenbaum, A.: Optimal transport for gaussian mixture models. IEEE Access 7, 6269–6278 (2018)
Choy, S.K., Tong, C.S.: Statistical wavelet subband characterization based on generalized gamma density and its application in texture retrieval. IEEE Signal Process 19(2), 281–289 (2009)
Cohen, A.C., Whitten, B.J.: Parameter estimation in reliability and life span models. CRC Press,96,(1988)
Crane, K., Weischedel, C., Wardetzky, M.: Geodesics in heat: a new approach to computing distance based on heat flow. ACM Trans. Graph. 32(5), 1–11 (2013)
Csiszar, I.: I-divergence geometry of probability distributions and minimization problems. Ann. Prob. 3(1), 146–158 (1975)
DasGupta, A.: Probability for statistics and machine learning. Springer Texts. Statistics (2011)
Daubechies, I.: Orthonormal bases of compactly supported wavelets. Commun. Pure Appl. Math. 41, 909–996 (1988)
Daubechies, I.: Ten lectures on wavelets. SIAM, CBMS-NSF. In: Regional Conference Series in Applied Mathematics volume 61,(1992)
Delon, J., Desolneux, A.: A wasserstein-type distance in the space of gaussian mixture models. SIAM J. Imag. Sci. 13(2), 936–970 (2020)
Dijkstra, E.W.: A note on two problems in connexion with graphs. Numer. Math. 1(1), 269–271 (1959)
Do, M.N., Vetterli, M.: Wavelet-based texture retrieval using generalized gaussian density and kullback-leibler distance. IEEE Trans. Image Process. 11(2), 146–158 (2002)
Dodson, C.T.J., Galanis, G., Vassiliou, E.: Geometry in a Fréchet context: A projective limit approach. London Mathematical Society Lecture Note Series 428, Cambridge University Press, NY (2015)
Fisher, R.A.: Theory of statistical estimation. Proc. Cambridge Philos. Soc. 22(5), 700–725 (1925)
Fletcher, R.: Practical Methods of Optimization, vol. 2. John Wiley and Sons, New York (1987)
Floyd, R.W.: Algorithm 97: shortest path. Commun. ACM 5(6), 345 (1962)
Geert, V., Scheunders, P.: On the geometry of multivariate generalized gaussian models. J. Math. Imag. Vision 43(3), 180–193 (2012)
Gomes, O., Combes, C., Dussauchoy, A.: Four-parameter generalized gamma distribution used for stock return modeling. Presented at the (2006)
Hua, J., Lai, Z., Dong, M., Gu, X., Qin, H.: Geodesic distance weighted shape vector image diffusion. IEEE Trans. Visual. Comp. Graph. 14(6), 1643–1650 (2008)
Huot, E., Yahia, H., Cohen, I., Herlin, I.: Matching structures by computing minimal paths on a manifold. J. Visual Commun. Image Represent. 13(1–2), 302–312 (2002)
Ikonen, L.: Priority pixel queue algorithm for geodesic distance transforms. Image Vision Comput. 25(10), 1520–1529 (2007)
Johnson, D.B.: Efficient algorithms for shortest paths in sparse networks. J. ACM. 24(1), 1–13 (1977)
Kailath, T.: The divergence and bhattacharyya distance measures in signal selection. IEEE Trans. Commun. Technol. 15(1), 52–60 (1967)
Kimmel, R., Sethian, J.A.: Computing geodesic paths on manifolds. Proc. Nation. Acad. Sci 95(15), 431–8435 (2013)
Kullback, S.: Information theory and Statistics. Dover Publications, NY (1968)
Kwitt, R., Uhl, A.: Image similarity measurement by kullback-leibler divergences between complex wavelet subband statistics for texture retrieval. In: 15th IEEE International Conference on Image Processing. (2008)
Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans. Neural Netw. Arch. 9(5), 987–1000 (1998)
Li, L., Xu, C., Tang, W., Zhong, C.: 3d face recognition by constructing deformation invariant image. Pattern Recognition Letters 29(10), 1596–1602 (2008)
Malek, A., Beidokhti, R.S.: Numerical solution for high order differential equations using a hybrid neural network-optimization method. Appl. Math. Comput. 183(1), 260–271 (2006)
Maliani, A.D.E., Lasmar, N., Hassouni, M.E., Berthoumieu, Y.: Texture classification based on the generalized gamma distribution and the dual tree complex wavelet transform. In: 5th International Symposium On I/V Communications and Mobile Network (2010)
Mallat, S.: A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Patt. Anal. Mach. Intell. 11(7), 674–693 (1989)
Mathiassen, J.R., Skavhaug, A., Bo, K.: Texture similarity measure using kullback-leibler divergence between gamma distributions. In: Proceedings of the 7th European Conference on Computer Vision-Part III (ECCV’02), pp. 133–147, Springer (2002)
Mirebeau, J.M.: Anisotropic fast-marching on cartesian grids using lattice basis reduction. SIAM J. Numer. Anal. 52(4), 1573–1599 (2014)
MIT: Vision texture (2009). http://vismod.media.mit.edu/vismod/imagery/VisionTexture/
Mitchell, A.F.S., Krzanowski, W.: Rao’s distance measure. Indian J. Statist. 43(3), 345–365 (2002)
Murray, M.K., Rice, J.W.: Differential Geometry and Statistics. Chapman and Hall, NY (1993)
Nielsen, F.: Closed-form information-theoretic divergences for statistical mixtures. Pattern recognition (ICPR), In: 21st international conference on, IEEE, pp. 1723–1726 (2012)
Pastore, J.I., Moler, E.G., Ballarin, V.L.: Segmentation of brain magnetic resonance images through morphological operators and geodesic distance. Dig. Signal Proces. 15(2), 153–160 (2005)
Patil, M., TomarSetu, S.S., Chaturvedi, K.: Dual tree complex wavelet transform (dtcwt) based adaptive interpolation technique for enhancement of image resolution. Int. J. Comp. Appl. 80(14), 37–42 (2013)
Peter, A., Anand, R.: Shape analysis using the fisher-rao riemannian metric: Unifying shape representation and deformation. In: 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, pp. 1164–1167 (2006)
Raj, V.N.P., Venkateswarlu, T.: Denoising of medical images using dual tree complex wavelet transform. In: 2nd International Conference on Computer, Communication, Control and Information Technology, vol. 4, pp. 238–244 (2012)
Rami, H., Belmerhnia, L., Maliani, A.D.E., Hassouni, M.E.: Texture retrieval using mixtures of generalized gaussian distribution and cauchy-schwarz divergence in wavelet domain. Signal Process. Image Commun. 42, 45–58 (2016)
Ramos, P.L., Louzada, F.: A modified reference prior for the generalized gamma distribution, p. (2014). arXiv:1412.5843v1
Rao, C.R.: Information and the accuracy attainable in the estimation of statistical parameters. Breakthroughs. Statistics 1, 235–247 (2012)
Rebbah, S., Nicol, F., Puechmorel, S.: The geometry of the generalized gamma manifold and an application to medical imaging. J. Math. 7(8), 674–689 (2019)
Rioul, O., Vetterli, M.: Wavelets and signal processing. IEEE Signal Process. Mag. 8(4), 14–38 (1991)
Salem, S., Bombrun, L., Berthoumieu, Y.: New riemannian priors on the univariate normal model. Entropy J. 16, 4015–4031 (2014)
Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Proc. National Acad. Sci. 93(4), 1591–1595 (1996)
Shin, J.W., Chang, J.H., Kim, N.S.: Statistical modeling of speech signals based on generalized gamma distribution. IEEE Signal Process 12(3), 258–261 (2005)
Shun-chi, A.: Methods of information geometry. OXFORD University Press, NY (1993)
Shun-chi, A.: Information geometry and its applications, 1st edn. Springer, Tokyo (2016)
Simo-Serra, E., Torras, C., Moreno-Noguer, F.: Geodesic finite mixture models. In: British Machine Vision Conference (BMVC), BMVA Press (2014)
Song, K.S.: Globally convergent algorithms for estimating generalized gamma distributions in fast signal and image processing. IEEE Trans. Image Process. 17(8), 1233–1250 (2008)
Stacy, E.W.: A generalization of the gamma distribution. Ann. Math. Statist. 33(3), 1187–1192 (1962)
Stacy, E.W.: Quasimaximum likelihood estimators for two-parameter gamma distributions. IBM J. Res. Dev. 17, 115–124 (1973)
Stacy, E.W., Mihram, G.A.: Parameter estimation for a generalized gamma distribution. Technometrics 7, 349–358 (1965)
Torres, J.N., Gambini, J., Frery, A.C.: The geodesic distance between g(1, 0) models and its dpplication to degion discrimination. IEEE J. Select. Topics Appl. Earth Observ. Remote Sens. 10(3), 987–997 (2017)
Twining, C., Marsland, S.: Constructing an atlas for the diffeomorphism group of a compact manifold with boundary, with application to the analysis of image registrations. J. Comput. Appl. Math. 222(2), 411–428 (2008)
USPtex: Usptex dataset (2012). http://fractal.ifsc.usp.br/dataset/USPtex.php
Wingo, D.R.: Computing maximum-likelihood parameter estimates of the generalized gamma distribution by numerical root isolation. IEEE Trans. Rel., vol. R-36, no. 5, pp. 586–590 (1987)
Author information
Authors and Affiliations
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
The Christoffel symbols \(\Gamma _{ij}^{k}\) associated with the G\(\Gamma \)D manifold throughout the Fisher-Rao metric are highly nonlinear and cannot be simplified, so we will limit ourselves to the seventeen Christoffel symbols that are used in the geodesic equations. For the simplicity of the expressions of the Christoffel symbols, we will define them by:
Where:
Where \(\psi ^{(m)}(x) = \frac{d^{(m)}}{dx^{m}} \psi (x)\) is the polygamma function and \(\psi ^{(0)}(x)\) is the digamma function.
The expressions of Christoffel symbols \(\Gamma _{ij}^{k}\) associated with the submanifold defined by fixed scale parameter are defined by:
Where:
Rights and permissions
About this article
Cite this article
Abbad, Z., Maliani, A.D.E., Alaoui, S.O.E. et al. The Geodesic Distance on the Generalized Gamma Manifold for Texture Image Retrieval. J Math Imaging Vis 64, 243–260 (2022). https://doi.org/10.1007/s10851-021-01063-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-021-01063-x