×

Fourier descriptors based on the structure of the human primary visual cortex with applications to object recognition. (English) Zbl 1425.68365

Summary: In this paper, we propose a supervised object recognition method using new global features and inspired by the model of the human primary visual cortex V1 as the semidiscrete roto-translation group \(\mathrm{SE}(2,N) = {\mathbb {Z}}_N\rtimes {\mathbb {R}}^2\). The proposed technique is based on generalized Fourier descriptors on the latter group, which are invariant to natural geometric transformations (rotations, translations). These descriptors are then used to feed an SVM classifier. We have tested our method against the COIL-100 image database and the ORL face database, and compared it with other techniques based on traditional descriptors, global and local. The obtained results have shown that our approach looks extremely efficient and stable to noise, in presence of which it outperforms the other techniques analyzed in the paper.

MSC:

68T10 Pattern recognition, speech recognition
43A30 Fourier and Fourier-Stieltjes transforms on nonabelian groups and on semigroups, etc.
68T05 Learning and adaptive systems in artificial intelligence
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Barut, A., Raçzka, R.: Theory of Group Representations and Applications. World Scientific, Singapore (1977) · Zbl 0471.22021
[2] Bay, H.; Tuytelaars, T.; Van Gool, L., Surf: speeded up robust features, 404-417 (2006), Heidelberg · doi:10.1007/11744023_32
[3] Boscain, U., Duplaix, J., Gauthier, J.P., Rossi, F.: Anthropomorphic image reconstruction via hypoelliptic diffusion. SIAM J. Control Optim. 50, 1-25 (2012) · Zbl 1259.94011 · doi:10.1137/11082405X
[4] Boscain, U., Chertovskih, R., Gauthier, J.P., Remizov, A.: Hypoelliptic diffusion and human vision: a semi-discrete new twist on the petitot theory. SIAM J. Imaging Sci. 7(2), 669-695 (2014a) · Zbl 1343.94002 · doi:10.1137/130924731
[5] Boscain, U., Gauthier, J.P., Prandi, D., Remizov, A.: Image reconstruction via non-isotropic diffusion in Dubins/Reed-Shepp-like control systems. In: 53rd IEEE Conference on Decision and Control, pp. 4278-4283 (2014b) · Zbl 1255.68174
[6] Bressloff, P., Cowan, J., Golubitsky, M., Thomas, P., Wiener, M.: Geometric visual hallucinations, euclidean symmetry and the functional architecture of striate cortex. Philos. Trans. R. Soc. Lond. Ser. B Biol. Sci. 356, 299-330 (2001) · doi:10.1098/rstb.2000.0769
[7] Choksuriwong, A., Emile, B., Rosenberger, C., Lauren, H.: Comparative study of global invariant descriptors for object recognition. J. Electron. Imaging 17, 1-35 (2008)
[8] Chong, C., Raveendran, P., Mukundan, R.: A comparative analysis of algorithms for fast computation of Zernike moments. Pattern Recogn. 36(3), 731-742 (2003a) · Zbl 1028.68142 · doi:10.1016/S0031-3203(02)00091-2
[9] Chong, C.W., Raveendran, P., Mukundan, R.: Translation invariants of zernike moments. Pattern Recogn. 36(8), 1765-1773 (2003b) · Zbl 1055.68135 · doi:10.1016/S0031-3203(02)00353-9
[10] Chou, J., O’Neill, W., Cheng, H.: Pavement distress classification using neural networks. In: 1994 IEEE International Conference on Systems, Man, and Cybernetics, 1994. Humans, Information and Technology, vol. 1, pp. 397-401. doi:10.1109/ICSMC.1994.399871 (1994)
[11] Citti, G., Sarti, A.: A cortical based model of perceptual completion in the roto-translation space. Pattern Recogn. 24(3), 307-326 (2006) · Zbl 1088.92008
[12] Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005, IEEE, vol. 1, pp. 886-893 (2005) · Zbl 1372.94086
[13] Derrode, S., Ghorbel, F.: Robust and efficient fourier-mellin transform approximations for invariant grey-level image description and reconstruction. Comput. Vis. Image Underst. 83(1), 57-78 (2001) · Zbl 0972.68561 · doi:10.1006/cviu.2001.0922
[14] Dubnov, S., Tishby, N., Cohen, D.: Polyspectra as measures of sound texture and timbre. Comput. Vis. Image Underst. 26(4), 277-314 (1997)
[15] Duits, R., Franken, E.: Left-invariant parabolic evolutions on SE(2) and contour enhancement via invertible orientation scores. Part I: Linear left-invariant diffusion equations on SE(2). Q. Appl. Math. 68, 255-292 (2010) · Zbl 1202.35334 · doi:10.1090/S0033-569X-10-01172-0
[16] Duits, R., Franken, E.: Left-invariant parabolic evolutions on SE(2) and contour enhancement via invertible orientation scores. Part II: Nonlinear left-invariant diffusions on invertible orientation scores. Q. Appl. Math. 68, 1-38 (2010) · Zbl 1205.35326
[17] Führ, H., Mayer, M.: Continuous wavelet transforms from semidirect products : Cyclic representations and Plancherel measure. J. Fourier Anal. Appl. 8(4):1-23. http://www.springerlink.com/index/G7TC4AANGTUC4HXW.pdf, 0102002v1 (2002) · Zbl 1100.42030
[18] Galerne, B., Gousseau, Y., Morel, J.: Random phase textures: theory and synthesis. IEEE Trans. Image Process. 20(1), 257-267 (2011) · Zbl 1372.94086 · doi:10.1109/TIP.2010.2052822
[19] Granlund, G.H.: Fourier preprocessing for hand print character recognition. IEEE Trans. Image Process. C-21(2), 195-201 (1972) · Zbl 0232.68042
[20] Hewitt, E., Ross, K.: Abstract Harmonic Analysis—Volume 1. Springer, Berlin/New York (1963) · Zbl 0115.10603 · doi:10.1007/978-3-662-40409-6
[21] Hjelmas, E., Low, B.: Face detection: a survey. Comput. Vis. Image Underst. 83(3), 236-274 (2001) · Zbl 0999.68196 · doi:10.1006/cviu.2001.0921
[22] Hu, M.: Visual pattern recognition by moment invariants. Comput. Vis. Image Underst. 8(2), 179-187 (1962) · Zbl 0102.13304
[23] Hubel, D., Wiesel, T.: Receptive fields of single neurones in the cat’s striate cortex. Comput. Vis. Image Underst. 148, 574-591 (1959)
[24] Kakarala, R.: The bispectrum as a source of phase-sensitive invariants for fourier descriptors: a group-theoretic approach. Comput. Vis. Image Underst. 44(3), 341-353 (2012) · Zbl 1255.68174
[25] Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. IEEE, vol 2, p. II-506 (2004)
[26] Kuhl, F.P., Giardina, C.R.: Elliptic Fourier features of a closed contour. Comput. Vis. Image Underst. 18(3), 236-258 (1982)
[27] Lowe, D.: Distinctive image features from scale-invariant keypoints. Comput. Vis. Image Underst. 60(2), 91-110 (2004)
[28] Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. Comput. Vis. Image Underst. 27(10), 1615-1630 (2005)
[29] Milgram, J., Cheriet, M., Sabourin, R.: “One Against One” or “One Against All”: which one is better for handwriting recognition with SVMs? In: Lorette, G. (ed.) Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Suvisoft, La Baule. http://www.suvisoft.com (2006)
[30] Morel, J.M., Yu, G.: Asift: a new framework for fully affine invariant image comparison. Comput. Vis. Image Underst. 2(2), 438-469 (2009) · Zbl 1181.68252
[31] Nene, S.A., Nayar, S.K., Murase, H., et al.: Columbia object image library (coil-20). Tech. rep., technical report CUCS-005-96 (1996)
[32] Petitot, J.: Neurogéométrie de la vision - Modèles mathématiques et physiques des architectures fonctionnelles. Les Éditions de l’École Polytechnique (2008)
[33] Prandi, D., Boscain, U., Gauthier, J.P.: Image processing in the semidiscrete group of rototranslations. In: To appear in the Proceedings of the 2nd Conference on Geometric Science of Information (2015) · Zbl 1406.94005
[34] Raja, D.M.S., Shanmugam, A.: Artificial neural networks based war scene classification using invariant moments and glcm features: A comparative study. Int. J. Eng. Sci. Technol. 3(2), 1189-1195 (2011)
[35] Rajasekaran, S., Pai, G.V.: Image recognition using simplified fuzzy artmap augmented with a moment based feature extractor. Int. J. Pattern Recognit. Artif. Intell. 14(08), 1081-1095 (2000) · doi:10.1142/S0218001400000684
[36] Samaria, F., Harter, A.: Parameterisation of a stochastic model for human face identification. In: Proceedings of the Second IEEE Workshop on Applications of Computer Vision, 1994, pp. 138-142 (1994)
[37] Sifre, L., Mallat, S.: Rotation, scaling and deformation invariant scattering for texture discrimination. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1233-1240. doi:10.1109/CVPR.2013.163 (2013) · Zbl 1343.94002
[38] Smach, F., Lemaître, C., Gauthier, J.P., Miteran, J., Atri, M.: Generalized Fourier descriptors with applications to objects recognition in SVM context. Int. J. Pattern Recognit. Artif. Intell. 30, 43-71 (2008)
[39] Vapnik, V.N., Vapnik, V.: Statistical Learning Theory, vol. 1. Wiley, New York (1998) · Zbl 0935.62007
[40] Zahn, C.T., Roskies, R.Z.: Fourier descriptors for plane closed curves. IEEE Trans. Comput. C-21(3), 269-281 (1972) · Zbl 0231.68042 · doi:10.1109/TC.1972.5008949
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.