Abstract
In this article, we suggest a new approach for classification and Recognition of 3D image Gaussian–Hermite moments using a Multilayer Perceptron architecture. The Multilayer Perceptron is an artificial neural network to evaluate the efficient structure in the non-linear systems. However, the determination of its architecture and weights is a fundamental issue due to their direct impact on the network convergence and performance. The robustness of the proposed approach have provided under many transforms. The experimental results show that our approaches are more robust than 3D Geometric moments.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
B. Yang and M. Dai, “Image analysis by Gaussian–Hermite moments,” Signal Process. 91 (10), 2290–2303 (2011).
M. El Mallahi, A. Mesbah, H. El Fadili, K. Zenkouar, and H. Qjidaa, “Compact computation of Tchebichef moments for 3D object representation,” WSEAS Trans. Circuits Syst. 13, 368–380 (2014).
M. El Mallahi, A. Mesbah, H. Qjidaa, K. Zenkouar, and H. El Fadili, “Translation and scale invariants of three-dimensional Tchebichef moments,” in 2015 Intelligent Systems and Computer Vision (ISCV’15) (Fez, Morocco, 2015), IEEE, pp. 1–5.
M. El Mallahi, A. Mesbah, H. Qjidaa, A. Berrahou, K. Zenkouar, and H. El Fadili, “Volumetric image reconstruction by 3D Hahn moments,” in Proc. 2015 IEEE/ACS 12th International Conference on Computer Systems and Applications (AICCSA) (Marrakech, Morocco, 2015), IEEE, pp. 1–8.
M. El Mallahi, A. Zouhri, A. Mesbah, and H. Qjidaa, “3D radial invariant of dual Hahn moments,” Neural Comput. Appl. 30 (7), 2283–2294 (2018).
A. Mesbah, M. El Mallahi, H. El Fadili, K. Zenkouar, A. Berrahou, and H. Qjidaa, “An algorithm for fast computation of 3D Krawtchouk moments for volumetric image reconstruction,” in Proc. Mediterranean Conference on Information & Communication Technologies 2015, MedCT 2015, Vol. 1, Ed. by A. El Oualkadi, F. Choubani, and A. El Moussati, Lecture Notes in Electrical Engineering (Springer, Cham, 2016), Vol. 380, pp. 267–276.
A. Mesbah, A. Berrahou, M. El Mallahi, and H. Qjidaa, “Fast algorithm for 3D local feature extraction using Hahn and Charlier moments,” in Advances in Ubiquitous Networking 2, Proc. UNet’16, Ed. by R. El-Azouzi, D. Menasche, E. Sabir, et al., Lecture Notes in Electrical Engineering (Springer, Singapore, 2017), Vol. 397, pp. 357–373.
A. Mesbah, A. Berrahou, M. El Mallahi, and H. Qjidaa, “Fast and efficient computation of three-dimensional Hahn moments,” J. Electron. Imaging 25 (6), 061621 (2016).
A. Mesbah, A. Zouhri, M. El Mallahi, K. Zenkouar, and H. Qjidaa, “Robust reconstruction and generalized dual Hahn moments invariants extraction for 3D images,” 3D Res. 8 (1), Article 7 (2017).
J. Flusser, T. Suk, and B. Zitová, Moments and Moment Invariants in Pattern Recognition (Wiley, Chichester, 2009).
M. El Mallahi, A. Zouhri, J EL-Mekkaoui, and H. Qjidaa, “Three dimensional radial Tchebichef moment invariants for volumetric image recognition,” Pattern Recogn. Image Anal. 27 (4), 810–824 (2017).
B. Xiao, Y. Zhang, L. Li, W. Li, and G. Wang, “Explicit Krawtchouk moment invariants for invariant image recognition,” J. Electron. Imaging 25 (2), 023002 (2016).
M. El Mallahi, A. Zouhri, A. Mesbah, A. Berrahou, I. El Affar, and H. Qjidaa, “Radial invariant of 2D and 3D Racah moments,” Multimed. Tools Appl. 77 (6), 6583–6604 (2018).
H.-S. Hsu and W.-H. Tsai, “Moment-preserving edge detection and its application to image data compression,” Opt. Eng. 32 (7), 1596–1608 (1993).
X.-Y. Wang, P.-P. Niu, H.-Y. Yang, C.-P. Wang, and A.-L. Wang, “A new robust color image watermarking using local quaternion exponent moments,” Inf. Sci. 277, 731–754 (2014).
M. El Mallahi, A. Zouhri, J. El-Mekkaoui, and H. Qjidaa, “Radial Meixner moments for rotational invariant pattern recognition,” in 2017 Intelligent Systems and Computer Vision (ISCV’17) (Fez, Morocco, 2017), IEEE, pp. 1–6.
F. Rosenblatt, The Perceptron: A Theory of Statistical Separability in Cognitive Systems (Project Para), Report No. VG-1196-G-1 (Cornell Aeronautical Laboratory, Buffalo, NY, 1958).
Y. Ghanou and G. Bencheikh, “Architecture optimization and training for the multilayer Perceptron using Ant system,” IAENG Int. J. Comput. Sci. 43 (1), 20–26 (2016).
M. El Mallahi, A. Zouhri, A. El Affar, A.Tahiri, and H. Qjidaa, “Radial Hahn moment invariants for 2D and 3D image recognition,” Int. J. Autom. Comput. 15 (3), 277–289 (2018).
M. El Mallahi, J. El Mekkaoui, A. Zouhri, H. Amakdouf, and H. Qjidaa, “Rotation scaling and translation invariants of 3D radial shifted Legendre moments,” Int. J. Autom. Comput. 15 (2), 169–180 (2018).
M. El Mallahi, A. Zouhri, and H. Qjidaa, “Radial Meixner moment invariants for 2D and 3D image recognition,” Pattern Recogn. Image Anal. 28 (2), 207–216 (2018).
A. Mesbah, M. El Mallahi, Z. Lakhili, H. Qjidaa, and A. Berrahou, “Fast and accurate algorithm for 3D local object reconstruction using Krawtchouk moments,” in Proc. 2016 5th Int. Conf. on Multimedia Computing and Systems (ICMCS) (Marrakech, Morocco, 2016), IEEE, pp. 1–6.
M. El Mallahi, A. Mesbah, H. Karmouni, A. El Affar, A. Tahiri, and H. Qjidaa, “Radial Charlier moment invariants for 2D object/image recognition,” in Proc. 2016 5th Int. Conf. on Multimedia Computing and Systems (ICMCS) (Marrakech, Morocco, 2016), IEEE, pp. 41–45.
M. El Mallahi, H. Amakdouf, A. Zouhri, and H. Qjidaa, “Rotation scaling and translation invariants of 3D radial shifted Legendre moments,” Int. J. Autom. Comput. 15 (2), 169–180 (2018).
M. El Mallahi, A. Zouhri, A. Mesbah, A. Berrahou, I. El Affar, and H. Qjidaa, “Radial invariant of 2D and 3D Racah moments,” Multimed. Tools Appl. 77 (6), 6583–6604 (2018).
H. Amakdouf, M. El Mallahi, A. Zouhri, A. Tahiri, and H. Qjidaa, “Classification and recognition of 3D image of Charlier moments using a Multilayer Perceptron architecture,” Procedia Comput. Sci. 127, 226–235 (2018).
H. Amakdouf, A. Zouhri, M. El Mallahi, A. Tahiri, and H. Qjidaa, “Translation scaling and rotation invariants of 3D Krawtchouk moments,” in Proc. 2018 Int. Conf. on Intelligent Systems and Computer Vision (ISCV2018) (Fez, Morocco, 2015), IEEE, pp. 1–6. https://doi.org/10.1109/ISACV.2018.8354059
McGill 3D Shape Benchmark (Shape Analysis Group, Centre for Intelligent Machines and School of Computer Science, McGill University, 2005). Available at: http://www.cim.mcgill.ca/~shape/benchMark/.
J. West, J. M. Fitzpatrick, M. Y. Wang, M., et al., “Comparison and evaluation of retrospective intermodality brain image registration techniques,” J. Comput. Assist. Tomogr. 21 (4), 554–566 (1997). https://doi.org/10.1097/00004728-199707000-00007
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Amal Zouhri received the B.Sc., M.Sc., and PhD degrees in electrical engineering from Faculty of Sciences, Sidi Mohammed Ben Abdellah University, Morocco in 2008, 2011, and 2017, respectively. Her research interests include embedded system, stability and stabilization of interconnected systems, decentralized systems.
Hicham Amakdouf received the B.Sc., M.Sc. degrees in computer sciences from Faculty of Sciences, Sidi Mohammed Ben Abdellah University, Morocco in 2003 and 2007, respectively. He is presently a PhD degree candidate in computer science at the Faculty of Sciences, Sidi Mohammed Ben Abdellah University, Morocco. His research interests include image processing, computer graphics, artificial intelligence, and geographic information systems.
Mostafa El Mallahi received the B.Sc., M.Sc., and PhD degrees in computer science from Faculty of Sciences, University Sidi Mohammed Ben Abdellah, Morocco in 2000, 2007, and 2017, respectively. His research interests include image processing, pattern classification, orthogonal systems, neural networks, big data, data mining, data science, deep learning, genetic algorithms, and special functions.
Ahmed Tahiri received the graduate degree DES in Department of Physics, Sidi Mohammed Ben Abdellah University, Morocco in 1997, received the PhD degree in physics and environment from the University Sidi Mohamed Ben Abdellah, Faculty of Science, Morocco in 2005. He completed his doctoral studies in didactics of science in the University of Sherbrooke in Canada in 2009. He is now a professor in Superior Normal School, ENS-FEZ, Morocco. His research interests include image processing, didactics of scientific disciplines, and environmental education.
Zakia Lakhliai rеcеivеd thе PhD dеgrее in physics from thе Univеrsity of Montpеlliеr II, Francе, in 1987, and thе Statе Doctor’s dеgrее from thе Univеrsity of Fеs, Morocco, in 1996. Shе is currently a mеmbеr of Lab of computering and intеrdisciplinary physics (L.I.P.I.), at (Е.N.S.F.), and a Professor in thе Superior School of technology (Е.S.T.F.) at Sidi Mohammed Ben Abdellah Univеrsity (USMBA), Fez, Morocco. Hеr current research intеrеsts include signal and imagе procеssing, indеxation of old manuscripts.
Driss Chenouni received the PhD degree in physics from the University of Montpellier II, France, in 1989, and the State Doctor’s degree from the University of Fes, Morocco, in 1996. He is currently a Lab director of computering and interdisciplinary physics (L.I.P.I.), at (E.N.S.F.), and a Director of the Ecole Normale Supérieur at Sidi Mohammed Ben Abdellah University (USMBA), Fez, Morocco. His current research interests include multi-agent systems, enterprise architecture, modeling, Web services, autonomic computing, image processing, and indexation of old manuscripts.
Hassan Qjidaa received the M.Sc. and PhD degrees in physics from Claud Bernard University of Lyon, France in 1983 and 1987, respectively. He is a full professor of electrical engineering at the Faculty of Sciences, Sidi Mohammed Ben Abdellah University, Morocco 1999. He is now a professor in Sidi Mohammed Ben Abdellah University, Morocco. His research interests include classification, image processing, pattern recognition, orthogonal systems, neural networks, deep learning and data science, big data, genetic algorithms, and special functions.
Rights and permissions
About this article
Cite this article
Zouhri, A., Amakdouf, H., El Mallahi, M. et al. Invariant Gaussian–Hermite Moments Based Neural Networks for 3D Object Classification. Pattern Recognit. Image Anal. 30, 87–96 (2020). https://doi.org/10.1134/S1054661820010186
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661820010186