Abstract
With the rapid development of 3D technology, 3D object classification has recently become a popular research topic in computer graphics and pattern recognition. Analyzing the shape of 3D models has become a common concern for researchers. A crucial technique for analyzing these 3D shapes is to capture features from 3D models that can sufficiently distinguish their shapes. While the 3D discrete orthogonal moments are powerful for the analysis and representation of 3D objects. It was proved that they have a better feature representation capability than the continuous orthogonal moments. This paper presents a new model for 3D shape classification named 3D Hahn moments neural networks (3DHMNNs) to improve the classification accuracy and decrease the computational complexity of 3D pattern recognition process. The proposed model is derived by introducing 3D Hahn moments as an input layer in neural network, largely utilized in various applications related to the pattern recognition. In fact, the advantages of image moments, especially discrete orthogonal moments have the property to extract relevant features from an object in lower orders and their robustness against image noise. Along with the efficiency of the neural networks, we can construct the proposed robust model. The main purpose of this work is to investigate the classification capabilities of the proposed model on rigid and non-rigid 3D shape datasets. The experiment simulations are conducted on the Articulated of McGill Princeton Shape Benchmark (PSB), SHREC’2011, ModelNet10 and ModelNet40 databases to assess the effectiveness of our proposed model. Two structures of the proposed model are constructed as noted 3DHMNNs6 layers and 3DHMNNs7 layers. The obtained results indicate that the proposed model provide a reasonable performance in terms of classification accuracy by achieving 90.96% on ModelNet10, 83.87% on ModelNet40, 97.66% on SHREC’2011 and over 90.16% on Articulated McGill outperforming other existing methods as well as being more robust under noisy conditions.
Similar content being viewed by others
References
Alzubi, J., Nayyar, A., Kumar A (2018) Machine learning from theory to algorithms: an overview. In journal of physics: conference series (Vol. 1142, no. 1, p. 012012). IOP publishing.
Arora S, Gupta A, Jain R, & Nayyar A (2021) Optimization of the CNN model for hand sign language recognition using Adam optimization technique. In Micro-electronics and telecommunication engineering (pp. 89–104). Springer, Singapore
Batioua I, Benouini R, Zenkouar K, Zahi A (2017) 3D image analysis by separable discrete orthogonal moments based on Krawtchouk and Tchebichef polynomials. Pattern Recogn 71:264–277
Batioua I, Benouini R, Zenkouar K (2020) Image recognition using new set of separable three-dimensional discrete orthogonal moment invariants. Multimed Tools Appl 79(19):13217–13245
Benouini R, Batioua I, Zenkouar K, Najah S, Qjidaa H (2018) Efficient 3D object classification by using direct Krawtchouk moment invariants. Multimed Tools Appl 77(20):27517–27542
Bronstein AM, Bronstein MM, Guibas LJ, Ovsjanikov M (2011) Shape google: geometric words and expressions for invariant shape retrieval. ACM Transactions on Graphics (TOG) 30(1):1–20
Canterakis N (1999) 3D Zernike moments and Zernike affine invariants for 3D image analysis and recognition. In proceedings of the 11th Scandinavian conference on image analysis SCIA’99, DSAGM, pp 85-93
Chen DY, Tian XP, Shen YT, Ouhyoung M (2003) On visual similarity based 3d model retrieval. Computer Graphics Forum 22(3):223–232
Clevert DA, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (ELUS). In: conference ICLR. arXiv:1511.07289
Cyganski D, Orr JA (1988) Object recognition and orientation determination by tensor methods. JAI Press 3:101–144
El Alami A, Lakhili Z, Mesbah A, Berrahou A, Qjidaa H (2019) Color face recognition by using quaternion and deep neural networks. In: 2019 international conference on wireless technologies. Embedded and Intelligent Systems (WITS), IEEE, pp 1–5
Ezuz D, Solomon J, Kim VG, Ben-Chen M (2017) GWCNN: a metric alignment layer for deep shape analysis. Computer Graphics Forum 36(5):49–57
Feng Y, Feng Y, You H, Zhao X, Gao Y (2019) MeshNet: mesh neural network for 3D shape representation. in Proc AAAI Conf Artif Intell 33:8279–8286
Galvez JM, Canton M (1993) Normalization and shape recognition of three-dimensional objects by 3D moments. Pattern Recogn 26:667–681
Garcia-Garcia A, Gomez-Donoso F, Garcia-Rodriguez J, Orts-Escolano S, Cazorla M, Azorin-Lopez J (2016) Pointnet: a 3d convolutional neural network for real-time object class recognition. In 2016 international joint conference on neural networks (IJCNN) (pp. 1578-1584). IEEE.
Gu X, Wang Y, Chan TF, Thompson PM, Yau ST (2004) Genus zero surface conformal mapping and its application to brain surface mapping. IEEE Trans Med Imaging 23(8):949–958
Guo X (1993) Three dimensional moment invariants under rigid transformation. In: proceedings of the fifth international Conf Comput anal images patterns (CAIP’93). Springer, pp 518–522
Hamza AB (2016) A graph-theoretic approach to 3D shape classification. Neurocomputing 211:11–21
Hanocka R, Hertz A, Fish N, Giryes R, Fleishman S, Cohen-Or D (2019) Meshcnn: a network with an edge. ACM Transactions on Graphics (TOG) 38(4):1–12
Hoang L, Lee SH, Kwon OH, Kwon KR (2019) A deep learning method for 3D object classification using the wave kernel signature and a center point of the 3D-triangle mesh. Electronics 8(10):1196
Hu M-K (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8:179–187
Iscan Z, Dokur Z, Olmez T (2010) Tumor detection by using Zernike moments on segmented magnetic resonance brain images. Expert Syst Appl 37:2540–2549
Lakhili Z, El Alami A, Mesbah A, Berrahou A, Qjidaa H (2019) Deformable 3D shape classification using 3D Racah moments and deep neural networks. Procedia Comput Sci 148:12–20
Lakhili Z, El Alami A, Mesbah A, Berrahou A, Qjidaa H (2019) 3D shape classification using 3D discrete moments and deep neural networks. In proceedings of the 2nd international conference on networking, information systems & security, 1-6
Lakhili Z, El Alami A, Mesbah A, Berrahou A, Qjidaa H (2020) Robust classification of 3D objects using discrete orthogonal moments and deep neural networks. Multimed Tools Appl 79:1–25
Lakhili Z, El Alami A, Qjidaa H (2020) Enhancing the performance of grayscale image classification by 2D Charlier moments neural networks. In International Conference on Electronic Engineering and Renewable Energy, Springer, Singapore, 151–159
Lian Z, Godil A, Bustos B, et al (2011) Shape retrieval on non-rigid 3D watertight meshes, in Eurographics workshop on 3D object retrieval (3DOR)
Liao S, Chiang A, Lu Q, Pawlak M (2002) Chinese character recognition via gegenbauer moments. In: 2002 proceedings 16th international conference on pattern recognition. IEEE, pp 485–488
Liu S, Giles L, Ororbia A (2018) Learning a hierarchical latent-variable model of 3d shapes. In 2018 international conference on 3D vision (3DV) (pp. 542-551). IEEE.
Liu Z, Song W, Tian Y, Ji S, Sung Y, Wen L, Zhang T, Song L, Gozho A (2020) VB-net: voxel-based broad learning network for 3D object classification. Appl Sci 10(19):6735
Lo CH, Don HS (1989) 3-D moment forms: their construction and application to object identification and positioning. IEEE Trans Anal Machine Intell 11:1053–1064
Loffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: proceedings of the 32nd international conference on machine learning.
Masoumi M, Li C, Hamza AB (2016) A spectral graph wavelet approach for nonrigid 3D shape retrieval. Pattern Recogn Lett 83:339–348
Maturana D, Scherer S (2015) Voxnet: a 3D convolutional neural network for real-time object recognition. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 922-928). IEEE
McGill 3D Shape Benchmark. www.cim.mcgill.ca/~shape/benchMark/
Mesbah A, Berrahou A, El Mallahi M, Qjidaa H (2016) Fast and efficient computation of three-dimensional Hahn moments. J Electron Imaging 25(6):061621
Milano F, Loquercio A, Rosinol A, Scaramuzza D, Carlone L (2020) Primal-dual mesh convolutional neural networks. arXiv preprint arXiv:2010.12455.
Mukundan R, Ong SH, Lee PA (2001) Image analysis by Tchebichef moments. IEEE Trans Image Process 10:1357–1364
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: proceedings of the 27th international conference on machine learning (ICML-10). Pp 807–814
Nie W, Wang K, Wang H, Su Y (2019) The assessment of 3D model representation for retrieval with CNN-RNN networks. Multimed Tools Appl 78(12):16979–16994
Novotni M, Klein R (2004) Shape retrieval using 3D Zernike descriptors. Comput Aided Des 36(11):1047–1062
Patil S, Ravi B (2005) Voxel-based representation, display and thickness analysis of intricate shapes. In: ninth international conference on computer aided design and computer graphics (CAD-CG’05). IEEE, pp 6-pp.
Reverdy P, Leonard NE (2016) Parameter estimation in Softmax decision-making models with linear objective functions. IEEE Trans Autom Sci Eng 13:54–67
Sadjadi FA, Hall EL (1980) Three-dimensional moment invariants. IEEE Trans Pattern Anal Mach Intell PAMI-2:127–136
Shen L, Makedon F (2006) Spherical mapping for processing of 3D closed surfaces. Image Vis Comput 24(7):743–761
Sheng Y, Shen L (1994) Orthogonal Fourier-Mellin moments for invariant pattern recognition. JOSA A 11:1748–1757
Shi B, Bai S, Zhou Z, Bai X (2015) Deeppano: deep panoramic representation for 3-d shape recognition. IEEE Signal Process Lett 22(12):2339–2343
Singh C (2012) Local and global features based image retrieval system using orthogonal radial moments. Opt Lasers Eng 50:655–667
Singh C, Walia E, Upneja R (2012) Analysis of algorithms for fast computation of pseudo Zernike moments and their numerical stability. Digit Signal Process 22:1031–1043
Sinha A, Bai J, Ramani K (2016) Deep learning 3D shape surfaces using geometry images. In European conference on computer vision (pp. 223-240). Springer, Cham
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Suk T, Flusser J (2011) Tensor method for constructing 3D moment invariants. In: proceedings of the 14th international conference on computer analysis of images and patterns (CAIP’11), pp 212-219
Suk T, Flusser J, Boldyš J (2015) 3D rotation invariants by complex moments. Pattern Recogn 48(11):3516–3526
Svirsky Y, Sharf A (2020) A non-linear differentiable CNN-rendering module for 3D data enhancement. IEEE Trans Vis Comput Graph 27:3238–3249
Valverde I (2017) Three-dimensional printed cardiac models: applications in the field of medical education, cardiovascular surgery, and structural heart interventions. Revista Española de Cardiología (English edition) 70(4):282–291
Wang CX, Shi TB, Tang L, Chen YC (2020) Design of neural network model for lightweight 3D point cloud classification. JNI 5:122–128
Wu H, Coatrieux JL, Shu H (2013) New algorithm for constructing and computing scale invariants of 3D Tchebichef moments. Math Probl Eng 2013:1–8
Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3d shapenets: a deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition pp 1912-1920
Xiao B, Zhang Y, Li L, Li W, Wang G (2016) Explicit Krawtchouk moment invariants for invariant image recognition. J Electron Imaging 25:023002
Xu D, Li H (2008) Geometric moment invariants. Pattern Recogn 41(1):240–249
Yang B, Dai M (2011) Image analysis by Gaussian-Hermite moments. Signal Process 91:2290–2303
Yang B, Flusser J, Suk T (2015) 3D rotation invariants of Gaussian–Hermite moments. Pattern Recogn Lett 54:18–26
Yap P-T, Paramesran R, Ong S-H (2003) Image analysis by Krawtchouk moments. IEEE Trans Image Process 12:1367–1377
Zhang, L., da Fonseca, M. J., Ferreira A, & e Recuperaçao CRA (2007) Survey on 3D shape descriptors. FundaÃgao para a Cincia ea Tecnologia, Lisboa, Portugal, Tech. Rep. Technical Report, DecorAR (FCT POSC/EIA/59938/2004), 3.
Zhao D, Li S (2005) A 3D image processing method for manufacturing process automation. Comput Ind 56(8–9):975–985
Zheng Q, Sun J, Zhang L, Chen W, Fan H (2018) An improved 3D shape recognition method based on panoramic view. Math Probl Eng 2018:1–11
Zhou J, Shu H, Zhu H, Toumoulin C, Luo L (2005) Image Analysis by Discrete Orthogonal Hahn Moments. In: Image analysis by discrete orthogonal Hahn moments. Image Analysis Recognition. Springer, In, pp 524–531
Zhou Y, Zeng F, Qian J, Han X (2019) 3D shape classification and retrieval based on polar view. Inf Sci 474:205–220
Zhu H, Shu H, Liang J, Luo L, Coatrieux J-L (2007) Image analysis by discrete orthogonal Racah moments. Signal Process 87:687–708
Zhu H, Shu H, Zhou J, Luo L, Coatrieux J-L (2007) Image analysis by discrete orthogonal dual Hahn moments. Pattern Recogn Lett 28:1688–1704
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict 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.
Rights and permissions
About this article
Cite this article
Lakhili, Z., El Alami, A., Mesbah, A. et al. Rigid and non-rigid 3D shape classification based on 3D Hahn moments neural networks model. Multimed Tools Appl 81, 38067–38090 (2022). https://doi.org/10.1007/s11042-022-12125-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12125-6