Abstract
In this paper, we propose a new model based on 3D discrete orthogonal moments and deep neural networks (DNN) to improve the classification accuracy of 3D objects under geometric transformations and noise. However, the utilization of moment invariants presents some drawbacks: They can’t describe the object efficiently, and their computation process is time consuming. Discrete orthogonal moments have the property to extract pertinent features from an image even in lower orders and are robust to noise. The main goal of this work is to investigate the robustness of the proposed model to geometric transformations like translation, scale and rotation and noisy conditions. The experiment simulations are conducted on datasets formed by applying some geometric transformations and noise on selected objects from McGill database. The obtained results indicate that the proposed model achieves high performance classification rates, robust to geometric transformations and noise degradation than other methods based on moment invariants.
Similar content being viewed by others
References
Al-Ayyoub M, AlZu’bi S, Jararweh Y, Shehab M-A, Gupta B-B (2018) Accelerating 3D medical volume segmentation using GPUs. Multimed Tools Appl 77(4):4939–4958
AlZu’bi S, Shehab M, Al-Ayyoub M, Jararweh Y, Gupta B (2018) Parallel implementation for 3d medical volume fuzzy segmentation. Pattern Recogn Lett
Batioua I, Benouini R, Zenkouar K, Zahi A, El Fadili H (2017) 3D image analysis by separable discrete orthogonal moments based on Krawtchouk and Tchebichef polynomials. Pattern Recogn 71:264–277
Belkasim SO, Shridhar M, Ahmadi M (1991) Pattern recognition with moment invariants: a comparative study and new results. Pattern Recogn 24:1117–1138
Benouini R, Batioua I, Zenkouar K, Najah S, Qjidaa H (2018) Efficient 3D object classification by using direct Krawtchouk moment invariants. Multimed Tools Appl:1–26
Blum C (2005) Ant colony optimization: introduction and recent trends. Phys Life Rev 2(4):353–373
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
Chong C-W, Raveendran P, Mukundan R (2003) The scale invariants of pseudo-Zernike moments. Pattern Anal Applic 6:176–184
Chong C-W, Raveendran P, Mukundan R (2004) Translation and scale invariants of Legendre moments. Pattern Recogn 37:119–129
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
Dai XB, Shu HZ, Luo LM, Han GN, Coatrieux JL (2010) Reconstruction of tomographic images from limited range projections using discrete radon transform and Tchebichef moments. Pattern Recogn 43:1152–1164
Fehr J, Burkhardt H (2008) 3D rotation invariant local binary patterns. In: 19th international conference on pattern recognition ICPR’08. IEEE Computer Society, Madison, pp 1–4
Flusser J, Suk T, Zitova B (2009) Moments and Moment Invariants in Pattern Recognition. Wiley, Hoboken
Flusser J, Suk T, Zitova B (2016) 2D and 3D image analysis by moments, Wiley, Hoboken
Galvez JM, Canton M (1993) Normalization and shape recognition of three-dimensional objects by 3D moments. Pattern Recogn 26:667–681
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. In: proceedings of the 13th international conference on artificial intelligence and statistics. Pp 249-256
Goh H-A, Chong C-W, Besar R, Abas FS, Sim K-S (2009) Translation and scale invariants of Hahn moments. Int J Image Graph 9:271–285
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
Hinton G, Deng L, Yu D, Dahl G et al (2012) Deep neural networks for Accoustic Modelling in speech recognition. IEEE Signal Process Mag 29
Hu M-K (1962) Visual pattern recognition by moment invariants. IRE Transaction on Information 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
Jian M, Dong J, Lam K-M (2013) FSAM: a fast self-adaptive method for correcting non-uniform illumination for 3D reconstruction. Comput Ind 64(9):1229–1236
Jian M, Yin Y, Dong J, Zhang W (2018) Comprehensive assessment of non-uniform illumination for 3D heightmap reconstruction in outdoor environments. Comput Ind 99:110–118
Kazhdan M (2007) An approximate and efficient method for optimal rotation alignment of 3D models. IEEE Trans Pattern Anal Mach Intell 29(7):1221–1229
Khotanzad A, Hong YH (1990) Invariant image recognition by Zernike moments. IEEE Trans Pattern Anal Mach Intell 12:489–497
Kingma, DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst:1079–1105
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
Lo CH, Don HS (1989) 3-D moment forms: their construction and application to object identification and positioning. IEEE Trans Anal and 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. pp 448–456
Luciano L, Hamza A-B (2018) Deep learning with geodesic moments for 3D shape classification. Pattern Recogn Lett 105:182–190
Mademlis A, Axenopoulos A, Daras P, Tzovaras D, Strintzis MG (2006) 3D content-based search based on 3D Krawtchouk moments. In: 2006 third international symposium on 3D data processing, visualization, and transmission (3DPVT’06). IEEE, pp 743–749
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. Journal of Electronic Imaging 25:061621
Mesbah A, Berrahou A, Hammouchi H, Berbia H, Qjidaa H, Daoudi M (2018) Non-rigid 3D model classification using 3D Hahn moment convolutional neural networks
Mesbah A, El Mallahi M, Lakhili Z, Qjidaa H, Berrahou A (2016) Fast and accurate algorithm for 3D local object reconstruction using Krawtchouk moments. In: 2016 IEEE 5th international conference on multimedia computing and systems (ICMCS). IEEE, pp 1–6
Mukundan R, Ong SH, Lee PA (2001) Image analysis by Tchebichef moments. IEEE Trans Image Process 10:1357–1364
Mukundan R, Ramakrishnan K (1998) Moment functions in image analysis—theory and applications.World scientific
Mundy J-L, Zisserman A (1992) Geometric invariance in computer vision. MIT Press, Cambridge
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
Nasrabadi NM (2007) Pattern recognition and machine learning. Journal of Electronic Imaging 16:49901
Palaniappan R, Raveendran P, Omatu S (2000) New invariant moments for non-uniformly scaled images. Pattern Anal Applic 3:78–87
Pandey VK, Singh J, Parthasarathy H (2016) Translation and scale invariance of 2D and 3D Hahn moments. In: IEEE, pp 255–259
Reiss T-H (1993) Recognizing planar objects using invariant image features. Springer, Berlin
Reverdy P, Leonard NE (2016) Parameter estimation in Softmax decision-making models with linear objective functions. IEEE Trans Autom Sci Eng 13:54–67
Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747
Rumelhart D-E, Hinton G-E, Williams R-J (1985) Learning internal representations by error propagation. Nature 323(99):533–536
Sadjadi FA, Hall EL (1980) Three-dimensional moment invariants. IEEE Trans Pattern Anal Mach Intell:127–136
Sheng Y, Shen L (1994) Orthogonal Fourier-Mellin moments for invariant pattern recognition. JOSA A 11:1748–1757
Sietsma J, Dow R-J (1991) Creating artificial neural networks that generalize. Neural Netw 4(1):67–79
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
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 (2003) Combined blur and affine moment invariants and their use in pattern recognition. Pattern Recogn 36:2895–2907
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
Teague MR (1980) Image analysis via the general theory of moments. JOSA 70:920–930
Wu H, Coatrieux JL, Shu H (2013) New algorithm for constructing and computing scale invariants of 3D Tchebichef moments. Math Probl Eng
Xiao B, Zhang Y, Li L, Li W, Wang G (2016) Explicit Krawtchouk moment invariants for invariant image recognition. Journal of Electronic Imaging 25:023002
Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853
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 Y, Wen C, Zhang Y, Soh YC (2002) Determination of blur and affine combined invariants by normalization. Pattern Recogn 35:211–221
Zhou J, Shu H, Zhu H, Toumoulin C, Luo L (2005) Image analysis by discrete orthogonal Hahn moments. In: Image Analysis Recognition. Springer, pp 524–531
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, Xia T, Luo L, Coatrieux JL (2007) Translation and scale invariants of Tchebichef moments. Pattern Recogn 40:2530–2542
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
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. Robust classification of 3D objects using discrete orthogonal moments and deep neural networks. Multimed Tools Appl 79, 18883–18907 (2020). https://doi.org/10.1007/s11042-020-08654-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08654-7