Abstract
Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural networks have typically considered the kernel weights without any constraint. We propose to investigate the impact of a symmetry constraint in convolutional layers for image classification tasks, taking our inspiration from the processes involved in the primary visual cortex and common image processing techniques. The goal is to determine if it is necessary to learn each weight of the filters independently, and the extent to which it is possible to enforce symmetrical constraints on the filters throughout the training process of a convolutional neural network by modifying the weight update preformed during the backpropagation algorithm and to evaluate the change in performance. The symmetrical constraint reduces the number of free parameters in the network, and it is able to achieve near identical performance. We address the following cases: x/y-axis symmetry, point reflection, and anti-point reflection. The performance is evaluated on four databases of images representing handwritten digits. The results support the conclusion that while random weights offer more freedom to the model, the symmetry constraint provides a similar level of performance while decreasing substantially the number of free parameters in the model. Such an approach can be valuable in phase-sensitive applications that require a linear phase property throughout the feature extraction process.
Similar content being viewed by others
References
Basu M (2002) Gaussian-based edge-detection methods—a survey. IEEE Trans Syst Man Cybern Part C Appl Rev 32(3):252–260
Bhattacharya U, Chaudhuri B (2005) Databases for research on recognition of handwritten characters of Indian scripts. In: Proceedings of the 8th international conference on document analysis and recognition (ICDAR’05), pp 789–793
Bhowmick T, Parui S, Bhattacharya U, Shaw B (2006) An HMM based recognition scheme for handwritten oriya numerals. In: Proceedings of the 9th international conference on information technology (ICIT 2006), pp 105–110
Cecotti H, Gräser A (2011) Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans Pattern Anal Mach Intell 33(3):433–445
Chaudhuri B (2006) A complete handwritten numeral database of Bangla—a major Indic script. In: Proceedings of the 10th international workshop on frontiers in handwriting recognition (IWFHR’10), pp 1–6
Chaudhuri BB, Pal U (1998) A complete printed Bangla OCR system. Pattern Recognit 31:531–549
Cheng Y, Wang D, Zhou P, Zhang T (2018) Model compression and acceleration for deep neural networks: the principles, progress, and challenges. IEEE Signal Process Mag 35(1):126–136
Cireşan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: Computer vision and pattern recognition (CVPR), pp 3642–3649
Cohen TS, Welling M (2016) Group equivalent convolutional networks. In: Proceedings of the 33rd international conference on machine learning, 48:2990–2999
Dieleman S, De Fauw J, Kavukcuoglu K (2016) Exploiting cyclic symmetry in convolutional neural networks. In: Proceedings of the 33rd international conference on machine learning, vol 48
Dieleman S, Willett KW, Dambre J (2015) Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon Not R Astron Soc 450:1441–1459
Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11:625–660
Fukushima K (1980) A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):193–202
Gonzalez RC, Woods RE (2008) Digital image processing. Pearson, London
Goodfellow I, Bengio Y, Courville A (2017) Deep learning. The MIT Press, Cambridge
Grill-Spector K, Malach R (2004) The human visual cortex. Annu Rev Neurosci 27:649–77
Hagiwara K, Hayashi T, Kawasaki S, Arakawa F, Endo O, Nomura H, Tsukamoto A, Nguyen D, Nguyen B, Tran A, Hyunh H, Kudoh I, Pham C (2018) A two-stage-pipeline CPU of sh-2 architecture implemented on FPGA and SOC for IOT, edge AI and robotic applications. In: 2018 IEEE symposium in low-power and high-speed chips (COOL CHIPS), pp 1–3
Hassibi B, Stork DG (1993) Second order derivatives for network pruning: optimal brain surgeon. In: Hanson SJ, Cowan JD, Giles CL (eds) Advances in neural information processing systems, vol 5, pp 164–171
Huang G, Bai Z, Kasun LLC, Vong CM (2015) Local receptive fields based extreme learning machine. IEEE Comput Intell Mag 10(2):18–29
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501
Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \(<\)0.5 mb model size
Jain AK, Ratha NK, Lakshmanan S (1997) Object detection using Gabor filters. Pattern Recognit 30:295–309
Jarrett K, Kavukcuoglu K, Ranzato M, LeCun Y (2009) What is the best multi-stage architecture for object recognition? In: Proceedings of the 12th international conference on computer vision (ICCV’09), pp 2146–2153
Kamarainen JK, Kyrki V, Kalviainen H (2006) Invariance properties of Gabor filter-based features-overview and applications. IEEE Trans Image Process 15:1088–1099
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25. Curran Associates, Inc, pp 1097–1105
LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L (1990) Handwritten digit recognition with a back-propagation network. Adv Neural Inf Process Syst 2:396–404
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
LeCun YA, Bottou L, Orr GB, Müller KR (2012) Efficient backprop. In: Montavon G, Orr GB, Müller KR (eds) Neural networks: tricks of the trade, 2nd edn. Springer, Berlin, pp 9–48
Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the international conference on computer vision, vol 2, pp 1150–1157
Roberts P (2011) Signals and systems: analysis using transform methods & MATLAB. McGraw-Hill Education
Ma J, Sheridan RP, Liaw A, Dahl GE, Svetnik V (2015) Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inf Model 55:263–274
Oppenheim AV, Schafer RW (1989) Discrete-time signal processing. Prentice-Hall, Englewood Cliffs
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Pal U, Chaudhuri BB (2004) Indian script character recognition: a survey. Pattern Recognit 37(9):1887–1899
Redmon J, Angelova A (2015) Real-time grasp detection using convolutional neural networks. In: Proceedings of IEEE international conference on robotics and automation (ICRA), pp 1316–1322
Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2:1019 EP
Russell S, Norvig P (2009) Artificial intelligence: a modern approach, 3rd edn. Prentice Hall Press, Upper Saddle River
Scherbaum F, Bouin MP (1997) FIR filter effects and nucleation phases. Geophys J Int 130:661–668
Sethi IK, Chatterjee B (1977) Machine recognition of constrained hand printed Devanagari. Pattern Recognit 9:69–75
Seto K, Nejatollahi H, An J, Kang S, Dutt N (2019) Small memory footprint neural network accelerators. In: 20th international symposium on quality electronic design (ISQED), pp 253–258
Shang W, Sohn K, Almeida D, Lee H (2016) Understanding and improving convolutional neural networks via concatenated rectified linear units
Shen LL, Ji Z (2009) Gabor wavelet selection and SVM classification for object recognition. Acta Automatica Sinica 35:350–355
Simard P, Steinkraus D, Platt J (2003) Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of the 7th international conference on document analysis and recognition (ICDAR), pp 958–962
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR. arXiv:abs/1409.1556
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
Sundararajan D (2003) Digital signal processing: theory and practice. World Scientific, Singapore
Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. CoRR. arXiv:abs/1409.4842
Vajda S, Roy K, Pal U, Chaudhuri B, Belaïd A (2009) Automation of Indian postal documents written in Bangla and English. Int J Pattern Recognit Artif Intell 23(8):1599–1632
Wu J, Leng C, Wang Y, Hu Q, Cheng J (2016) Quantized convolutional neural networks for mobile devices. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 4820–4828
Zee A (2007) Fearful symmetry. Princeton University Press, Princeton
Zhai S, Cheng Y, Zhang ZM (2016) Doubly convolutional neural networks. In: Advances in neural information processing systems, pp 1082–1090
Zheng L, Yang Y, Tian Q (2018) SIFT meets CNN: a decade survey of instance retrieval. IEEE Trans PAMI 40(5):1224–1244
Ziou D, Tabbone S (1998) Edge detection techniques: an overview. Int J Pattern Recognit Image Anal 8(4):537–559
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
Dzhezyan, G., Cecotti, H. Symmetrical filters in convolutional neural networks. Int. J. Mach. Learn. & Cyber. 12, 2027–2039 (2021). https://doi.org/10.1007/s13042-021-01290-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01290-z