Incorporating rotational invariance in convolutional neural network architecture | Pattern Analysis and Applications Skip to main content
Springer Nature Link
Log in

Incorporating rotational invariance in convolutional neural network architecture

  • Theoretical Advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Convolutional neural networks (CNNs) are one of the deep learning architectures capable of learning complex set of nonlinear features useful for effectively representing the structure of input to the network. Existing CNN architectures are invariant to small distortions, translations, scaling but are sensitive to rotations. In this paper, unlike the approaches where training samples with different orientations are included, we propose a new architecture in which addition of a rotational invariant map gives few folds of improvement towards rotational invariance to the network. We also propose an improved architecture where rotational invariance is achieved by rotationally varying the convolutional maps. We show that the proposed methods give better invariance towards rotations as compared to conventional training of CNN architecture (where the network is trained without considering the different orientation of training samples). The methods achieve rotation-independent classification by introducing few modifications in conventional CNNs, but do not add any trainable parameter to the network, thus keeping the number of free parameters/weights constant. We demonstrate the performance of proposed rotation invariant architectures for handwritten digits and texture data sets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, Boston, pp 255–258

    Google Scholar 

  2. Lauer F, Suen CY, Bloch G (2007) A trainable feature extractor for handwritten digit recognition. Pattern Recognit. 40(6):1816–1824

    Article  MATH  Google Scholar 

  3. Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: Null. IEEE, p 958

  4. Ahranjany SS, Razzazi F, Ghassemian MH (2010) A very high accuracy handwritten character recognition system for Farsi/Arabic digits using convolutional neural networks. In: 2010 IEEE fifth international conference on bio-inspired computing: theories and applications (BIC-TA). IEEE, pp 1585–1592

  5. Zagoruyko S, Komodakis N (2015) Learning to compare image patches via convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353–4361

  6. Ijjina EP, Mohan CK (2014) Facial expression recognition using Kinect depth sensor and convolutional neural networks. In: 2014 13th international conference on machine learning and applications (ICMLA). IEEE, pp 392–396

  7. Tivive FHC, Bouzerdoum A (2003) A new class of convolutional neural networks (SICoNNets) and their application of face detection. In: Proceedings of the international joint conference on neural networks, 2003, vol 3. IEEE, pp 2157–2162

  8. Dong C, Loy CC, He K, Tang X (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307

    Article  Google Scholar 

  9. Gopakumar G, Babu KH, Mishra D, Gorthi SS, Subrahmanyam GRS (2017) Cytopathological image analysis using deep-learning networks in microfluidic microscopy. JOSA A 34(1):111–121

    Article  Google Scholar 

  10. Kandi H, Mishra D, Gorthi SRS (2017) Exploring the learning capabilities of convolutional neural networks for robust image watermarking. Comput Secur 65:247–268

    Article  Google Scholar 

  11. Garcia C, Delakis M (2004) Convolutional face finder: a neural architecture for fast and robust face detection. IEEE Trans Pattern Anal Mach Intell 26(11):1408–1423

    Article  Google Scholar 

  12. Lo S-CB, Chan H-P, Lin J-S, Li H, Freedman MT, Mun SK (1995) Artificial convolution neural network for medical image pattern recognition. Neural Netw 8(7):1201–1214

    Article  Google Scholar 

  13. Tivive FHC, Bouzerdoum A (2006) Rotation invariant face detection using convolutional neural networks. In: Neural information processing: 13th international conference, ICONIP 2006, Hong Kong, China, October 3–6, 2006. Proceedings, Part II. Springer, Berlin, pp 260–269

  14. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252

    Article  MathSciNet  Google Scholar 

  15. Laptev D, Savinov N, Buhmann JM, Pollefeys M (2016) TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. In: CoRR. arXiv:abs/1604.06318

  16. Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: CoRR. http://arxiv.org/abs/1506.02025

  17. Zhou Y, Ye Q, Qiu Q, Jiao J (2017) Oriented response networks. CoRR. http://arxiv.org/abs/1701.01833

  18. Jain AK (1989) Fundamentals of digital image processing. Prentice-Hall, Inc., Englewood Cliffs

    MATH  Google Scholar 

  19. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  20. Rumelhart DE, Hinton GE, Williams RJ (1988) Learning representations by back-propagating errors. Cogn Model 5(3):1

    MATH  Google Scholar 

  21. LeCun Y, Cortes C (2010) Mnist handwritten digit database. AT&T Labs. http://yann.lecun.com/exdb/mnist

  22. Yokono JJ, Poggio T (2004) Rotation invariant object recognition from one training example

  23. Rowley HA, Baluja S, Kanade T (1998) Neural network-based face detection. IEEE Trans Pattern Anal Mach Intell 20(1):23–38

    Article  Google Scholar 

  24. Fasel B, Gatica-Perez D (2006) Rotation-invariant neoperceptron. In: 18th international conference on pattern recognition, 2006. ICPR 2006. vol 3. IEEE, pp 336–339

  25. Chen J, Shan S, He C, Zhao G, Pietikäinen M, Chen X, Gao W (2010) Wld: a robust local image descriptor. IEEE Trans Pattern Anal Mach Intell 32(9):1705–1720

    Article  Google Scholar 

  26. Li S, Gong D, Yuan Y (2013) Face recognition using Weber local descriptors. Neurocomputing 122:272–283

    Article  Google Scholar 

  27. Hussain M, Muhammad G, Saleh SQ, Mirza AM, Bebis G (2013) Image forgery detection using multi-resolution Weber local descriptors. In: EUROCON, 2013 IEEE. IEEE, pp. 1570–1577

  28. Larochelle H, Erhan D, Courville A, Bergstra J, Bengio Y (2007) An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th international conference on machine learning (ICML ’07). ACM, New York, pp 473–480. https://doi.org/10.1145/1273496.1273556

  29. Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A (2014) Describing textures in the wild. In: 2014 IEEE conference on computer vision and pattern recognition, pp 3606–3613

Download references

Author information

Authors and Affiliations

  1. Department of Avionics, Indian Institute of Space Science and Technology, Thiruvananthapuram, Kerala, 695547, India

    Haribabu Kandi, Ayushi Jain, Swetha Velluva Chathoth & Deepak Mishra

  2. Department of Electrical Engineering, Indian Institute of Technology, Tirupati, Andhra Pradesh, India

    Gorthi R. K. Sai Subrahmanyam

Authors
  1. Haribabu Kandi
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ayushi Jain
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Swetha Velluva Chathoth
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Deepak Mishra
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Gorthi R. K. Sai Subrahmanyam
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Gorthi R. K. Sai Subrahmanyam.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kandi, H., Jain, A., Velluva Chathoth, S. et al. Incorporating rotational invariance in convolutional neural network architecture. Pattern Anal Applic 22, 935–948 (2019). https://doi.org/10.1007/s10044-018-0689-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-018-0689-0

Keywords