Abstract
Convolutional Neural Networks (CNNs) are being used popularly for detecting and classifying objects. Rotational invariance is not guaranteed by many of the existing CNN architectures. Many attempts have been made to acquire rotational invariance in CNNs. Our approach ‘Eigenvector Orientation Corrected LeNet (EOCL)’ presents a simple method to make ordinary LeNet [1] capable of detecting rotated digits, and also to predict the relative angle of orientation of digits with unknown orientation. The proposed method does not demand any modification in the existing LeNet architecture, and requires training with digits having only single orientation. EOCL incorporates an ‘orientation estimation and correction’ step prior to the testing phase. Using Principal Component Analysis, we find the maximum spread direction (Principal Component) of each test sample and then align it vertically. We demonstrate the improvement in classification accuracy and reduction in test time achieved by our approach, on rotated-MNIST [2] and MNIST_rot_12k test datasets, compared to other existing methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141–142 (2012). https://www.microsoft.com/en-us/research/publication/the-mnist-database-of-handwritten-digit-images-for-machine-learning-research/
Santosh K.C.: Character recognition based on DTWRadon. In: International Conference on Document Analysis and Recognition (2011). https://doi.org/10.1109/ICDAR.2011.61
Bhandare, A., Bhide, M., Gokhale, P., Chandavarka, R.: Applications of convolutional neural networks. Int. J. Comput. Sci. Inf. Technol. 7(5), 2206–2215 (2016)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 14(1), 234–778 (2004). https://doi.org/10.1023/B:VISI.0000029664.99615.94
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. Lecture Notes in Computer Science, vol. 3951(1), pp. 404–417. Springer, Berlin (2006). https://doi.org/10.1007/11744023_32
Zhang, H., Li, Z., Liu, Y.: Fractional orthogonal Fourier-Mellin moments for pattern recognition. In: CCPR, vol. 662(1), 766–778. Springer, Singapore (2016). https://doi.org/10.1007/978-981-10-3002-4_62
Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Harmonic networks: deep translation and rotation equivariance. arXiv:1612.04642
Marcos, D., Volpi, M., Komodakis, N., Tuia, D.: Rotation equivariant vector field networks. arXiv:1612.09346
Kandi, H., Jain, A., Velluva Chathoth, S. et al.: Incorporating rotational invariance in convolutional neural network architecture. Pattern Anal. Appl. (2018). https://doi.org/10.1007/s10044-018-0689-0
Jaderberg, M., Kimonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. arXiv:1506.02025
Jain, A., Subrahmanyam, G.S., Mishra, D.: Stacked features based CNN for rotation invariant digit classification. In: Pattern Recognition and Machine Intelligence, 7th International Conference, PReMI Proceedings (2017). https://doi.org/10.1007/978-3-319-69900-4_67
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Swetha, V.C., Mishra, D., Gorthi, S.S. (2020). Eigenvector Orientation Corrected LeNet for Digit Recognition. In: Chaudhuri, B., Nakagawa, M., Khanna, P., Kumar, S. (eds) Proceedings of 3rd International Conference on Computer Vision and Image Processing. Advances in Intelligent Systems and Computing, vol 1022. Springer, Singapore. https://doi.org/10.1007/978-981-32-9088-4_27
Download citation
DOI: https://doi.org/10.1007/978-981-32-9088-4_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9087-7
Online ISBN: 978-981-32-9088-4
eBook Packages: EngineeringEngineering (R0)