Rotation Invariant Digit Recognition Using Convolutional Neural Network
Deep learning architectures use a set of layers to learn hierarchical features from the input. The learnt features are discriminative, and thus can be used for classification tasks. Convolutional neural networks (CNNs) are one of the widely used deep learning architectures. CNN extracts prominent features from the input by passing it through the layers of convolution and nonlinear activation. These features are invariant to scaling and small amount of distortions in the input image, but they offer rotation invariance only for smaller degrees of rotation. We propose an idea of using multiple instance of CNN to enhance the overall rotation invariant capabilities of the architecture even for higher degrees of rotation in the input image. The architecture is then applied to handwritten digit classification and captcha recognition. The proposed method requires less number of images for training, and therefore reduces the training time. Moreover, our method offers an additional advantage of finding the approximate orientation of the object in an image, without any additional computational complexity.
KeywordsConvolutional neural networks Rotation invariance Digit recognition LeNet
- 1.Yann LeCun and Yoshua Bengio. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10):1995, 1995.Google Scholar
- 2.Sajjad S Ahranjany, Farbod Razzazi, and Mohammad H Ghassemian. A very high accuracy handwritten character recognition system for farsi/arabic digits using convolutional neural networks. In Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010 IEEE Fifth International Conference on, pages 1585–1592. IEEE, 2010.Google Scholar
- 3.Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2):295–307, 2016.Google Scholar
- 4.Fok Hing Chi Tivive and Abdesselam Bouzerdoum. Rotation invariant face detection using convolutional neural networks. In International Conference on Neural Information Processing, pages 260–269. Springer, 2006.Google Scholar
- 5.D. Wu, L. Pigou, P. J. Kindermans, N. D. H. Le, L. Shao, J. Dambre, and J. M. Odobez. Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(8):1583–1597, 2016.Google Scholar
- 6.B. Fasel and D. Gatica-Perez. Rotation-invariant neoperceptron. In 18th International Conference on Pattern Recognition (ICPR’06), volume 3, pages 336–339, 2006.Google Scholar
- 7.Shih-Chung B Lo, Heang-Ping Chan, Jyh-Shyan Lin, Huai Li, Matthew T Freedman, and Seong K Mun. Artificial convolution neural network for medical image pattern recognition. Neural networks, 8(7):1201–1214, 1995.Google Scholar
- 8.Dmitry Laptev, Nikolay Savinov, Joachim M. Buhmann, and Marc Pollefeys. TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. CoRR, arXiv:1604.06318, 2016.
- 9.Max Jaderberg, Karen Simonyan, Andrew Zisserman, and Koray Kavukcuoglu. Spatial transformer networks. CoRR, arXiv:1506.02025, 2015.
- 10.Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.Google Scholar
- 11.Yann LeCun and Corinna Cortes. Mnist handwritten digit database. AT&T Labs [Online]. Available: https://yann.lecun.com/exdb/mnist, 2010.