ABSTRACT
Deep Learning (DL) methods extract complex set of features using architectures containing hierarchical set of layers. The features so learned have high discriminative power and thus represents the input to the network in the most efficient manner. Convolutional Neural Networks (CNN) are one of the deep learning architectures, extracts structural features with little invariance to smaller translational, scaling and other forms of distortions. In this paper, the learning capabilities of CNN's are explored towards providing improvement in rotational invariance to its architecture. We propose a new CNN architecture with an additional layer formed by differential excitation against distance for the improvement of rotational invariance and is called as RICNN. Moreover, we show that the proposed method is giving superior performance towards invariance to rotations against the original CNN architecture (training samples with different orientations are not considered) without disturbing the invariance to smaller translational, scaling and other forms of distortions. Different profiles like training time, testing time and accuracies are evaluated at different percentages of training data for comparing the performance of the proposed configuration with original configuration.
- 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 ScholarDigital Library
- Patrice Y Simard, Dave Steinkraus, and John C Platt. Best practices for convolutional neural networks applied to visual document analysis. In null, page 958. IEEE, 2003. Google ScholarDigital Library
- Sergey Zagoruyko and Nikos Komodakis. Learning to compare image patches via convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4353--4361, 2015.Google ScholarCross Ref
- Fok Hing Chi Tivive and Abdesselam Bouzerdoum. A new class of convolutional neural networks (siconnets) and their application of face detection. In Neural Networks, 2003. Proceedings of the International Joint Conference on, volume 3, pages 2157--2162. IEEE, 2003.Google ScholarCross Ref
- Earnest Paul Ijjina and C Krishna Mohan. Facial expression recognition using kinect depth sensor and convolutional neural networks. In Machine Learning and Applications (ICMLA), 2014 13th International Conference on, pages 392--396. IEEE, 2014. Google ScholarDigital Library
- 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 ScholarDigital Library
- K Haribabu, GRKS Subrahmanyam, and Deepak Mishra. A robust digital image watermarking technique using auto encoder based convolutional neural networks. In Computational Intelligence: Theories, Applications and Future Directions (WCI), 2015 IEEE Workshop on, pages 1--6. IEEE, 2015.Google Scholar
- Christophe Garcia and Manolis Delakis. Convolutional face finder: A neural architecture for fast and robust face detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(11):1408--1423, 2004. Google ScholarDigital Library
- 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 ScholarDigital Library
- 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 ScholarDigital Library
- Anil K Jain. Fundamentals of digital image processing. Prentice-Hall, Inc., 1989. Google ScholarDigital Library
- 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 ScholarCross Ref
- David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. Learning representations by back-propagating errors. Cognitive modeling, 5(3):1, 1988.Google Scholar
- Yann LeCun and Corinna Cortes. Mnist handwritten digit database. AT&T Labs {Online}. Available: http://yann.lecun.com/exdb/mnist, 2010.Google Scholar
- Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, and Wen Gao. Wld: A robust local image descriptor. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(9):1705--1720, 2010. Google ScholarDigital Library
- Mutawarra Hussain, Ghulam Muhammad, Sahar Q Saleh, Anwar M Mirza, and George Bebis. Image forgery detection using multi-resolution weber local descriptors. In EUROCON, 2013 IEEE, pages 1570--1577. IEEE, 2013.Google Scholar
- Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Sammy Mohamed, and Andrea Vedaldi. Describing textures in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3606--3613, 2014. Google ScholarDigital Library
Index Terms
- A differential excitation based rotational invariance for convolutional neural networks
Recommendations
Incorporating rotational invariance in convolutional neural network architecture
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 ...
Towards dropout training for convolutional neural networks
Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper ...
Convolutional neural networks for wavelet domain super resolution
Proposed a super resolution method with higher reconstruction accuracy than before.Cast super resolution as a problem of estimating sparse wavelet detail coefficients.Estimated sparse wavelet coefficients using a convolutional neural network (CNN)...
Comments