Geometric transformations embedded into convolutional neural networks

• Autorzy: Tarasiuk P. , Pryczek M.
• Języki publikacji: EN

Abstrakty

EN

This paper presents a novel extension to convolutional neural networks. While CNNs are known for invariance to object translation, changes to the other parameters could make the image recognition tasks difficult - that includes rotations and scaling. Some improvement in this area could be achieved with embedded geometric transformations used inside the CNNs. In order to provide a practical solution, which allows fast propagation and learning of the modified networks, “fast geometric transformations” are introduced.

Słowa kluczowe

EN

artificial intelligence; machine learning; deep learning; convolutional neural networks; image processing; image recognition; geometric transformation

PL

sztuczna inteligencja; uczenie maszynowe; uczenie głębokie; splotowe sieci neuronowe; przetwarzanie obrazów; rozpoznawanie obrazów; przekształcenie geometryczne

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2016
• Tom: Vol. 24, nr 3
• Strony: 33--48
• Opis fizyczny: Bibliogr. 18 poz.

Twórcy

autor

Tarasiuk P.

• Lodz University of Technology, Institute of Information Technology, ul. Wolczanska 215, 90-924 Lodz, Poland

autor

Pryczek M.

• Lodz University of Technology, Institute of Information Technology, ul. Wolczanska 215, 90-924 Lodz, Poland

Bibliografia

• [1] Krizhevsky, A., Sutskever, I., and Hinton, G. E., ImageNet Classification with Deep Convolutional Neural Networks, In: Advances in Neural Information Processing Systems 25, edited by F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Curran Associates, Inc., 2012, pp. 1097-1105.
• [2] Zeiler, M. D. and Fergus, R., Visualizing and Understanding Convolutional Networks, CoRR, Vol. abs/1311.2901, 2013.
• [3] Nguyen, T. V., Lu, C., Sepulveda, J., and Yan, S., Adaptive Nonparametric Image Parsing, CoRR, Vol. abs/1505.01560, 2015.
• [4] Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L., ImageNet: A Large-Scale Hierarchical Image Database, In: CVPR09, 2009.
• [5] Fukushima, K., Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position, Biological Cybernetics, Vol. 36, 1980, pp. 193-202.
• [6] Hubel, D. H. andWiesel, T. N., Receptive Fields and Functional Architecture in Two Nonstriate Visual Areas (18 and 19) of the Cat, Journal of Neurophysiology, Vol. 28, 1965, pp. 229-289.
• [7] LeCun, Y. and Bengio, Y., Convolutional Networks for Images, Speech, and Time-Series, In: The Handbook of Brain Theory and Neural Networks, edited by M. A. Arbib, MIT Press, 1995.
• [8] Cheng, G., Zhou, P., and Han, J., Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images, IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, No. 12, Dec 2016, pp. 7405-7415.
• [9] Gonzalez, D. M., Volpi, M., and Tuia, D., Learning rotation invariant convolutional filters for texture classification, CoRR, Vol. abs/1604.06720, 2016.
• [10] Laptev, D., Savinov, N., Buhmann, J. M., and Pollefeys, M., TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks, CoRR, Vol. abs/1604.06318, 2016.
• [11] Vialatte, J., Gripon, V., and Mercier, G., Generalizing the Convolution Operator to Extend CNNs to Irregular Domains, CoRR, Vol. abs/1606.01166, 2016.
• [12] Weiman, C. F. R. and Chaikin, G., Logarithmic Spiral Grids for Image Processing and Display, Computer Graphics and Image Processing, Vol. 11, No. 3, November 1979, pp. 197-226.
• [13] Tomczyk, A., Szczepaniak, P. S., and Lis, B., Generalized Multi-layer Kohonen Network and Its Application to Texture Reognition, In: Proceedings of the Lecture Notes in Artificial Intelligence, No. 3070, 2004, pp. 760-767.
• [14] Foundation, P. S., The Python Language Reference, 1990-2016.
• [15] Ascher, D., Dubois, P. F., Hinsen, K., Hugunin, J., and Oliphant, T., Numerical Python, Lawrence Livermore National Laboratory, Livermore, CA, ucrlma- 128569 ed., 1999.
• [16] PythonWare, Python Imaging Library (PIL), 2009-2016.
• [17] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R., Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res., Vol. 15, No. 1, Jan. 2014, pp. 1929-1958.
• [18] Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., and Ng, A. Y., Reading Digits in Natural Images with Unsupervised Feature Learning, In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011, 2011.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).