Image Recognition using MLMVN and Frequency Domain Features

In this paper, we develop a new approach to image recognition. This approach is based on the analysis of frequency domain features (namely Fourier transform phases corresponding to certain frequencies) using the multilayer neural network with multi-valued neurons (MLMVN). MLMVN is a powerful complex-valued feedforward neural network, which has shown its high efficiency in solving various classification, prediction, and intelligent image filtering problems. As a complex-valued neural network, MLMVN has an ability to treat the phase information properly, completely preserving a circular nature of phase. At the same time it is known that phases contain all information about image edges, their location and spatial orientation. This means that the phase information can be used for image recognition. Particularly, this is the case when it is necessary to recognize objects whose size is known and fixed and it is possible to use phases corresponding to certain frequencies found based on the Nyquist-Shannon theorem as features for recognition. These phases can then be analyzed using MLMVN. We illustrate this approach using the famous MNIST image dataset, which for a 100% recognition rate was achieved. Phases corresponding only to the three lowest frequencies (1 to 3) and just a single hidden layer MLMVN are enough to achieve this result. A batch learning algorithm (MLMVN-SM-LLS) is employed to train the network.

[1]  A.V. Oppenheim,et al.  The importance of phase in signals , 1980, Proceedings of the IEEE.

[2]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Igor N. Aizenberg,et al.  MLMVN as an intelligent image filter , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[4]  Christian Hacker,et al.  GPU simulator of multilayer neural network based on multi-valued neurons , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[5]  Naum N. Aizenberg,et al.  CNN based on multi-valued neuron as a model of associative memory for grey scale images , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[6]  Jacek M. Zurada,et al.  Blur Identification by Multilayer Neural Network Based on Multivalued Neurons , 2008, IEEE Transactions on Neural Networks.

[7]  Akira Hirose,et al.  Improvement of Plastic Landmine Visualization Performance by Use of Ring-CSOM and Frequency-Domain Local Correlation , 2009, IEICE Trans. Electron..

[8]  Naum N. Aizenberg,et al.  Image recognition on the neural network based on multi-valued neurons , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Narasimhan Sundararajan,et al.  Projection-Based Fast Learning Fully Complex-Valued Relaxation Neural Network , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Kazuyuki Aihara,et al.  Complex-valued forecasting of wind profile , 2006 .

[12]  C.E. Shannon,et al.  Communication in the Presence of Noise , 1949, Proceedings of the IRE.

[13]  D. Mandic,et al.  Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models , 2009 .

[14]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[15]  Igor N. Aizenberg,et al.  A modified learning algorithm for the multilayer neural network with multi-valued neurons based on the complex QR decomposition , 2012, Soft Comput..

[16]  Igor N. Aizenberg,et al.  MLMVN With Soft Margins Learning , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Claudio Moraga,et al.  A Feedforward Neural Network based on Multi-Valued Neurons , 2004, Fuzzy Days.

[18]  Igor N. Aizenberg,et al.  System identification using FRA and a modified MLMVN with arbitrary complex-valued inputs , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[19]  Igor N. Aizenberg,et al.  Complex-Valued Neural Networks with Multi-Valued Neurons , 2011, Studies in Computational Intelligence.

[20]  Akira Hirose,et al.  Blood Vessel Segmentation in Complex-Valued Magnetic Resonance Images with Snake Active Contour Model , 2010, Int. J. E Health Medical Commun..

[21]  Igor N. Aizenberg,et al.  Multilayer Neural Network with Multi-Valued Neurons in time series forecasting of oil production , 2014, Neurocomputing.

[22]  Enrico Zio,et al.  Predicting component reliability and level of degradation with complex-valued neural networks , 2014, Reliab. Eng. Syst. Saf..

[23]  Claudio Moraga,et al.  Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm , 2006, Soft Comput..

[24]  J. Reinitz,et al.  Temporal classification of Drosophila segmentation gene expression patterns by the multi-valued neural recognition method. , 2002, Mathematical biosciences.