Learning-Based Image Scaling Using Neural-Like Structure of Geometric Transformation Paradigm

In this chapter, it is proposed the solutions of a problem of changing image resolution based on the use of computational intelligence means, which are constructed using the new neuro-paradigm—Geometric Transformations Model. The topologies, the training algorithms, and the usage of neural-like structures of Geometric Transformations Model are described. Two methods of solving a problem of reducing and increasing image resolution are considered: using neural-like structures of Geometric Transformations Model and on the basis of the matrix operator of the weight coefficients of synaptic connections. The influences of the parameters of image preprocessing procedure, as well as the parameters of the neural-like structures of Geometric Transformations Model on the work quality of both methods are investigated. A number of the practical experiments using different quality indicators of synthesized images (PSNR, SSIM, UIQ, MSE) are performed. A comparison of the effectiveness of the developed method with the effectiveness of the existing one is implemented.

[1]  Hugh G. Lewis,et al.  Super-resolution mapping using Hopfield Neural Network with panchromatic imagery , 2011 .

[2]  Yevgeniy Bodyanskiy,et al.  Self-Learning Cascade Spiking Neural Network for Fuzzy Clustering Based on Group Method of Data Handling , 2013 .

[3]  Ivan Tsmots,et al.  Development of a regional energy efficiency control system on the basis of intelligent components , 2016, 2016 XIth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT).

[4]  Liming Zhang,et al.  New image super-resolution scheme based on residual error restoration by neural networks , 2003 .

[5]  Fei Xiao,et al.  Object-based sub-pixel mapping of buildings incorporating the prior shape information from remotely sensed imagery , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[6]  Pavlo Tkachenko,et al.  Features of the auto-associative neurolike structures of the geometrical transformation machine (GTM) , 2009, 2009 5th International Conference on Perspective Technologies and Methods in MEMS Design.

[7]  Ivanna Dronyuk,et al.  Synthesis of Noise-Like Signal Based on Ateb-Functions , 2015 .

[8]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[9]  Ivan Tsmots,et al.  Hardware implementation of the real time neural network components , 2011, Perspective Technologies and Methods in MEMS Design.

[10]  Yevgeniy Bodyanskiy,et al.  Adaptive robust models for identification of nonstationary systems in data stream mining tasks , 2016, 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP).

[11]  Qi Feng,et al.  Superresolution Mapping of Remotely Sensed Image Based on Hopfield Neural Network With Anisotropic Spatial Dependence Model , 2014, IEEE Geoscience and Remote Sensing Letters.

[12]  Fei Xiao,et al.  Super-resolution land-cover mapping using multiple sub-pixel shifted remotely sensed images , 2010 .

[13]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[15]  Iryna Khomytska,et al.  The Method of Statistical Analysis of the Scientific, Colloquial, Belles-Lettres and Newspaper Styles on the Phonological Level , 2017, CSIT.

[16]  Eric Mjolsness,et al.  Neural networks, pattern recognition, and fingerprint hallucination , 1986 .

[17]  Yevgeniy Bodyanskiy,et al.  Fast learning algorithm for deep evolving GMDH-SVM neural network in data stream mining tasks , 2016, 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP).

[18]  Xiao Dan,et al.  Automatic orthogonalization detection approach for GS algorithm , 1995 .

[19]  Nataliia Kunanets,et al.  E-Science: New paradigms, system integration and scientific research organization , 2015, 2015 Xth International Scientific and Technical Conference "Computer Sciences and Information Technologies" (CSIT).

[20]  V. Riznyk,et al.  Information Encoding Method of Combinatorial Optimization , 2006, 2006 International Conference - Modern Problems of Radio Engineering, Telecommunications, and Computer Science.

[21]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  I. Yurchak,et al.  Neurolike networks on the basis of Geometrical Transformation Machine , 2008, 2008 International Conference on Perspective Technologies and Methods in MEMS Design.

[23]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[24]  Dmytro Peleshko,et al.  Hybrid Generalized Additive Wavelet-Neuro-Fuzzy-System and Its Adaptive Learning , 2016, DepCoS-RELCOMEX.

[25]  Olena Vynokurova,et al.  Evolving spiking wavelet-neuro-fuzzy self-learning system , 2014, Appl. Soft Comput..

[26]  Ivan Izonin,et al.  Learning-based image super-resolution using weight coefficients of synaptic connections , 2015, 2015 Xth International Scientific and Technical Conference "Computer Sciences and Information Technologies" (CSIT).

[27]  Nathalie Plaziac.  Image interpolation using neural networks , 1999, IEEE Trans. Image Process..