Blur Identification Using Neural Network for Image Restoration

A prior knowledge about the distorting operator and its parameters is of crucial importance in blurred image restoration. In this paper the continuous- valued multilayer neural network based on multi-valued neurons (MLMVN) is exploited for identification of a type of blur among six trained blurs and of its parameters. This network has a number of specific properties and advantages. Its backpropagation learning algorithm does not require differentiability of the activation function. The functionality of the MLMVN is higher than the ones of the traditional feedforward neural networks and a variety of kernel-based networks. Its higher flexibility and faster adaptation to the mapping implemented make possible an accomplishment of complex problems using a simpler network. Therefore, the MLMVN can be used to solve those non- standard recognition and classification problems that cannot be solved using other techniques.

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

[2]  José Mira,et al.  Bio-Inspired Applications of Connectionism , 2001, Lecture Notes in Computer Science.

[3]  A. Murat Tekalp,et al.  Image Recovery: Theory and Application (Henry Stark, ed.) , 1989, SIAM Rev..

[4]  Richard G. Baraniuk,et al.  ForWaRD: Fourier-wavelet regularized deconvolution for ill-conditioned systems , 2004, IEEE Transactions on Signal Processing.

[5]  Jan Flusser,et al.  Multichannel blind deconvolution of spatially misaligned images , 2005, IEEE Transactions on Image Processing.

[6]  Jaakko Astola,et al.  A spatially adaptive nonparametric regression image deblurring , 2005, IEEE Transactions on Image Processing.

[7]  Robert D. Nowak,et al.  An EM algorithm for wavelet-based image restoration , 2003, IEEE Trans. Image Process..

[8]  Bernd Reusch.  Computational Intelligence, Theory and Applications , 1997 .

[9]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[10]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[11]  Yukio Kosugi,et al.  Rotation-Invariant Image Association for Endoscopic Positional Identification Using Complex-Valued Associative Memories , 2001, IWANN.

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

[13]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[14]  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.

[15]  Yukio Kosugi,et al.  An image storage system using complex-valued associative memories , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Jacek M. Zurada,et al.  Complex-valued multistate neural associative memory , 1996, IEEE Trans. Neural Networks.

[17]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[18]  Constantine Butakoff,et al.  Type of Blur and Blur Parameters Identification Using Neural Network and Its Application to Image Restoration , 2002, ICANN.

[19]  Reginald L. Lagendijk,et al.  Identification and restoration of noisy blurred images using the expectation-maximization algorithm , 1990, IEEE Trans. Acoust. Speech Signal Process..

[20]  Yoram Bresler,et al.  Perfect blind restoration of images blurred by multiple filters: theory and efficient algorithms , 1999, IEEE Trans. Image Process..

[21]  Constantine Butakoff,et al.  Blurred image restoration using the type of blur and blur parameter identification on the neural network , 2002, IS&T/SPIE Electronic Imaging.

[22]  Henry Stark,et al.  Image recovery: Theory and application , 1987 .

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

[24]  Joos Vandewalle,et al.  Multi-Valued and Universal Binary Neurons: Theory, Learning and Applications , 2012 .

[25]  Jaakko Astola,et al.  Image Processing: Algorithms and Systems II , 2003 .

[26]  Thomas S. Huang,et al.  Image processing , 1971 .

[27]  Jacek M. Zurada,et al.  A new design method for the complex-valued multistate Hopfield associative memory , 2003, IEEE Trans. Neural Networks.

[28]  Jaakko Astola,et al.  Multilayer Neural Network based on Multi-Valued Neurons and the Blur Identification Problem , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[29]  Dianne P. O'Leary,et al.  Restoring Images Degraded by Spatially Variant Blur , 1998, SIAM J. Sci. Comput..