ABSTRACT
This paper describes a neural network based multiscale image restoration approach in which multilayer perceptrons are trained with artificial images of degraded gray level cocentered circles. The main objective of this approach is to make the neural network learn inherent space relations of the degraded pixels in the restoration of the image. In the conducted experiment, the degradation is simulated by submitting the image to a low pass Gaussian filter and the addition of noise to the pixels at pre-established rates. The degraded image pixels make the input and the non-degraded image pixels make the output for the supervised learning process. The neural network performs an inverse operation by recovering a quasi non-degraded image in terms of least squared. The main difference of the approach to existing ones relies on the fact that the space relations are taken from different scales, thus providing relational space data to the neural network. The approach is an attempt to develop a simple method that may lead to a good restored version of the image, without the need of a priori knowledge of the possible degradation cause. Considering different window sizes around a pixel simulates the multiscale operation. In the generalization phase the neural network is exposed to indoor, outdoor, and satellite degraded images following the same steps use for the artificial circle image. The neural network restoration results show the proposed approach performs similarly to existing methods with the advantage it does not require a priori knowledge of the degradation causes.
- M. Bertero and P. Boccacci. Int. to Inverse Problems in Imaging. Bristol, Philadelphia, 1998.Google ScholarCross Ref
- F. M. Candocia and A. M. Díaz. A time-domain approach to determining inverse fir filters. In IPCV - International Conference on Image Processing and Computer Vision & Pattern Recognition, volume 1, pages 290--296, Las Vegas, 26--29 June 2006 2006. CSREA Press.Google Scholar
- D. Cao and P. Guo. Blind image restoration based on wavelet analysis. In 2005 International Conference on Machine Learning and Cybernetics, 2005, volume 8, pages 4977- 4982, Guangzhou, 18--21 August 2005 2005. IEEE Press.Google Scholar
- A. P. A. Castro and J. D. S. Silva. Neural network-based multiscale image restoration approach. In Proceeding on Electronic Imaging, volume 6497, pages 3854--3859, San Jose, February 2007. The International Society for Optical Engineering (SPIE2007), January 2007, San Jose, California, USA.Google ScholarCross Ref
- J. Chen, J. Benesty, Y. Huang, and S. Doclo. New insights into the noise reduction wiener filter. IEEE Trans. on Audio, Speech and Language Processing, 14(4):1218--1234, July 2006. Google ScholarDigital Library
- S. Y. Fu, Y. X. Zhang, L. Cheng, Z. Z. Liang, Z. G. Hou, and M. Tan. Motion based image deblur using recurrent neural network for power transmission line inspection robot. International Joint Conference on Neural Networks, pages 3854--3859, July 2006.Google Scholar
- R. C. Gonzalez and R. C. Woods. Digital Image Processing. Addison Wesley, New York, 1992. Google ScholarDigital Library
- S. Haykin. Redes Neurais: Princpios e Prtica. Bookman, Porto Alegre, 2001.Google Scholar
- K. V. D. Heijden. Image Based Measurement Systems. Wiley, New York, 1994.Google Scholar
- A. K. Jain. Fundamentals of digital image processing. Prentice hall, Inc, New Jersey, 1989. Google ScholarDigital Library
- S. Jeon, G. Cho, Y. Huh, S. Jin, and J. Park. Determination of point spread function for a flat-panel x-ray imager and its application in image restoration. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 563(1):167--171, July 2006.Google ScholarCross Ref
- T. Kanungo and Z. Qigong. Solving ill-posed problems with artificial neural networks. Neural Networks, 4(4):477--484, Abril 1991. Google ScholarDigital Library
- T. Kanungo and Z. Qigong. Estimating degradation model parameters using neighborhood pattern distributions: An optimization approach. IEEE Trans. on Pattern Analysis and Machine Intelligence, 26(4):520--524, Abril 2004. Google ScholarDigital Library
- A. D. Kulkarni. Computer Vision and Fuzzy-Neural Systems. Prentice Hall, New Jersey, 2001. Google ScholarDigital Library
- C. S. Lee, S. M. Guo, and C. Y. Hsu. Genetic-based fuzzy image filter and its application to image processing. IEEE Transcations on Systems, Man, and Cybernetics - PartB: Cybernetics, 34(4):694--711, August 2005. Google ScholarDigital Library
- F. Sroubek and J. Flusser. Multichannel blind deconvolution of spatially misaligned images. IEEE Trans. on Image Processing, 14(7):874--883, July 2005. Google ScholarDigital Library
- Y. D. Wu, Q. Z. Zhu, S. X. Sun, and H. Y. Zhang. Image restoration using variational pde-based neural network. Neurocomputing, 69(16--18):2364--2368, October 2006.Google Scholar
- M. E. Yksel. A median/anfis filter for efficient restoration of digital images corrupted by impulse noise. International Journal of Electronics and Communications, 60(10):628--637, October 2006.Google ScholarCross Ref
- Y. T. Zhou and R. Chellappa. Stereo matching using a neural network. In International Conference on Acoustics, Speech, and Signal Processing, volume 2, pages 940--943, 11--14 April 1988 1988.Google ScholarCross Ref
Index Terms
- Restoring images with a multiscale neural network based technique
Recommendations
Research on image restoration algorithms based on BP neural network
AbstractWith the development of information transmission technology and computer technology, information acquisition mode is mainly converted from character to image nowadays. However, in the process of acquiring and transmitting images, image ...
Image Restoration Using a Multilayered Quantum Backpropagation Neural Network
CICN '11: Proceedings of the 2011 International Conference on Computational Intelligence and Communication NetworksThe problem of image restoration in presence of blur and noise has been a very important problem in the domain of digital image processing and computer vision. A quantum inspired back propagation neural network (QBPNN) architecture based on quantum ...
Two image restoration algorithms using variational PDE based neural network
IWCMC '07: Proceedings of the 2007 international conference on Wireless communications and mobile computingIn this paper, based on the modified Hopfield neural network, we present two variational PDEs (Partial Differential Equations) as the regularization terms to the image restoration model. One is based on a harmonic model and the other is based on a total ...
Comments