Morphological Neural Network Based on QGA for Image Restoration

Zheng Chun Ye; Chun Mei He

doi:10.4028/www.scientific.net/AMM.278-280.1388

Paper Titles

A New Robust Color Image Watermarking Based on DWT and DRT
p.1366

Extracting Palm Vein Patterns Based on Low-Cost Devices
p.1374

Reversible Authentication Scheme of Images Based on Lifting Wavelet Transform
p.1379

A New Denoising Approach for Optical Coherence Tomography Image Based on the Total Variational Model
p.1383

Morphological Neural Network Based on QGA for Image Restoration
p.1388

Hyper-Chaotic Cat Map and its Application in Image Processing
p.1392

A Smart Temperature and Humidity Controller for Tobacco Bulk Curing Barn
p.1399

A Time-Varying Generalized Minimum Variance Controller for Servo Application
p.1403

Adaptive Control of Brushless DC Motors without Model Reduction
p.1409

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280Morphological Neural Network Based on QGA for...

Morphological Neural Network Based on QGA for Image Restoration

Abstract:

A method based on quantum genetic algorithm (QGA) is presented to train and implement morphological neural network (MNN) in this paper. The algorithm adjusts the weights and biases of MNN and the QGA automatically determines the learning rate of the algorithm. Then the trained MNN is applied to image restoration. The image restoration simulation and a comparison with the median filter are shown in the end. We can see that the MNN is a quite good method applied to image restoration.

You might also be interested in these eBooks

Advances in Mechatronics and Control Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 278-280)

Pages:

1388-1391

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.278-280.1388

Citation:

Cite this paper

Online since:

January 2013

Authors:

Zheng Chun Ye, Chun Mei He

Keywords:

Image Restoration, Morphological Neural Network, Quantum Genetic Algorithm

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J.L. Davidson, G.X. Ritter: A theory of morphological neural networks In Digital Optical Computing II, volume 1215 of Proc. of SPIE(1990), pp.378-388.

Google Scholar

[2] G.X. Ritter, P. Sussner: An introduction to Morphological Neural Networks, Proc. 13th Inter. Conf. on Pattern Recognition, Austria, April(1996) pp.709-717.

DOI: 10.1109/icpr.1996.547657

Google Scholar

[3] P. Sussner ,E. Laureano Esmi: Information Science Vol. 181(10) (2011) p.1929-(1950).

Google Scholar

[4] Ling Zhang, Yun Zhang, Yimin Yang. Color image restoration with multilayer Morphological Neural network, Proc. of the second inter. conf. on Machine learning and Cybernetics, Xian(2003) (In Chinese).

DOI: 10.1109/icmlc.2003.1260037

Google Scholar

[5] Chunmei He, Zhengchun Ye, Mu Han and Youpei Ye: Journal of Nanjing University of Science and Technology Vol. 35(5) (2011) pp.664-669(In Chinese).

Google Scholar

[6] A. A Ricardo de.: Neural Networks Vol. 23(2010) pp.1238-1251.

Google Scholar

[7] A. A. Ricardo de, O. Adriano,. An evolutionary approach to design dilation- erosion perceptrons for stock market indices forecasting. Proc. of the 13th annual conf. on Genetic and evolutionary computation (2011) pp.1651-1658.

DOI: 10.1145/2001576.2001799

Google Scholar

[8] Chunmei He, Youpei Ye: International Journal of Intelligent Systems Vol. 26(4) (2011) pp.340-352.

Google Scholar

[9] A. Blanco, M. Delgado, E. Requena: Fuzzy Sets and Systems Vol. 71 (1995) pp.215-226.

Google Scholar