Salt and Pepper Noise Removal Based on GA-BP Algorithm

Abstract:

Noise detection-based median filters have been widely adopted to reduce salt and pepper noise in images. However, since noise pixel is not detected accurately, it is likely to blur the fringe of image under the high noise density. In this paper, we propose an algorithm of salt and pepper noise filter which is based on GA-BP algorithm noise detector to remove the salt and pepper noise in images. The algorithm firstly detect the location of noise pixels by using optimized GA-BP network,then,it introduce edge-preserving function and PRP algorithm to solve the objective function of extreme value further to realize the image denoising. Compared with the traditional algorithms, experimental results show that the proposed algorithm has an evident improvement, and have good characters of generalization, robust and self-adaptive.

• Periodical: Advanced Materials Research (Volumes 301-303)
• Pages: 1243-1248
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.301-303.1243
• Online since: July 2011
• Authors: Yin Mao Song, Xiao Juan Li
• Keywords: Edge-Preserving Function, GA-BP Algorithm, Noise Detection, Pepper Noise, Salt Noise

References

[1] NodesTA, GallagherN C. Median filters: some modifications and their properties[J]. IEEE Transactions on Acoustics, Speech, and SignalProcessing(S 0372-2112), 1982, 30(5): 739~746.

DOI: 10.1109/tassp.1982.1163951

[2] Xing Zang-ju, WangShou-jue, DengHao-jiang, etal. A new filteringalgorithm based on extremum andmedian value[J]. Journalof Imageand Graphics(s1006-8961), 2001, 6(6): 533-536.

[3] Wang Zhou, Zhang David. Progressive switching median filter for the removal of impulse noise from highly corrupted images[J]. IEEE Transactions on Circuits System II(s1051-8215), 1999, 46(1): 78~80.

DOI: 10.1109/82.749102

[4] WANG Yuan-yu, LI Yuan-zong. Edge detection of ceramic substrate based on GA-BP algorithm[J]. Computer Engineering and Design. 2009, 30(14)3455~3457.

[5] R Garnett, T Huegerich, C Chui and W-J He. A universal noise removal algorithm with an impulse detector[J]. IEEE Transactions on Image Processing(S1057-7149), 2005, 14 (11) : 1747–1754.

DOI: 10.1109/tip.2005.857261

[6] McInerney M, Dhawan A P. Use of genetic algorithms with back propagation in training of feed-forward neural networks[C]. Proceedings of IEEE International Conference on Neural Networks, San Francisco（S1057-7149）, 1993: 203-208.

DOI: 10.1109/icnn.1993.298557

[7] Raymond H. Chan, Chung-Wa Ho, and Mila Nikolova. Salt-and-Pepper Noise Removal by Median-Type Noise Detectors and Detail-Preserving Regularization. IEEE Transactions on Image Processing(S1057-7149), 2005, 14(10): 1479-1485.

DOI: 10.1109/tip.2005.852196

[8] HE Kun, ZHOU Ji-liu, LIU Chang, LIU Ran. Low-SNR Image noise removal based on local edge-preserving function[J]. Journal of Sichuan University (Engineering Science Editton), 2009, 41(2): 179~184.

[9] Leah Bar, Nir Sochen, and Nahum Kiryati1. Image Deblurring in the Presence of Salt-and-Pepper Noise[J]. Lecture Notes in Computer Science(S1006-1630), 2005, Volume 3459, Scale Space and PDE Methods in Computer Vision. pp.107-118.

DOI: 10.1007/11408031_10

[10] Bogdan Kwolek. Detail-Preserving Regularization Based Removal of Impulse Noise from Highly Corrupted Images[J]. Lecture Notes in Computer Science(S1006-1630), 2007, Volume 4432, Adaptive and Natural Computing Algorithms. pp.599-605.

DOI: 10.1007/978-3-540-71629-7_67

[11] Yu Gaohang, Guan Luta, Wei Zengxin. A globally convergent polak-Ribière-polyal ponjugate gradient method with Armijo-type line search[J]. Numerical Mathematics a Journal of Chinese Universities: English Series (S 1004-8979), 2006, 15(4): 357-366. 显{TTP}26174 示{TTP}31034 对{TTP}23545 应{TTP}24212 的{TTP}30340 拉{TTP}25289 丁{TTP}19969 字{TTP}23383 符{TTP}31526 的{TTP}30340 拼{TTP}25340 音{TTP}-26637 字{TTP}23383 典{TTP}20856.

DOI: 10.1039/c4ce01928h