PCNN与灰度形态学相结合的图像去噪方法

doi:10.13190/jbupt.200802.108.mayd

北京邮电大学学报 ›› 2008, Vol. 31 ›› Issue (2): 108-112.doi: 10.13190/jbupt.200802.108.mayd

PCNN与灰度形态学相结合的图像去噪方法

马义德，张红娟

兰州大学信息科学与工程学院，兰州 730000

收稿日期:2007-06-08 修回日期:1900-01-01 出版日期:2008-04-28 发布日期:2008-04-28
通讯作者: 马义德

A New Image De-noising Algorithm Combined PCNN with Gray-Scale Morphology

MA Yi-de, ZHANG Hong-juan

School of Information Science & Engineering, Lanzhou University，Lanzhou 730000,China

Received:2007-06-08 Revised:1900-01-01 Online:2008-04-28 Published:2008-04-28
Contact: MA Yi-de

摘要/Abstract

摘要：

通过总结脉冲噪声的特性，将脉冲耦合神经网络(PCNN)与数学形态学相结合，提出了一种基于PCNN与数学形态学的脉冲噪声去除方法。首先利用PCNN的同步脉冲发放特性定位脉冲噪声点的位置；然后利用数学形态学开-闭滤波对其进行去噪处理，并将结果与中值滤波、形态学开-闭滤波及PCNN与中值滤波相结合的方法进行了比较。结果表明，本文方法取得了良好的效果，但是以比中值滤波和形态学滤波更多的运算时间为代价的。在和PCNN与中值滤波相结合的方法结果相当的情况下，本文方法的运算时间较少。

关键词: 脉冲耦合神经网络, 中值滤波, 形态学滤波, 脉冲噪声, 峰值信噪比

Abstract:

Under summarizing the characteristics of pulse noise, the pulse coupled neural network (PCNN) is combined with gray-scale morphology, and a new pulse noise removing algorithm based on PCNN and gray-scale morphology is proposed. Firstly, the noisy points are located using the synchronous pulse burst property of PCNN, then, are processed using the gray-scale open-close filtering. Finally the algorithm is compared with median filtering, gray-scale open-close filtering and with the algorithm combined PCNN with median filtering. Experimental results show that the proposed algorithm performs well。However，it is at a cost of more calculating time than median filtering and gray-scale open-close filtering. But, with similar results, it spends less time than that of the algorithm combined PCNN with median filtering.

Key words: pulse coupled neural network, median filtering, morphological filtering, pulse noise, peak signal-to-noise ratio

中图分类号:

TN911.73

马义德，张红娟. PCNN与灰度形态学相结合的图像去噪方法[J]. 北京邮电大学学报, 2008, 31(2): 108-112.

MA Yi-de, ZHANG Hong-juan
. A New Image De-noising Algorithm Combined PCNN with Gray-Scale Morphology[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2008, 31(2): 108-112.

参考文献

[1] 马义德, 张祥光. 非线性滤波除噪技术综述. (2004-07-09). http://mathchina.com/001/mayd.pdf. Ma Yide, Zhang Xiangguang. The summarize of non-linear filtering and de-noise. (2004-07-09). http://mathchina.com/001/mayd.pdf.
[2] 李玲玲, 余文勇, 陈幼平, 等. 基于数学形态学的灰度线形态识别研究与开发[J]. 计算机工程与应用, 2002, 11: 104-105. Li Lingling, Yu Wenyong, Chen Youping, et al. Research on the recognition system of grey-tone lines using mathematical morphology[J]. Computer Engineering and Applications, 2002, 11: 104-105.
[3] 马义德, 杨淼. 一种彩色柔性形态模糊模型的设计及其实现[J]. 电路与系统学报, 2006, 11(3): 30-35. Ma Yide, Yang Miao. A new kind of fuzzy model for soft morphological color image processing[J]. Journal of Circuits and Systems, 2006, 11(3): 30-35.
[4] 马义德, 张祥光, 杨淼. 基于多结构元广义形态滤波的改进算法[J]. 电子科技大学学报, 2004, 33(4): 391-394. Ma Yide, Zhang Xiangguang, Yang Miao. Improved algorithm of the filter based on the generalized morphological filter with omnidirectional structuring element. Journal of University of Electronic Science and Technology of China, 2004, 33(4): 391-394.
[5] 马义德, 李廉, 王亚馥, 等. 脉冲耦合神经网络原理及其应用[M]. 北京: 科学出版社, 2006: 35-40.
[6] Johnson J L. PCNN models and applications[J]. IEEE Trans on Neural Networks, 1999, 10(3): 480-498.
[7] Ranganath H S. Object detection using pulse coupled neural networks[J]. IEEE Trans on Neural Networks, 1999, 10(3): 615-620.
[8] Lindblad T, Becanovic V. Intelligent detectors modelled from the cats eye[J]. Nucl Instrum Meth A, 1997, 389(122): 245-250.
[9] Skourikhine A N. A pulse couple neural network for image smoothing and segmentation//International Symposium on Computational Intelligence. Kosice, Slovakia: , 2000.
[10] Thhomas L. Inherent features of wavelets and pulse coupled neural networks[J]. IEEE Trans on Neural Networks, 1999, 10(3): 607-614.
[11] Kuntimad G, Ranganath H S. Perfect image segmentation using pulse coupled neural networks[J]. IEEE Trans on Neural Networks, 1999, 10(3): 591-598.
[12] Eckhorn R, Reitboeck H J, Arndt M, et al. Feature linking via synchronization among distributed assemblies: simulations of results from catvisual cortex[J]. Neural Computation, 1990, 2(MIT): 293-307.
[13] Ma Yide, Shi Fei, Li Lian. A new kind of impulse noise filter based on PCNN//IEEE ICNNSP. USA: IEEE Press, 2003: 332-336.
[14] 王咏胜. 基于数学形态学的灰度图像的边缘检测技术的研究. 哈尔滨: 哈尔滨工程大学信息与通信工程学院, 2005. Wang Yongsheng. Research of edge detection for grey-scale image based on mathematical morphology. Harbin: School of Information and Communication Engineering, Harbin Engineering University, 2005.
[15] Wang Wei, Zhao Chunhui, Sun Shenghe. Optimal 2-D stack filter based on omnidirectional structural elements constraints[J]. Journal of Image and Graphics, 1999, 4(6): 445-449.
[16] 赵春晖, 孙圣和. 一类多结构元素并行复合形态滤波器[J]. 哈尔滨工业大学学报, 1997, 29(2): 64-67. Zhao Chunhui, Sun Shenghe. A class of parallel complex morphological filters with multiple structuring elements[J]. Journal of Harbin Institute of Technology, 1997, 29(2): 64-67.
[17] Stevenmon R L, Arce G. Morphological filters: statistical and further syntactic properties[J]. IEEE Trans, 1987, CAS-34(11): 1292-1305.

PCNN与灰度形态学相结合的图像去噪方法

A New Image De-noising Algorithm Combined PCNN with Gray-Scale Morphology

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	陶艺文, 陆阳, 安春燕, 李斌, 赵成林. 脉冲噪声环境下的空闲信道检测方案[J]. 北京邮电大学学报, 2019, 42(1): 41-46.
[2]	宫霄霖，毛瑞全. 结合PCNN和局部维纳滤波的图像去噪[J]. 北京邮电大学学报, 2011, 34(5): 67-70.
[3]	黄文辉,陈仁雷,张家谋. 数字视频图像质量客观测量方法的改进与实现[J]. 北京邮电大学学报, 2005, 28(4): 87-90.
[4]	王建勇,周晓光,廖启征. 基于2级检测的脉冲噪声滤除算法[J]. 北京邮电大学学报, 2005, 28(3): 59-61.
[5]	魏春城, 蔡朝晖, 全子一. 一种数字视频解码器的设计与应用[J]. 北京邮电大学学报, 1998, 21(4): 86-88.