计算机应用 ›› 2011, Vol. 31 ›› Issue (04): 1037-1039.

• 图形图像技术 • 上一篇    下一篇

基于脉冲耦合神经网络的自适应图像滤波

李海燕,张榆锋,施心陵,陈建华   

  1. 云南大学 信息学院, 昆明 650091
  • 收稿日期:2010-10-11 修回日期:2010-11-18 发布日期:2011-04-08 出版日期:2011-04-01
  • 通讯作者: 李海燕
  • 作者简介:李海燕(1976-),女,云南红河人,副教授,博士,主要研究方向:人工神经网络;
    张榆锋(1965-),男,云南大理人,教授,博士,主要研究方向:生物医学信号检测与处理;
    施心陵(1956-),男,云南昆明人,教授,主要研究方向:智能信号检测与处理;
    陈建华(1964-),男,云南昆明人,教授,博士,主要研究方向:信息编码。
  • 基金资助:
    国家自然科学基金资助项目(61065008);云南大学第二批中青年骨干教师基金、云南大学在职培养博士科研启动基金资助项目(21132014)

Adaptive filtering method for images based on pulse-coupled neural network

Hai-yan LI,Yu-feng ZHANG,Xin-ling SHI,Jian-hua CHEN   

  1. School of Information Science and Engineering, Yunnan University, Kunming Yunnan 650091, China
  • Received:2010-10-11 Revised:2010-11-18 Online:2011-04-08 Published:2011-04-01
  • Contact: Hai-yan LI

摘要: 为有效滤除灰度图像中的椒盐噪声并保留图像的边缘及细节信息,提出一种简化的阈值单向衰减脉冲耦合神经网络(PCNN)点火矩阵自适应图像滤波方法,简化的PCNN结构减少了所需参数并提高了运算速度。该方法通过对PCNN点火矩阵的分析,定位出被噪声污染的像素,只对噪声像素进行滤波,因而有效地保留了图像的细节信息;并根据椒盐噪声的特点,动态估计图像的噪声强度,自适应地选择滤波窗口的大小和滤波次数。实验结果表明提出方法较常见的图像降噪方法在滤波效果、自适应性及保留图像细节方面有明显的优势。

关键词: 脉冲耦合神经网络, 点火矩阵, 椒盐噪声, 图像去噪, 自适应滤波

Abstract: An adaptive filter was proposed to detect and remove pepper and salt noise in an image based on Pulse Coupled Neural Network (PCNN) firing matrix. The PCNN was simplified and a unidirectional decaying threshold was proposed to avoid complex parameter selection and improve processing speed. The noise-polluted pixels were detected through analyzing the PCNN firing matrix, and then only the noisy pixels were filtered by a median filter while protecting image edges and details. The window size of the filter and the filtering time were adaptively determined by calculating the noise intensity of the contaminated image. The experimental results show that the proposed method performs better in removing noise while conserving detailed information than traditional filters do.

Key words: Pulse Coupled Neural Network (PCNN), firing matrix, pepper and salt noise, image denoising, adaptive filtering

中图分类号: