Abstract：Due to the impact of shooting environment, such as light and fuselage vibration, aerial image is often mixed with Gauss noise and impulse noise. Aiming at this characteristics, a new image denoising method based on the pixel peer groups is proposed, which combining the improved median filtering and Wiener filtering. Firstly, the image is divided into a number of pixel peer groups. Then, according to the characteristics of each pixel peer groups, the median filtering or Wiener filtering to filter the image noise was selected. Finally, the simulation experiment is carried out by the use of aerial insulator image. And the experimental results of this paper are compared with the denoising effect of the use of the median filter and the use of Wiener filtering along. The experimental results show that the method in dealing with aerial image noise, which mixed with Gaussian noise and impulse noise, has a good denoising effect.
［1］李洪均,赵志敏,魏本征,等.图像噪声方差大小的测量新算法［J］.计量学报,2012,33(2):121-125.
［2］Munasinghe R, Davari A. Peer groups, neighbor groups, and edge detection［C］//2010 42nd Southeastern Symposium on System Theory (SSST). 2010: 47-50.
［3］何洪英,钱艳萍,王玲,等. 基于像素同龄组和相邻组的绝缘子去噪方法［J］.计算机科学,2012,39(6): 283-284,307.
［4］Kennedy C, Deng Y, Manjunath B S, et al. Peer group image enhancement［J］.IEEE Trans on Image Processing, 2001,10:326-334.
［5］Morillas S, Gregori V, Hervas A. Fuzzy peer groups for reducing mixed Gaussian-impulse noise from color images［J］. Image Processing, IEEE Transactons on, 2009, 18(7):1452-1466.
［6］庞璐璐,李从利.航拍图像噪声分析及滤除方法研究［J］.现代电子技术,2011,23(10):27-29.
［7］马少贤,江成顺.基于四阶偏微分方程的盲图像恢复模型［J］.中国图像图形学报,2010,15(1):26-30.
［8］孙海英.图像高斯噪声及椒盐噪声去噪算法研究 ［D］.上海:复旦大学,2012.
［9］张小波.基于维纳滤波的图像去噪算法研究［D］.陕西:西安电子科技大学,2014.
［10］王洪斌,于菲,李一骏,等.分块特征匹配与局部差分结合的运动目标检测［J］.计量学报,2015,36(4):352-355.
［11］魏文力.航拍输电线路图像处理及故障定位方法［D］.北京:华北电力大学,2014.
2016, Vol. 37 
