【摘要】 提出了一种基于象素分类的自适应滤波去噪方法。在一副图像中,平坦区域的方差较小,边缘和脉冲噪声存在的区域方差较大。根据方差的不同,对不同区域的中心象素分类,并采用不同的滤波方式。本文提出的方法,考虑到图像边缘特征细节的保留和整体噪声的消除,用归类的思想,在分类即细节的保留后,进一步对相同类中的象素点进行平滑去噪。这样可以使边缘点和非边缘点分开来,从而最大限度的保留图像的细节信息。更多还原

【Abstract】 An adaptive algorithm for noise elimination is presented,which is based on thought of pixels classif- ying.In an image,variant of the plain area is less than the edge area and implus noise area.We classify centre pixels of different areas according to the value of the va- riant and use different methods for noise elimination. The method taken in this paper has considered the im- age edge details preserving and the whole noise elimina- tion,after sorting and details preserving by using the thoughts of classifying,and then the similar pixels in same sort will be smoothed.Using this method to differ the edge pixels from un - edge pixels so that the infor- mation of image details can be preserved as possible as we can.更多还原