一种基于粗集的彩色图像边界噪声迭代滤除方法

An Iterative Filtering Algorithm Based on the Rough Set for Boundary Noise of Color Images

边界噪声的处理在图像去噪中占有重要位置,该文提出了一种图像边界噪声处理方法.该方法将边界噪声和内部噪声分开处理,降低了二者在处理过程中的相互影响.文中将粗集和矢量DDF(Directional Distance Filter)滤波相结合,首先对图像中除边界以外的内部噪声,以迭代的形式进行滤除.由于在内部像素滤除之前已对边界像素进行了检测,因此边界噪声不会作为内部滤波器的输入像素,有效地避免了边界噪声的传播.待内部噪声完全滤除后,再取特定的窗口对边界噪声进行滤除.因为粗集与矢量DDF滤波的结合在噪声滤除率、颜色保持、细节保护各方面都有优势,使得内部噪声像素去除效果比较好,不会影响到边界噪声的去除.仿真实验表明该方法能有效滤除边界噪声.

How to treat boundary noise is crucial in image denoising.A filtering method for boundary noise is proposed,which treats boundary and internal noises separately,therefore reduces the interactive influences between each other.To be precise,the method of the rough set is combined with the Directional Distance Filter（DDF）,first the internal the noise is filtered iteratively.Indeed,the noise from boundaries will not spread since it is singled out before the DDF filtering process.Then,a specific window is taken for filtering the boundary noise after the internal one is removed completely.The combination of the rough set and DDF gives a higher noise filtering rate,and performs well in color keeping and detail preservation.Simulation results show that the method can filter the boundary noise effectively.