高性能医学图像三维中值滤波去斑算法与实现

Algorithm and Implementation of High Performance 3-D Median Filter for Medical Image Despeckling

为了满足实时实现三维医学图像去斑应用的需要,本文提出一种新的实现三维中值滤波器的快速算法及其高性能VLSI结构。该方法根据二维数组部分排序结果的分布特征,采用一种三维部分排序技术,有效减少三维中值滤波算法的实现复杂度。理论分析和实验结果表明,该方法可减少约33%的计算复杂度和/或硬件资源需求,从而能有效减少三维中值滤波器软件实现的系统延时和硬件实现的系统成本和功耗。

To achieve real-time 3-D medical image despeckling, a novel fast algorithm and high-performance Very Large Scale Integrated （VLSI） architecture for 3-D median filter were presented. According to the data＇s distributing character of the 2-D array ordered by a 2-D partial sorting technique, the proposed method could efficiently reduce the implementation complexity of the 3-D median filter by using a 3-D partial sorting technique. Theoretical analysis and experimental results demonstrate that the presented method could reduce the computation complexity and/or hardware resources by about 33%, which could significantly decrease the computation delay of the 3-D median filter implemented by software, and/or the hardware cost and power consumption.