鲁棒的二维Renyi嫡图像闭值分割快速算法

二维Renyi熵阈值分割算法是经典的图像阈值分割方法,但其性能对椒盐噪声较敏感。针对此不足,引入图像滤波中对椒盐噪声有较好鲁棒性的中值滤波技术,提出了新的二维直方图构造方法。为了进一步提高算法效率,分析了阈值分割目标函数的特点,使用惯性权重递增的粒子群算法对其进行优化。通过实验与原方法比较说明了此方法的优越性。

Fast Robust Thresholding Method Based on Two-dimensional Renyi's Entropy

The thresholding method based on two-dimensional Renyi's entropy is a classical thresholding approach.However, it suffers from the sensitivity to the salt and pepper noise. I}his paper introduced the median filtering method which is robust to the salt and pepper noise into the process of constructing the two-dimensional histogram. To further improve the performance of the algorithm, an improved version of particle swarm optimization with increasing inertia weight was employed. Several experiments show the algorithm is effective.