DECISION-BASED ADAPTIVE LOW-UPPER-MIDDLE FILTER FOR IMAGE PROCESSING

作者：Lin Tzu Chao^*; Lin Chao Ming

来源：International Journal of Innovative Computing Information and Control, 2011, 7(10): 5977-5990.

• Impulse noise
• Median filter
• Center weighted median filter
• Least mean square

In this paper, an adaptive filter is proposed for improving the performance of median-based filters by preserving image details while effectively suppressing impulse noise. The proposed filter is composed of a noise decision-maker and an adaptive low-upper-middle (LUM) filter. The proposed filter uses a novel approach to judge whether the input pixel is noisy. If a pixel is detected as corrupted, it is classified into one of M blocks, with each block having its own central weight for the LUM filter. Otherwise, it is kept unchanged. The observation vector space is partitioned, and then a learning approach is employed to obtain the adaptive center weight of each block. Based on the least mean square (LMS) algorithm, an iterative learning rule is derived to minimize the mean square error of the filter output. Extensive experimental results demonstrate that the proposed filter outperforms existing median-based filters.

• 出版日期2011-10