ORDER STATISTIC LAST OUTPUT REFERENCE FILTERS.

Median filtering can be viewed as an operation that selects a sample from each window close to the last output. This observation results in an edge-preserving smoother called the last output reference (LOR) filter. The LOR filter is similar in function to the median or recursive median filters, but has additional advantages particularly in suppressing impulses. It has been shown that repeated applications of LOR filtering produces a sequence that is invariant to subsequent passes through the same filter. Also, it has been proven that any sequence can be converted to a locally monotone sequence by using a combination of forward and backward LOR filters. When the LOR filter is applied to an actual noisy image, it is shown to perform well.