An ensemble vector median filter for color image denoising

Focusing on noise reduction in color images, an ensemble-based vector median filter (EVMF) is proposed, which integrates the technique of vector median filtering into the framework of ensemble learning. The algorithm consists of two main steps: 1) Base filtering step, where a contaminated image is filtered by a group of vector median filters (i.e. base filters) in parallel; 2) Meta-filtering step, where the outputs of all the base filters are fed into a vector median filter (i.e. meta-filter) to obtain the final result. The effectiveness performance of EVMF is evaluated and compared with that of several non-ensemble vector median filtering algorithms through the simulation experiment. The experimental results demonstrate that EVMF outperforms the non-ensemble filtering approaches on both noise suppression and detail preservation.