Modification of advanced boundary discriminative noise detection algorithm

Aim at random-valued impulse noise detection in two boundaries, advanced boundary discriminative noise detection(ABDND) used global histogram to obtain noise boundary and got good detection results. However, the rate of false detection increases a lot for ABDND when the range of noise boundary is broadened. Modification of ABDND (MABDND) is proposed based on ABDND in this paper which includes two stages. Firstly, it uses the global histogram to obtain the noise boundary as the same as ABDND. Secondly, the statistic of part histogram is employed to find out pixels of false detection in the first stage, and marks them as uncorrupt pixels. The merit of MABDND is to use the verified technique in the second stage to rectify many pixels of false detection in the first stage so keep a low rate both for miss detection and false detection. Image Lena and Peppers are used for simulations, and the experimental results show the performance of MABDND is better than that of ABDND, especially, when the range of random-valued is wide.