Impulse Noise Denoising Using Confidence Measure with Non-sequential Process Order for X-Ray Bio-images

Abstract

Most image denoising methods process each noise-corrupted pixel from the top-left to the bottom-right of the images using a sliding window. By firstly processing a noise-corrupted pixel with plenty of noise neighbor pixels in a local window may deteriorate the quality of subsequent pixels, enabling the quality of the denoised image to be reduced. In this paper, we present a method to change the process order on noise-corrupted pixels to improve the performance of bio-image denoising according to the confidence measure. If the center pixel of a local window with a non-extreme gray value (the pixel value is neither 0 nor 255 for an 8-bit gray bio-image) represents a noise-free pixel, no processing is performed. Conversely, the gray level of the center pixel is modified by a restored value. Two confidence measures are used to determine the order of producing the restored value, including direction confidence and noise-free confidence. An analysis window both with a greater quantity of noise-free pixels and with a consistent pixel change direction is defined as a high confidence region which will be processed firstly. If the variation direction of a pixel is consistent with the neighbor pixels, directional mean filtering is performed. Conversely, median filtering is performed for the pixels with low confidence where the quantity of noise-free pixels is low in a local window or the directions of pixel changes are inconsistent. The experimental results show that the proposed method can further improve the performance of an image denoising method which utilizes the sliding window from the top-left to the bottom-right. The major reason is because of the prior restoration of the noise-corrupted pixels in high confidence regions. These restored pixels are subsequently employed to restore the noise-corrupted pixels with low confidence, resulting in the quality of restored bio-image being improved.