Salt and Pepper Noise Reduction with a Novel Approach of Noise Models using Median Filter

Image enhancement plays an imperative role in the field of image preprocessing in order to remove noise from images corrupted by various kinds of noise and to extract useful image features. However, the performance of these filters varies for different kinds of noise. In this study, we focus on the techniques which are employed to filter salt-and-pepper noise from the digital images. A comparative study on the performance of the low pass filters and the median filters for removing this kind of impulse noise from the images corrupted up to 90% of noise density is performed. In addition to the impulse noise models implemented in the Boundary Discriminative noise detection (BDND) algorithm, two new noise models are proposed in consideration to handle a high noise environment. The performance metrics like Peak Signal-to-Noise Ratio (PSNR) and Image Enhancement Factor (IEF) are analyzed and compared for the proposed novel noise models using Matlab simulation software tool.