Fuzzy filter based on interval-valued fuzzy sets for image filtering

Abstract

A new fuzzy image filter controlled by interval-valued fuzzy sets (IVFS) is proposed for removing noise from images. The proposed approach is based on IVFS entropy application. IVFS makes it possible to take into account the total uncertainty inherent to image processing, and particularly noise removal is considered. Interval-valued fuzzy sets entropy is used as a tool to perform histogram analysis in order to find all major homogeneous regions at the first stage. Then, an efficient peak-finding algorithm is employed to identify the most significant peaks of the histogram $(1)$ and a noise filtering process $(2)$ that estimates the original value of each noisy pixel (utilizing the global information from $(1)$ and the local information of the image pixels) is proposed. Experimental results have demonstrated that the proposed filter can outperform some well-known classical and fuzzy filters in preserving image details while suppressing impulse noise and reducing Gaussian noise. The main advantage of the proposed technique is to restrict the number of thresholds or parameters which have to be tuned.