Adaptive image denoising for speckle noise images based on fuzzy logic. Issue 4 (1st June 2020)

• Record Type: Journal Article
• Authors: Yu, Jimin; Chen, Long; Zhou, Shangbo; Wang, Limin; Li, Hantao; Huang, Saiao
• Is Part Of: International journal of imaging systems and technology. Volume 30:Issue 4(2020)
• Page Start: 1132
• Page End: 1142
• Publication Date: 2020-06-01
• Subjects: convolution template -- fuzzy logic -- image denoising -- mask template -- membership function; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22442
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Speckle noise is a kind of ubiquitous noise in medical image, which will damage the texture structure of image and affect the analysis of image structure by doctors. Therefore, we propose an image denoising model based on fuzzy logic, which can eliminate speckle noise in the image well, improve the recognition of the image, and facilitate the acquisition of image information by doctors. The main work arrangement of the algorithm model is to design a membership function that can traverse the noise image and preprocess the noise image to make the image smooth. Then, a mask template of 5 × 5 is designed by the definition of g‐l calculus, and there is mainly an unknown parameter in this template. We design the functional relation between this parameter and the image gradient, which makes the model algorithm adaptive. Finally, the convolution operation is performed between the template and the smooth image. By comparison with the existing mainstream models, the overall denoising effect of this model is better than other models, and the relevant numerical indexes are better than other models. This model is an extension of the denoising model of fuzzy theory, which is beneficial to the future research and development.