Modified Gaussian Fuzzy Membership Function for Mixed Noise Reduction from Ultrasound Images

Biswas, Pranab Kumar; Halder, Kalyan Kumar; Sarkar, Arnab

doi:10.1109/icrpset57982.2022.10188550

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the realm of computational imaging, digital images frequently experience the unwelcome presence of noise, which lowers the visual quality and makes it more difficult to accurately analyze and interpret the underlying data. Image noise can come from a number of things, including sensor limitations, transmission faults, ambient conditions, or even inherently flawed image-collecting techniques [4]. Uddin et al proposed an Artificial Neural Network (ANN)-based image denoising method [5].…”

Section: ) Introductionmentioning

confidence: 99%

Enhancing the Quality of 2D and 3D Image Using Block Matching 3D and Fuzzy Hybrid Model Based on Random Noise Reduction

Biswas,

Bushra,

Islam

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Medical imaging has become an important research field that embraces a great variety of sciences. Imaging is the central science of measurement in the diagnosis and treating diseases. The effort of technological progress has made possible human imaging starting from a single molecule to the whole body. A new strategy for suppressing random noise in medical images has been proposed in this research. This methodology is founded on a fuzzy filter which follows BM3D (Block Matching 3D) and fuzzy hybrid model. In this comprehensive study, we address the challenges posed by random noise in 2D and 3D images through a unique approach of image denoising. As high-quality medical imaging (Ultrasound, CT-Scan and MRI) is required to obtain a quick and accurate diagnosis. But the problem is that the image can frequently be contaminated by several types of noises including speckle noise, salt & pepper noise, and Gaussian noise. For RGB and grayscale images, some traditional fuzzy membership function is adeptly employed to eliminate these random noises. But here, our proposed research methodology also encompasses 2D and 3D techniques for medical and non-medical image denoising. This research contributes to advancing the field, offering insights into effective strategies for enhancing the quality and accuracy of images crucial for diagnostic and treatment purposes.

show abstract

Section: ) Introductionmentioning

confidence: 99%