Kalman Bucy Filtered Neuro Fuzzy Image Denoising for Medical Image Processing
Keywords:
Neutrosophic Sets, Kalman–Bucy, Fuzzy Segmentation, Image Processing, Neutrosophic Neuro Fuzzy, Image DenoisingAbstract
Neutrosophic sets (NS) have referred to as interval fuzzy sets applied in minimizing the
uncertainty and fuzziness in computer-vision and machine-learning communities and hence
employed for several applications. As far as medical image processing applications are concerned
NSs are obtained as an important technique for de-noising. Also, fuzzy segmentation with machine
and deep learning is determined as a familiar procedure that splits input image into distinct regions
for precise learning. Several research works conducted in different image-processing domains.
However, less works was focused on denoising and segmentation of medical image processing with
minimal time complexity and accuracy. In this work we plan to develop a Kalman–Bucy Filtered
Neutrosophic Neuro Fuzzy Image Denoising (KBF-NNFID) method with the objective of reducing
the noisy artifacts with higher peak signal-to-noise ratio in a computationally efficient manner. First,
medical images obtained from Brain MRI LGG segmentation dataset are subjected to filtering
employing Kalman Bucy Filtering algorithm with series of measurements examined. Second with
the filtered medical images provided as input, uncertainty is handled by utilizing Neutrosophic
Neuro Fuzzy set (NNFS) with help of the membership grade. With the aid of three membership
grades, i.e., truth, indeterminacy and falsity, uncertainty involved in noisy image are said to be
handled in a time efficient manner. By this way, an efficient image denoising process is performed
with better PSNR. Experimental evaluation is carried out using medical images with different
performance metrics such as enhanced PSNR and true positive rate up to 13%, 14% as well
minimum execution time by 38% using medical images.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Neutrosophic Sets and Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.