Medical image processing using fractal functions
Abstract
In this paper, a comparison was made between a modified methods for repeated engineering modeling in order to increase the accuracy of medical images. A comparison was made between different types in terms of classification accuracy. The lacuinartiy feature has also been used to reduce the noise ratio in the received images. The results showed the importance of fractal IFS in medical pulse compression, where a ratio of (98%) was obtained in reducing noise and a ratio of (0.421) in the gap coefficient was obtained. It separated the diseased tissues from the healthy tissues by applying several multi-fractal factors. Fractal image compression is dependent on subjective similarity, with one part of the image being the same as the other part of a similar image. The partial coding is constantly linked to the grayscale images by dividing a color RGB image into three channels - red, green and blue, and is compressed independently by considering each color segment as a specific gray scale image. Based on the smart neural network, the patterns are distinguished for the medical images used by a few learning time and positive error 0.22%.
Full Text:
PDFDOI: http://dx.doi.org/10.21533/pen.v9i2.1870
Refbacks
- There are currently no refbacks.
Copyright (c) 2021 Maha Abdulameer Kadhim
This work is licensed under a Creative Commons Attribution 4.0 International License.
ISSN: 2303-4521
Digital Object Identifier DOI: 10.21533/pen
This work is licensed under a Creative Commons Attribution 4.0 International License