Title: A unique noise detector developed for the filtering of X-ray images of bone fractures

Authors: A. Selin Vironicka; J.G.R. Sathiaseelan

Addresses: Department of Computer Science, Bishop Heber College (Affiliated to Bharathidasan University), Trichy, 620 017, Tamilnadu, India ' Department of Computer Science, Bishop Heber College (Affiliated to Bharathidasan University), Trichy, 620 017, Tamilnadu, India

Abstract: In various fields, especially in the health division, rapidly developing technologies emerge daily. However, some old techniques are still very popular, efficient, and effective. X-rays are one of these bone fracture detection techniques. However, the size of fractures is sometimes insignificant and cannot be easily detected. Efficient and smart systems should therefore be developed. Image processing is one of the mainly hopeful and extensive medical imaging research fields. Medical imagery is most important because different medical images are diagnosed at different recovery stages. Images may be distorted by noise during diagnosis, or X-ray images may contain noise. Filters are generally used to remove noise from certain image acquisition errors. Filters improve images. This work introduces a two-decision noise detection strategy since filtering system presentation depends on it. We first identify corrupted pixels broadly and then assess if a pixel is corrupt in the second step. The proposed filter worked in extensive simulations.

Keywords: median filter; Gaussian filter; MSE; mean square error; SBMF; switching based median filter; SSIM; structural similarity index metric; PSNR; peak signal to noise ratio.

DOI: 10.1504/IJCBDD.2023.133846

International Journal of Computational Biology and Drug Design, 2023 Vol.15 No.5, pp.377 - 390

Received: 23 Aug 2022
Accepted: 28 Nov 2022
Published online: 04 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article