Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.17559/TV-20150620130712

A new approach of weighted gradient filter for denoising of medical images in the presence of Poisson noise

Khan Bahadar Khan orcid id orcid.org/0000-0003-1409-7571 ; International Islamic University Islamabad Pakistan, FET, IIUI sector H-10, Islamabad, Pakistan
Amir A. Khaliq ; International Islamic University Islamabad Pakistan, Chairman office, FET, IIUI sector H-10, Islamabad, Pakistan
Muhammad Shahid orcid id orcid.org/0000-0001-6142-9861 ; Muhammad Ali Jinnah University Islamabad Pakistan, MAJU, Islamabad Expressway, Kahuta Road, Zone-V, Islamabad, Pakistan
Jawad Ali Shah ; International Islamic University Islamabad Pakistan, FET, IIUI sector H-10, Islamabad, Pakistan


Puni tekst: hrvatski pdf 5.774 Kb

str. 1755-1762

preuzimanja: 465

citiraj

Puni tekst: engleski pdf 5.774 Kb

str. 1755-1762

preuzimanja: 447

citiraj


Sažetak

We propose a Weighted Gradient Filter for denoising of Poisson noise in medical images. In a predefined window, gradient of the centre pixel is averaged out. Gaussian Weighted filter is used on all calculated gradient values. Proposed method is applied on biomedical images X-Rays and then on different general images of LENA and Peppers. Recovery results show that the proposed weighted gradient filter is efficient and has better visual appearance. Moreover, proposed method is computationally very efficient and faster than Non Local Mean (NLM) filter which is an advanced technique for Poisson noise removal. Proposed method results are also better in terms of performance measures parameters i.e. correlation, Peak Signal-to-Noise Ratio (PSNR), Maximum Structural Similarity Index Measure (MSSIM) and Mean Square Error (MSE) than the conventional Median, Wiener and NLM filter.

Ključne riječi

denoising; image filtering; image processing; medical images; Poisson noise

Hrčak ID:

169364

URI

https://hrcak.srce.hr/169364

Datum izdavanja:

29.11.2016.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.858 *