Impulse Noise Removal from Medical Images by Two Stage Quaternion Vector Median Filter

Chanu, P. Roji; Singh, Kh. Manglem

doi:10.1007/s10916-018-1057-8

Cited by 21 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Median filtering adalah salah satu teknik filter yang mengurutkan nilai intensitas sekelompok pixel, kemudian mengganti nilai pixel yang diproses dengan nilai median [4], [5], [9]. Gaussian lowpass filter berfungsi menekan derau yang tergambarkan dari distribusi citra, berfungsi juga untuk mereduksi hambatan atau noise tetapi memberi efek kabur pada citra.…”

Section: Langkahunclassified

Pemilihan Metode Pengurangan Noise Pada Citra Ultrasonografi Ovarium

Eliyani

Maulana

2020

E-LINK

View full text Add to dashboard Cite

Pengurangan noise merupakan upaya untuk memperbaiki kualitas citra yang akan memudahkan tahapan selanjutnya dalam pengolahan citra. Noise Reduction atau mengurangi noise untuk menghasilkan citra lebih baik sehingga informasi data citra tidak hilang dan citra dapat diintepretasikan oleh mata manusia. Penelitian ini menggunakan data gambar ultrasonografi ovarium untuk membantu menganalisa kondisi kesehatan ovarium perempuan. Gambar ultrasonografi ovarium biasanya terdapat noise, metode pengurangan noise yang akan digunakan pada penelitian ini adalah Median Filtering dan Adaptive Median Filtering. Hasil filtering dari 2 metode tersebut akan dibandingkan menggunakan Mean Square Error(MSE) dan Peak Signal To Noise Ratio(PNSR). Ukuran kernel untuk Median Filtering dan Adaptive Median Filtering dipilih sebagai 3x3, 5x5, dan 7x7. Penelitian ini menghasilkan metode filtering dengan kinerja terbaik yaitu Adaptive Median Filtering dengan ukuran window 5x5 yang ditunjukan dari nilai Mean Square Error dan Peak Signal To Noise Ratio .

show abstract

Section: Langkahunclassified

Pemilihan Metode Pengurangan Noise Pada Citra Ultrasonografi Ovarium

Eliyani

Maulana

2020

E-LINK

View full text Add to dashboard Cite

show abstract

“…Although a plethora of impulsive noise suppression algorithms have been proposed [ 28 , 29 , 30 , 31 , 32 ], a family of switching filters show very promising performance [ 33 , 34 , 35 , 36 , 37 , 38 , 39 ], which can only be outperformed by deep learning techniques [ 39 , 40 ]. These switching algorithms separate noise suppression into two steps: impulse detection and impulse correction [ 39 ].…”

Section: Introductionmentioning

confidence: 99%

Decomposed Dissimilarity Measure for Evaluation of Digital Image Denoising

Maliński

2023

Sensors

View full text Add to dashboard Cite

A new approach to the evaluation of digital image denoising algorithms is presented. In the proposed method, the mean absolute error (MAE) is decomposed into three components that reflect the different cases of denoising imperfections. Moreover, aim plots are described, which are designed to be a very clear and intuitive form of presentation of the new decomposed measure. Finally, examples of the application of the decomposed MAE and the aim plots in the evaluation of impulsive noise removal algorithms are presented. The decomposed MAE measure is a hybrid of the image dissimilarity measure and detection performance measures. It provides information about sources of errors such as pixel estimation errors, unnecessary altered pixels, or undetected and uncorrected distorted pixels. It measures the impact of these factors on the overall correction performance. The decomposed MAE is suitable for the evaluation of algorithms that perform a detection of the distortion that affects only a certain fraction of the image pixels.

show abstract

“…A type-2 fuzzy kernel for eliminating impulse noise from the grayscale image has been proposed in [25], which uses the combination of mean and variance for the restoration process. A fuzzy logic technique [26], a direction-weighted mean filter [27], and a Quaternion two-stage filter [28] are applied to eliminate noise from medical images.…”

Section: Introductionmentioning

confidence: 99%

Impulse noise recuperation from grayscale and medical images using supervised curve fitting linear regression and mean filter

Thomas

Krishna

2022

IJEECS

View full text Add to dashboard Cite

Acquisition of images from electronic devices or Transmission of the image through any medium will cause an additional commotion. This study aims to investigate a framework for eliminating impulse noise from grayscale and medical images by utilizing linear regression and a mean filter. Linear regression is a supervised machine learning algorithm that computes the value of a dependent variable based on an independent variable. The value of the recuperating pixel is measured using a curve-fitting, direction-based linear regression approach or applying a mean filter to the noise-free pixels. The efficiency of the proposed technique experiments with benchmark test images and the images of the USC-SIPI and TESTIMAGES data sets. Peak signal-to-noise ratio and structural similarity index metrics are determined to prove the performance of the proposed method. The evaluated results, when compared with the seven recent state-of-the-art techniques, show the superiority of the proposed method in terms of visual quality and accuracy. The proposed model achieves an average PSNR value of 65.21dB and an SSIM value of 0.999 for the reconstruction of medical images, proving its accuracy and efficiency. The impulse noise restoration process helps the radiologist get a clear visual clarity of the DICOM image for diagnosis purposes.

show abstract

Impulse Noise Removal from Medical Images by Two Stage Quaternion Vector Median Filter

Cited by 21 publications

References 8 publications

Pemilihan Metode Pengurangan Noise Pada Citra Ultrasonografi Ovarium

Pemilihan Metode Pengurangan Noise Pada Citra Ultrasonografi Ovarium

Decomposed Dissimilarity Measure for Evaluation of Digital Image Denoising

Impulse noise recuperation from grayscale and medical images using supervised curve fitting linear regression and mean filter

Contact Info

Product

Resources

About