Comparison of different image preprocessing methods used for retinal fundus images

Swathi, C; Anoop, B. K.; Dhas, D. Anto Sahaya; Sanker, S. Perumal

doi:10.1109/icedss.2017.8073677

Cited by 32 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results showed that the adaptive median filter has the best performance in salt & paper noise and the adaptive filter has the best performance for Gaussian noise, but their performance is close to each other, based on our fundus image (6) database noise. The results showed that the adaptive median filter has the best performance compared to other filters.…”

Section: Resultsmentioning

confidence: 75%

“…Noise in an image is undesirable to us as it disrupts and degrades the quality of the image. Noise removal is always a difficult task so as edge preservation when the intensity of the disrupted noise in the original image is high [4], as authors in [5] represents a comparison of different methods used for pre-processing in retinal fundus images and discussed principles, advantages and disadvantages, Here adaptive median filter is found to be better compared to other preprocessing methods, because it have higher PSNR value and lower MSE value in 3 diabetic retinopathy retinal images, and authors in [6], [7] at HRT database and [8] used the median filter for noise removed in fundus retinal images. But the authors at [9] proposed denoising method based on image sequences and an adaptive frame averaging approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Filtering Techniques in Retinal Fundus Images are Evaluated

Vishwanath¹

2023

Preprint

View full text Add to dashboard Cite

The denoising of the fundus images is an essential pre-processing step in glaucoma diagnosis to ensure sufficient qualityfor the Computer Aided Diagnosing (CAD) system. In this paper, we present an evaluation approach for different denoising filters ofeye fundus images that suffer from two different types of noises (Gaussian noise and Salt & Pepper noise), which had been applied tothe retinal images and then various Spatial filtering techniques like linear (Gaussian, mean), nonlinear filtering (median) and adaptivefiltering have been implemented to three types of images (original images, images with salt and pepper noise and images withGaussian noise) and their performance are compared to each other based on evaluation parameters: Mean Squared Error (MSE), PeakSignal Noise Ratio (PSNR) and Structural Similarity (SSIM). The results showed that the adaptive median filter has the bestperformance in salt & paper noise and the adaptive filter has the best performance for Gaussian noise, but their performance is closeto each other. In conclusion, six spatial filters applied to RIM-ONE fundus image database and found that, the adaptive median filterhas the best performance compared to

show abstract

Section: Resultsmentioning

confidence: 75%

Section: Introductionmentioning

confidence: 99%

Spatial Filtering Techniques in Retinal Fundus Images are Evaluated

Vishwanath¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Noise Removal [44] Many denoising algorithms like Gaussian filters, median filters, non-local means denoising, etc. are utilized for removing unwanted noise.…”

Section: Colour Space Transformationmentioning

confidence: 99%

A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images

et al. 2022

View full text Add to dashboard Cite

In recent years, there has been an unprecedented growth in computer vision and deep learning implementation owing to the exponential rise of computation infrastructure. The same was also reflected in retinal image analysis and successful artificial intelligence models were developed for various retinal disease diagnoses using a wide variety of visual markers obtained from eye fundus images. This article presents a comprehensive study of different deep learning strategies employed in recent times for the diagnosis of five major eye diseases, i.e., Diabetic retinopathy, Glaucoma, age-related macular degeneration, Cataract, and Retinopathy of prematurity. This article is organized according to the deep learning implementation process pipeline, where commonly used datasets, evaluation metrics, image pre-processing techniques, and deep learning backbone models are first illustrated followed by an extensive review of different strategies for each of the five mentioned retinal diseases is presented. Finally, this article summarizes eight major research directions available in the field of retinal disease diagnosis and outlines key challenges and future scope for the present research community.

show abstract

“…Uma das principais etapas do pré-processamento é a remoc ¸ão dos ruídos, que são categorizados como: ruído de sal e pimenta (ocorre aleatoriedade do pixel preto e branco); ruído gaussiano (ocorre variac ¸ão do valor da intensidade com a distribuic ¸ão normal de gaussion); e ruído de cintilac ¸ão (contém pixels brancos aleatórios) [Swathi et al 2017]. Outras etapas importantes são o aprimoramento de contraste, correc ¸ão de tonalidade e redimensionamento [Chatterjee et al 2021].…”

Section: Pré-processamento De Imagens De Retinasunclassified

“…O algoritmo de método não linear, por sua vez, aplica o filtro definindo qual pixel está corrompido ou não corrompido. O filtro não linear produz melhor resultado em comparac ¸ão com o filtro linear [Swathi et al 2017].…”

Section: Pré-processamento De Imagens De Retinasunclassified

Computação de Borda versus Computação em Nuvem: Impacto do Pré-processamento de Imagens de Retinas

Künas¹,

Pinto²,

Navaux³

et al. 2022

Anais Do XXIII Simpósio Em Sistemas Computacionais De Alto Desempenho (SSCAD 2022)

View full text Add to dashboard Cite

Na área da saúde, a prevenção é uma forma eficaz de evitar a progressão de doenças, muitas das quais podem ser tratadas quando diagnosticadas precocemente. A procura por exames preventivos tem aumentado e não se consegue atender essa procura com eficiência. Logo, existe a necessidade de automatizar e aumentar a eficiência de exames de triagem. Entretanto, a captura de dados para estes sistemas geralmente utiliza vários dispositivos de hardware sob condições ambientais diversas, induzindo ruído nos dados. Portanto, antes da fase de triagem, a seleção de uma estrutura de pré-processamento eficaz é fundamental. Neste artigo, é discutido o desenvolvimento de uma aplicação para pré-processamento de imagens de retinas para uso eficiente em sistemas de triagem e o impacto que o pré-processamento causa na interconexão de rede. Foi reduzido em até ≈ 73% o tempo de execução com a versão paralela. Também foi reduzido em ≈ 11,5× a largura de banda utilizada, alcançando taxa de transferência acima de 5 imagens/segundo com pré-processamento na Borda, 2,57× maior do que na Nuvem.

show abstract

Comparison of different image preprocessing methods used for retinal fundus images

Cited by 32 publications

References 0 publications

Spatial Filtering Techniques in Retinal Fundus Images are Evaluated

Spatial Filtering Techniques in Retinal Fundus Images are Evaluated

A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images

Computação de Borda versus Computação em Nuvem: Impacto do Pré-processamento de Imagens de Retinas

Contact Info

Product

Resources

About