Automated Detection of Hard Exudates in Fundus Images Using Improved OTSU Thresholding and SVM

Gao, Weiwei; Zuo, Jing

doi:10.5121/ijcses.2016.7101

Cited by 7 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within sight of a small number of mistaken shading data, focuses, or vessel twist focuses, the proposed strategy can, in any case, accomplish a precise optic cup limit. "A Cloud-based system for Automatic Glaucoma Screening," we propose a half and half cloud arrangement that comprises of an open cloud level and private cloud level to address these worries [6]. This arrangement offers anyplace access in the open cloud level and stores delicate patients' data just as it performs a savvy evaluation of the disease in the private cloud level [8].…”

Section: Literature Surveymentioning

confidence: 99%

Automated Detection of fundus retinal image using EGODD algorithm

Subha¹,

Mohideen²

2022

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

The developed device is tested for optical disc identification in the retinal image of the fundus. The theme chosen was interesting, as optical disc detection plays a critical role in retinal image processing for recognizing other fundus structures and is essential for identifying eye-related diseases. Because human visual vision has been little researched for optical disc detection and an effort to extract data analytics based on eye eyes, the proposed study first discovers how human perception functions for optical disc detection using a bottom-up visual focus paradigm. Eye-view data as the user conducts basic target-search tasks are obtained from separate user groups made up of experts and no expert groups. Extensive data processing has been carried out to extract eye gazing characteristics such as fixation and using computer approach mark regions in the fundus' retinal picture. Segregated labeled data was used to build up a piece of top-down information to bend the search map to the target area. The resulting Eye-based Optical Disk Detection System (EGODD) was tested through normal machine learning algorithms. This proposed framework has been testedand approved for optical disc detection; however, it can also be applied to other applications.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Automated Detection of fundus retinal image using EGODD algorithm

Subha¹,

Mohideen²

2022

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

show abstract

“…The existing major methods used for image processing to segment electron microscope images include segmentation algorithm based on super pixel [9][10][11][12], segmentation method based on wavelet transform and Gaussian difference [13][14][15], segmentation method based on image block [16][17][18], and segmentation algorithm based on Otsu [19][20][21], segmentation algorithm based on neural network [22][23][24][25], etc. Otsu algorithm has been widely used as the best algorithm to find the global threshold of image, but it has noise sensitivity and can only segment a single target.…”

Section: Introductionmentioning

confidence: 99%

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

Hou,

Zhao,

Cui

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The identification research of hydrogenation catalyst information has always been one of the most important businesses in the chemical industry. In order to aid researchers in efficiently screening high-performance catalyst carriers and tackle the pressing challenge at hand, it is imperative to find a solution for the intelligent recognition of hydrogenation catalyst images. To address the issue of low recognition accuracy caused by adhesion and stacking of hydrogenation catalysts, An image recognition algorithm of hydrogenation catalyst based on FPNC Net was proposed in this paper. In the present study, Resnet50 backbone network was used to extract the features, and spatially-separable convolution kernel was used to extract the multi-scale features of catalyst fringe. In addition, to effectively segment the adhesive regions of stripes, FPN (Feature Pyramid Network) is added to the backbone network for deep and shallow feature fusion. Introducing an attention module to adaptively adjust weights can effectively highlight the target features of the catalyst. The experimental results showed that the FPNC Net model achieved an accuracy of 94.2% and an AP value improvement of 19.37% compared to the original CenterNet model. The improved model demonstrates a significant enhancement in detection accuracy, indicating a high capability for detecting hydrogenation catalyst targets

show abstract

“…Retinal images are known as called fundus images [3]. The vital manifestations of diabetic retinopathy and retinopathy of prematurity and cardiovascular risk are the changes in retinal vasculature, such as haemorrhages, angiogenesis, and increase in vessel tortuosity, blockages and arteriolar-venular diameter ratios [4].…”

Section: Introductionmentioning

confidence: 99%

Fundus Image Enhancement by Using Maximum Entropy and Perona-Malik Diffusion FilterFundus Image Enhancement by Using Maximum Entropy and Perona-Malik Diffusion Filter

2017

Sept. 28-30, 2017 Kuala Lumpur (Malaysia) ESTSD-17, IEREM-17, CBAES-17, LHSSE-17 &Amp; TBFL-17

View full text Add to dashboard Cite

Automated Detection of Hard Exudates in Fundus Images Using Improved OTSU Thresholding and SVM

Cited by 7 publications

References 19 publications

Automated Detection of fundus retinal image using EGODD algorithm

Automated Detection of fundus retinal image using EGODD algorithm

FPNC Net: A hydrogenation catalyst image recognition algorithm based on deep learning

Fundus Image Enhancement by Using Maximum Entropy and Perona-Malik Diffusion FilterFundus Image Enhancement by Using Maximum Entropy and Perona-Malik Diffusion Filter

Contact Info

Product

Resources

About