{"title":"Retinal Picture Investigation For The Early Recognition Of Diabetic Retinopathy","authors":"B. Devisri, M. Kavitha","doi":"10.1109/ICSSS54381.2022.9782234","DOIUrl":null,"url":null,"abstract":"Diabetic retinopathy is a diabetes complication that cause damage to eyes and eye sight. It harms the light-delicate tissue in retinal veins at the retina. At the beginning stage, DR patients couldn't find any symptoms, only gentle vision issues they can experience. Recognizing retina fundus disorder ahead of time shields will safeguard the patients from losing their vision and assists the ophthalmologists with applying appropriate therapies that could get rid of the disease or reducing its seriousness. Image processing techniques can decrease the optician's diagnosing work and are utilized to detect the irregularities of fundus pictures which are captured during evaluation. This paper centers around Retinal blood vessels segmentation and discovery of exudates, which assumes to be a significant part in diagnosing the pathologies in early stage and also helps the optometric physician to detect the disease in early stage so as to prevent the DR sufferer from losing the eye sight. The proposed system is divided into two modules. I. Blood vessel segmentation and II. Exudate's detection and classification. The module I includes 1. pre-processing of input color fundus image 2. segmentation & classification. The pre-processing process includes image filtration & image enhancement using Weight Median filter and CLAHE histogram. Followed by pre-processing is Edge based segmentation techniques, declivity operator and morphological operations (Dilation, Thinning, opening and closing) are implemented for segmenting and classifying the retinal arteries. The module II:1. Initialization and Transformation to delineate the optic disk., 2. Nonlinear Diffusion Segmentation 3. Detection and classification of Exudates (Hard and delicate Exudates).","PeriodicalId":186440,"journal":{"name":"2022 8th International Conference on Smart Structures and Systems (ICSSS)","volume":"75 11","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 8th International Conference on Smart Structures and Systems (ICSSS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSSS54381.2022.9782234","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Diabetic retinopathy is a diabetes complication that cause damage to eyes and eye sight. It harms the light-delicate tissue in retinal veins at the retina. At the beginning stage, DR patients couldn't find any symptoms, only gentle vision issues they can experience. Recognizing retina fundus disorder ahead of time shields will safeguard the patients from losing their vision and assists the ophthalmologists with applying appropriate therapies that could get rid of the disease or reducing its seriousness. Image processing techniques can decrease the optician's diagnosing work and are utilized to detect the irregularities of fundus pictures which are captured during evaluation. This paper centers around Retinal blood vessels segmentation and discovery of exudates, which assumes to be a significant part in diagnosing the pathologies in early stage and also helps the optometric physician to detect the disease in early stage so as to prevent the DR sufferer from losing the eye sight. The proposed system is divided into two modules. I. Blood vessel segmentation and II. Exudate's detection and classification. The module I includes 1. pre-processing of input color fundus image 2. segmentation & classification. The pre-processing process includes image filtration & image enhancement using Weight Median filter and CLAHE histogram. Followed by pre-processing is Edge based segmentation techniques, declivity operator and morphological operations (Dilation, Thinning, opening and closing) are implemented for segmenting and classifying the retinal arteries. The module II:1. Initialization and Transformation to delineate the optic disk., 2. Nonlinear Diffusion Segmentation 3. Detection and classification of Exudates (Hard and delicate Exudates).