An Early Screening System for the Detection of Diabetic Retinopathy using Image Processing

Abstract

Diabetic Retinopathy (DR) is a leading cause of vision loss. Exudates are one of the significant signs of diabetic retinopathy which is a main cause of blindness that could be prevented with an early screening process In our method, the knowledge of digital image processing is used to diagnose exudates from images of retina. An automatic system to detect and localize the presence of exudates from color fundus images with non-dilated pupils is proposed. First, the image is preprocessed and segmented using CIE Lab color space. The segmented image along with Optic Disc (OD) is chosen. Feature vector based on color and texture are extracted from the selected segment using GLCM . The selected feature vector are then classified as exudates and non-exudates using a K-Nearest Neighbors Classifier. Using a clinical reference model, images with exudates were detected with 97% success rate. The proposed method performs best by segmenting even smaller area of exudates.

Detection of Abnormalities of Retina Due to Diabetic Retinopathy and Age Related Macular Degeneration Using SVM

“…Gaussian shaped curve is used for identifying red lesions. Color based segmentation is done in [10] after converting the input image into L*a*b* color space. In [10], Classification is done using K nearest neighbor approach.…”

“…Color based segmentation is done in [10] after converting the input image into L*a*b* color space. In [10], Classification is done using K nearest neighbor approach. Conversion of RGB images into CIE color space is done in [11].…”

Screening of Damage Regions in Retinopathy Using Segmentation-Color Space Selection

“…Rmasubramanian stated that the image is preprocessed and segmented using CIE Lab color space. The segmented image along with Optic Disc (OD) is chosen [5]. By assessing the algorithm's performance while conducting experiments with the colour space selection, both luminance and colour correction, and background class information, the use of colour in the detection of diabetic retinopathy was quantitatively evaluated by Kauppi et al [6].…”

“…However, if image capturing is conducted using the same camera under the same illuminant then the white point in the transformation can be fixed, e.g. CIE standard illuminant D65 [5].…”

“…However, high correlation between channels, significant perceptual non-linearity with visual perception, device dependency and mixing of chrominance and luminance data make RGB not a very favorable choice for color image processing. Thus we seek for another color spaces which are more suitable for processing [5].…”